Compare commits

...

47 Commits

Author SHA1 Message Date
Logan Markewich 2298f42c18 remove advanced concepts section 2023-07-18 20:35:37 -06:00
Logan Markewich a67bfe26ed fix link to node_parser 2023-07-18 19:58:34 -06:00
Logan Markewich d73ac8e718 Update high-level concetps 2023-07-18 19:54:06 -06:00
Logan Markewich 213a68bb0f round out low level modules 2023-07-18 19:13:05 -06:00
Logan Markewich 5bba0de1f3 reorder 2023-07-18 16:44:28 -06:00
Logan Markewich f1d609df5f docs re-generate 2023-07-18 13:57:05 -06:00
Logan Markewich f9f6dc6985 link in modules index 2023-07-18 13:13:42 -06:00
Logan Markewich 4ae690612a flesh out more 2023-07-18 13:09:07 -06:00
Logan Markewich dc74b40c7a add end-to-end examples 2023-07-18 11:48:53 -06:00
Logan Markewich b6b2598119 better org 2023-07-18 09:31:51 -06:00
Logan Markewich e108757255 add more structure 2023-07-17 20:48:48 -06:00
Logan Markewich 3cdc7e3feb re-org top level 2023-07-17 20:48:36 -06:00
Logan Markewich bc1a0fe651 undo organization 2023-07-17 20:48:27 -06:00
Logan Markewich 5752fb6921 organize modules 2023-07-17 20:48:19 -06:00
Logan Markewich f36f4b2dae Revert "organize modules"
This reverts commit 1a3940376a.
2023-07-17 20:46:37 -06:00
Logan Markewich 8ee5503505 Revert "undo organization"
This reverts commit abafa6014c.
2023-07-17 20:46:37 -06:00
Logan Markewich da7199b3e9 Revert "re-org top level"
This reverts commit 452b678450.
2023-07-17 20:46:37 -06:00
Logan Markewich 67be6f373a Revert "add more structure"
This reverts commit d5cbaa9ec7.
2023-07-17 20:46:37 -06:00
Logan Markewich d5cbaa9ec7 add more structure 2023-07-17 20:42:26 -06:00
Logan Markewich 452b678450 re-org top level 2023-07-17 16:53:57 -06:00
Logan Markewich abafa6014c undo organization 2023-07-17 16:53:22 -06:00
Logan Markewich 1a3940376a organize modules 2023-07-17 16:30:32 -06:00
Yi Ding 775be4da64 add next as a dev dep on lint rules 2023-07-17 15:02:40 -07:00
yisding fcd70abc1f Merge pull request #11 from run-llama/docs
doc site
2023-07-17 10:43:26 -07:00
Yi Ding 737623443c add something about contributing to the docs 2023-07-17 10:38:34 -07:00
Yi Ding 07c5aeba13 built out the docs 2023-07-17 09:18:39 -07:00
Yi Ding d16113adbb Added JSDoc to our classes 2023-07-14 14:37:41 -07:00
Yi Ding 4649536f33 doc site 2023-07-12 20:53:17 -07:00
Yi Ding df4b1ad8a3 new LLM interface 2023-07-11 10:18:30 -07:00
Yi Ding 6eb44a4c13 Merge branch 'main' into llm 2023-07-10 07:34:04 -07:00
Yi Ding cdf1685f7c new llm abstraction from Simon 2023-07-10 07:24:59 -07:00
yisding 2f468ab132 Merge pull request #8 from run-llama/stream_responses
[Feature] CallbackManager with onLLMStream and onRetrieve
2023-07-10 07:19:15 -07:00
yisding 1e510093ef Merge pull request #10 from run-llama/listindex_fix
fix to get listindex script working
2023-07-10 07:12:20 -07:00
Sourabh Desai f9520d9374 small bugs 2023-07-10 08:14:32 +00:00
Sourabh Desai 2c141d2528 remove spammy console.log 2023-07-10 07:17:14 +00:00
Sourabh Desai bcca3b896c fix to get listindex script working 2023-07-10 06:58:18 +00:00
Abdul Jamjoom 0bec460937 clean-up 2023-07-09 16:46:34 -07:00
Abdul Jamjoom 5d8d344e1f updated tests 2023-07-09 16:42:58 -07:00
Abdul Jamjoom 81e22587eb add callback and event tracking 2023-07-09 16:31:04 -07:00
Yi Ding 539ec0fe3d try smaller chunks 2023-07-06 21:41:13 -07:00
Yi Ding ebf3bc19fd ContextChatEngine v1 2023-07-06 20:59:10 -07:00
Yi Ding 204b8f5316 chatengine 2023-07-06 08:53:09 -07:00
yisding 71dd461a47 Merge pull request #9 from run-llama/subquestion
SubQuestionQueryEngine
2023-07-05 19:39:11 -07:00
Abdul Jamjoom 35a6795559 polish 2023-07-04 22:34:49 -07:00
Abdul Jamjoom 968109455d Create the CallbackManager with onLLMStream and onRetrieve 2023-07-04 21:53:45 -07:00
Abdul Jamjoom 5487de8c37 Merge branch 'main' of github.com:run-llama/llamascript into stream_responses 2023-07-04 09:34:46 -07:00
Abdul Jamjoom 2a038c00ec unstable checkpoint 2023-07-04 09:27:54 -07:00
193 changed files with 31479 additions and 1174 deletions
+4 -1
View File
@@ -1,5 +1,8 @@
{
"editor.tabSize": 2,
"editor.formatOnSave": true,
"editor.defaultFormatter": "esbenp.prettier-vscode"
"editor.defaultFormatter": "esbenp.prettier-vscode",
"[xml]": {
"editor.defaultFormatter": "redhat.vscode-xml"
}
}
+78
View File
@@ -0,0 +1,78 @@
# Contributing
## Structure
This is a monorepo built with Turborepo
Right now there are two packages of importance:
packages/core which is the main NPM library llamaindex
apps/simple is where the demo code lives
### Turborepo docs
You can checkout how Turborepo works using the built in [README-turborepo.md](README-turborepo.md)
## Getting Started
Install NodeJS. Preferably v18 using nvm or n.
Inside the llamascript directory:
```
npm i -g pnpm ts-node
pnpm install
```
Note: we use pnpm in this repo, which has a lot of the same functionality and CLI options as npm but it does do some things better in a monorepo, like centralizing dependencies and caching.
PNPM's has documentation on its [workspace feature](https://pnpm.io/workspaces) and Turborepo had some [useful documentation also](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks).
### Running Typescript
When we publish to NPM we will have a tsc compiled version of the library in JS. For now, the easiest thing to do is use ts-node.
### Test cases
To run them, run
```
pnpm run test
```
To write new test cases write them in packages/core/src/tests
We use Jest https://jestjs.io/ to write our test cases. Jest comes with a bunch of built in assertions using the expect function: https://jestjs.io/docs/expect
### Demo applications
You can create new demo applications in the apps folder. Just run pnpm init in the folder after you create it to create its own package.json
### Installing packages
To install packages for a specific package or demo application, run
```
pnpm add [NPM Package] --filter [package or application i.e. core or simple]
```
To install packages for every package or application run
```
pnpm add -w [NPM Package]
```
### Docs
To contribute to the docs, go to the docs website folder and run the Docusaurus instance.
```bash
cd apps/docs
pnpm install
pnpm start
```
That should start a webserver which will serve the docs on https://localhost:3000
Any changes you make should be reflected in the browser. If you need to regenerate the API docs and find that your TSDoc isn't getting the updates, feel free to remove apps/docs/api. It will automatically regenerate itself when you run pnpm start again.
+57 -43
View File
@@ -1,64 +1,78 @@
# LlamaScript: LlamaIndex for TS/JS
# LlamaIndex.TS
## Structure
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.
This is a monorepo built with Turborepo
## What is LlamaIndex.TS?
Right now there are two packages of importance:
LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.
packages/core which is the main NPM library @llamaindex/core
## Getting started with an example:
apps/simple is where the demo code lives
LlamaIndex.TS requries Node v18 or higher. You can download it from https://nodejs.org or use https://nvm.sh (our preferred option).
### Turborepo docs
In a new folder:
You can checkout how Turborepo works using the built in [README-turborepo.md](README-turborepo.md)
## Getting Started
Install NodeJS. Preferably v18 using nvm or n.
Inside the llamascript directory:
```
npm i -g pnpm ts-node
pnpm install
```bash
export OPEN_AI_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
npx tsc -init # if needed
pnpm install llamaindex
```
Note: we use pnpm in this repo, which has a lot of the same functionality and CLI options as npm but it does do some things better in a monorepo, like centralizing dependencies and caching.
Create the file example.ts
PNPM's has documentation on its [workspace feature](https://pnpm.io/workspaces) and Turborepo had some [useful documentation also](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks).
```ts
// example.ts
import fs from "fs/promises";
import { Document, VectorStoreIndex } from "llamaindex";
### Running Typescript
async function main() {
// Load essay from abramov.txt in Node
const essay = await fs.readFile(
"node_modules/llamaindex/examples/abramov.txt",
"utf-8"
);
When we publish to NPM we will have a tsc compiled version of the library in JS. For now, the easiest thing to do is use ts-node.
// Create Document object with essay
const document = new Document({ text: essay });
### Test cases
// Split text and create embeddings. Store them in a VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments([document]);
To run them, run
// Query the index
const queryEngine = index.asQueryEngine();
const response = await queryEngine.aquery(
"What did the author do in college?"
);
```
pnpm run test
// Output response
console.log(response.toString());
}
```
To write new test cases write them in packages/core/src/tests
Then you can run it using
We use Jest https://jestjs.io/ to write our test cases. Jest comes with a bunch of built in assertions using the expect function: https://jestjs.io/docs/expect
### Demo applications
You can create new demo applications in the apps folder. Just run pnpm init in the folder after you create it to create its own package.json
### Installing packages
To install packages for a specific package or demo application, run
```
pnpm add [NPM Package] --filter [package or application i.e. core or simple]
```bash
npx ts-node example.ts
```
To install packages for every package or application run
## Core concepts:
```
pnpm add -w [NPM Package]
```
- [Document](packages/core/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
- [Node](packages/core/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
- Indexes: indexes store the Nodes and the embeddings of those nodes.
- [QueryEngine](packages/core/src/QueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected nodes from your Index to give the LLM the context it needs to answer your query.
- [ChatEngine](packages/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indexes.
- [SimplePrompt](packages/core/src/Prompt.ts): A simple standardized function call definition that takes in inputs and puts them in a prebuilt template.
## Contributing:
We are in the very early days of LlamaIndex.TS. If youre interested in hacking on it with us check out our [contributing guide](CONTRIBUTING.md)
## Bugs? Questions?
Please join our Discord! https://discord.com/invite/eN6D2HQ4aX
-4
View File
@@ -1,4 +0,0 @@
module.exports = {
root: true,
extends: ["custom"],
};
+10 -24
View File
@@ -1,34 +1,20 @@
# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
# dependencies
# Dependencies
/node_modules
/.pnp
.pnp.js
# testing
/coverage
# next.js
/.next/
/out/
# production
# Production
/build
# misc
# Generated files
.docusaurus
.cache-loader
# Misc
.DS_Store
*.pem
# debug
npm-debug.log*
yarn-debug.log*
yarn-error.log*
# local env files
.env.local
.env.development.local
.env.test.local
.env.production.local
# vercel
.vercel
npm-debug.log*
yarn-debug.log*
yarn-error.log*
+41
View File
@@ -0,0 +1,41 @@
# Website
This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
### Installation
```
$ yarn
```
### Local Development
```
$ yarn start
```
This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
### Build
```
$ yarn build
```
This command generates static content into the `build` directory and can be served using any static contents hosting service.
### Deployment
Using SSH:
```
$ USE_SSH=true yarn deploy
```
Not using SSH:
```
$ GIT_USER=<Your GitHub username> yarn deploy
```
If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.
-30
View File
@@ -1,30 +0,0 @@
## Getting Started
First, run the development server:
```bash
yarn dev
```
Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
You can start editing the page by modifying `pages/index.js`. The page auto-updates as you edit the file.
[API routes](https://nextjs.org/docs/api-routes/introduction) can be accessed on [http://localhost:3000/api/hello](http://localhost:3000/api/hello). This endpoint can be edited in `pages/api/hello.js`.
The `pages/api` directory is mapped to `/api/*`. Files in this directory are treated as [API routes](https://nextjs.org/docs/api-routes/introduction) instead of React pages.
## Learn More
To learn more about Next.js, take a look at the following resources:
- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
- [Learn Next.js](https://nextjs.org/learn/foundations/about-nextjs) - an interactive Next.js tutorial.
You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js/) - your feedback and contributions are welcome!
## Deploy on Vercel
The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_source=github.com&utm_medium=referral&utm_campaign=turborepo-readme) from the creators of Next.js.
Check out our [Next.js deployment documentation](https://nextjs.org/docs/deployment) for more details.
-11
View File
@@ -1,11 +0,0 @@
export default function RootLayout({
children,
}: {
children: React.ReactNode;
}) {
return (
<html lang="en">
<body>{children}</body>
</html>
);
}
-10
View File
@@ -1,10 +0,0 @@
import { Button, Header } from "ui";
export default function Page() {
return (
<>
<Header text="Docs" />
<Button />
</>
);
}
+3
View File
@@ -0,0 +1,3 @@
module.exports = {
presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
};
Binary file not shown.

After

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 49 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 36 KiB

+2
View File
@@ -0,0 +1,2 @@
label: "API"
position: 4
@@ -0,0 +1,81 @@
---
id: "BaseEmbedding"
title: "Class: BaseEmbedding"
sidebar_label: "BaseEmbedding"
sidebar_position: 0
custom_edit_url: null
---
## Hierarchy
- **`BaseEmbedding`**
↳ [`OpenAIEmbedding`](OpenAIEmbedding.md)
## Constructors
### constructor
**new BaseEmbedding**()
## Methods
### aGetQueryEmbedding
`Abstract` **aGetQueryEmbedding**(`query`): `Promise`<`number`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
#### Returns
`Promise`<`number`[]\>
#### Defined in
[Embedding.ts:206](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L206)
___
### aGetTextEmbedding
`Abstract` **aGetTextEmbedding**(`text`): `Promise`<`number`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
#### Returns
`Promise`<`number`[]\>
#### Defined in
[Embedding.ts:205](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L205)
___
### similarity
**similarity**(`embedding1`, `embedding2`, `mode?`): `number`
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `embedding1` | `number`[] | `undefined` |
| `embedding2` | `number`[] | `undefined` |
| `mode` | [`SimilarityType`](../enums/SimilarityType.md) | `SimilarityType.DEFAULT` |
#### Returns
`number`
#### Defined in
[Embedding.ts:197](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L197)
+120
View File
@@ -0,0 +1,120 @@
---
id: "BaseIndex"
title: "Class: BaseIndex<T>"
sidebar_label: "BaseIndex"
sidebar_position: 0
custom_edit_url: null
---
Indexes are the data structure that we store our nodes and embeddings in so
they can be retrieved for our queries.
## Type parameters
| Name |
| :------ |
| `T` |
## Hierarchy
- **`BaseIndex`**
↳ [`VectorStoreIndex`](VectorStoreIndex.md)
↳ [`ListIndex`](ListIndex.md)
## Constructors
### constructor
**new BaseIndex**<`T`\>(`init`)
#### Type parameters
| Name |
| :------ |
| `T` |
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | [`BaseIndexInit`](../interfaces/BaseIndexInit.md)<`T`\> |
#### Defined in
[BaseIndex.ts:80](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L80)
## Properties
### docStore
**docStore**: `BaseDocumentStore`
#### Defined in
[BaseIndex.ts:75](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L75)
___
### indexStore
`Optional` **indexStore**: `BaseIndexStore`
#### Defined in
[BaseIndex.ts:77](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L77)
___
### indexStruct
**indexStruct**: `T`
#### Defined in
[BaseIndex.ts:78](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L78)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[BaseIndex.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L73)
___
### storageContext
**storageContext**: [`StorageContext`](../interfaces/StorageContext.md)
#### Defined in
[BaseIndex.ts:74](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L74)
___
### vectorStore
`Optional` **vectorStore**: `VectorStore`
#### Defined in
[BaseIndex.ts:76](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L76)
## Methods
### asRetriever
`Abstract` **asRetriever**(): [`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Returns
[`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Defined in
[BaseIndex.ts:89](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L89)
+287
View File
@@ -0,0 +1,287 @@
---
id: "BaseNode"
title: "Class: BaseNode"
sidebar_label: "BaseNode"
sidebar_position: 0
custom_edit_url: null
---
Generic abstract class for retrievable nodes
## Hierarchy
- **`BaseNode`**
↳ [`TextNode`](TextNode.md)
## Constructors
### constructor
**new BaseNode**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`BaseNode`](BaseNode.md)\> |
#### Defined in
[Node.ts:48](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L48)
## Properties
### embedding
`Optional` **embedding**: `number`[]
#### Defined in
[Node.ts:39](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L39)
___
### excludedEmbedMetadataKeys
**excludedEmbedMetadataKeys**: `string`[] = `[]`
#### Defined in
[Node.ts:43](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L43)
___
### excludedLlmMetadataKeys
**excludedLlmMetadataKeys**: `string`[] = `[]`
#### Defined in
[Node.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L44)
___
### hash
**hash**: `string` = `""`
#### Defined in
[Node.ts:46](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L46)
___
### id\_
**id\_**: `string`
#### Defined in
[Node.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L38)
___
### metadata
**metadata**: `Record`<`string`, `any`\> = `{}`
#### Defined in
[Node.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L42)
___
### relationships
**relationships**: `Partial`<`Record`<[`NodeRelationship`](../enums/NodeRelationship.md), [`RelatedNodeType`](../modules.md#relatednodetype)\>\> = `{}`
#### Defined in
[Node.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L45)
## Accessors
### childNodes
`get` **childNodes**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Defined in
[Node.ts:104](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L104)
___
### nextNode
`get` **nextNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Defined in
[Node.ts:84](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L84)
___
### nodeId
`get` **nodeId**(): `string`
#### Returns
`string`
#### Defined in
[Node.ts:58](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L58)
___
### parentNode
`get` **parentNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Defined in
[Node.ts:94](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L94)
___
### prevNode
`get` **prevNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Defined in
[Node.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L72)
___
### sourceNode
`get` **sourceNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Defined in
[Node.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L62)
## Methods
### asRelatedNodeInfo
**asRelatedNodeInfo**(): [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
[`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Defined in
[Node.ts:124](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L124)
___
### getContent
`Abstract` **getContent**(`metadataMode`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) |
#### Returns
`string`
#### Defined in
[Node.ts:54](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L54)
___
### getEmbedding
**getEmbedding**(): `number`[]
#### Returns
`number`[]
#### Defined in
[Node.ts:116](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L116)
___
### getMetadataStr
`Abstract` **getMetadataStr**(`metadataMode`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) |
#### Returns
`string`
#### Defined in
[Node.ts:55](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L55)
___
### getType
`Abstract` **getType**(): [`ObjectType`](../enums/ObjectType.md)
#### Returns
[`ObjectType`](../enums/ObjectType.md)
#### Defined in
[Node.ts:52](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L52)
___
### setContent
`Abstract` **setContent**(`value`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `any` |
#### Returns
`void`
#### Defined in
[Node.ts:56](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L56)
@@ -0,0 +1,83 @@
---
id: "CallbackManager"
title: "Class: CallbackManager"
sidebar_label: "CallbackManager"
sidebar_position: 0
custom_edit_url: null
---
## Implements
- `CallbackManagerMethods`
## Constructors
### constructor
**new CallbackManager**(`handlers?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `handlers?` | `CallbackManagerMethods` |
#### Defined in
[callbacks/CallbackManager.ts:68](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L68)
## Properties
### onLLMStream
`Optional` **onLLMStream**: (`params`: [`StreamCallbackResponse`](../interfaces/StreamCallbackResponse.md)) => `void` \| `Promise`<`void`\>
#### Type declaration
▸ (`params`): `void` \| `Promise`<`void`\>
##### Parameters
| Name | Type |
| :------ | :------ |
| `params` | [`StreamCallbackResponse`](../interfaces/StreamCallbackResponse.md) |
##### Returns
`void` \| `Promise`<`void`\>
#### Implementation of
CallbackManagerMethods.onLLMStream
#### Defined in
[callbacks/CallbackManager.ts:65](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L65)
___
### onRetrieve
`Optional` **onRetrieve**: (`params`: [`RetrievalCallbackResponse`](../interfaces/RetrievalCallbackResponse.md)) => `void` \| `Promise`<`void`\>
#### Type declaration
▸ (`params`): `void` \| `Promise`<`void`\>
##### Parameters
| Name | Type |
| :------ | :------ |
| `params` | [`RetrievalCallbackResponse`](../interfaces/RetrievalCallbackResponse.md) |
##### Returns
`void` \| `Promise`<`void`\>
#### Implementation of
CallbackManagerMethods.onRetrieve
#### Defined in
[callbacks/CallbackManager.ts:66](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L66)
@@ -0,0 +1,113 @@
---
id: "ChatGPTLLMPredictor"
title: "Class: ChatGPTLLMPredictor"
sidebar_label: "ChatGPTLLMPredictor"
sidebar_position: 0
custom_edit_url: null
---
ChatGPTLLMPredictor is a predictor that uses GPT.
## Implements
- [`BaseLLMPredictor`](../interfaces/BaseLLMPredictor.md)
## Constructors
### constructor
**new ChatGPTLLMPredictor**(`props?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `props?` | `Partial`<[`ChatGPTLLMPredictor`](ChatGPTLLMPredictor.md)\> |
#### Defined in
[LLMPredictor.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L26)
## Properties
### callbackManager
`Optional` **callbackManager**: [`CallbackManager`](CallbackManager.md)
#### Defined in
[LLMPredictor.ts:24](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L24)
___
### languageModel
**languageModel**: [`OpenAI`](OpenAI.md)
#### Defined in
[LLMPredictor.ts:23](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L23)
___
### model
**model**: ``"gpt-3.5-turbo"`` \| ``"gpt-3.5-turbo-16k"`` \| ``"gpt-4"`` \| ``"gpt-4-32k"``
#### Defined in
[LLMPredictor.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L21)
___
### retryOnThrottling
• **retryOnThrottling**: `boolean`
#### Defined in
[LLMPredictor.ts:22](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L22)
## Methods
### apredict
▸ **apredict**(`prompt`, `input?`, `parentEvent?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `prompt` | `string` \| [`SimplePrompt`](../modules.md#simpleprompt) |
| `input?` | `Record`<`string`, `string`\> |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<`string`\>
#### Implementation of
[BaseLLMPredictor](../interfaces/BaseLLMPredictor.md).[apredict](../interfaces/BaseLLMPredictor.md#apredict)
#### Defined in
[LLMPredictor.ts:49](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L49)
___
### getLlmMetadata
▸ **getLlmMetadata**(): `Promise`<`void`\>
#### Returns
`Promise`<`void`\>
#### Implementation of
[BaseLLMPredictor](../interfaces/BaseLLMPredictor.md).[getLlmMetadata](../interfaces/BaseLLMPredictor.md#getllmmetadata)
#### Defined in
[LLMPredictor.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L45)
@@ -0,0 +1,105 @@
---
id: "CompactAndRefine"
title: "Class: CompactAndRefine"
sidebar_label: "CompactAndRefine"
sidebar_position: 0
custom_edit_url: null
---
CompactAndRefine is a slight variation of Refine that first compacts the text chunks into the smallest possible number of chunks.
## Hierarchy
- [`Refine`](Refine.md)
**`CompactAndRefine`**
## Constructors
### constructor
**new CompactAndRefine**(`serviceContext`, `textQATemplate?`, `refineTemplate?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext` | [`ServiceContext`](../interfaces/ServiceContext.md) |
| `textQATemplate?` | [`SimplePrompt`](../modules.md#simpleprompt) |
| `refineTemplate?` | [`SimplePrompt`](../modules.md#simpleprompt) |
#### Inherited from
[Refine](Refine.md).[constructor](Refine.md#constructor)
#### Defined in
[ResponseSynthesizer.ts:66](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L66)
## Properties
### refineTemplate
**refineTemplate**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Inherited from
[Refine](Refine.md).[refineTemplate](Refine.md#refinetemplate)
#### Defined in
[ResponseSynthesizer.ts:64](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L64)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Inherited from
[Refine](Refine.md).[serviceContext](Refine.md#servicecontext)
#### Defined in
[ResponseSynthesizer.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L62)
___
### textQATemplate
**textQATemplate**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Inherited from
[Refine](Refine.md).[textQATemplate](Refine.md#textqatemplate)
#### Defined in
[ResponseSynthesizer.ts:63](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L63)
## Methods
### agetResponse
**agetResponse**(`query`, `textChunks`, `prevResponse?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `textChunks` | `string`[] |
| `prevResponse?` | `any` |
#### Returns
`Promise`<`string`\>
#### Overrides
[Refine](Refine.md).[agetResponse](Refine.md#agetresponse)
#### Defined in
[ResponseSynthesizer.ts:152](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L152)
@@ -0,0 +1,148 @@
---
id: "CondenseQuestionChatEngine"
title: "Class: CondenseQuestionChatEngine"
sidebar_label: "CondenseQuestionChatEngine"
sidebar_position: 0
custom_edit_url: null
---
CondenseQuestionChatEngine is used in conjunction with a Index (for example VectorIndex).
It does two steps on taking a user's chat message: first, it condenses the chat message
with the previous chat history into a question with more context.
Then, it queries the underlying Index using the new question with context and returns
the response.
CondenseQuestionChatEngine performs well when the input is primarily questions about the
underlying data. It performs less well when the chat messages are not questions about the
data, or are very referential to previous context.
## Implements
- [`ChatEngine`](../interfaces/ChatEngine.md)
## Constructors
### constructor
**new CondenseQuestionChatEngine**(`init`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | `Object` |
| `init.chatHistory` | [`ChatMessage`](../interfaces/ChatMessage.md)[] |
| `init.condenseMessagePrompt?` | [`SimplePrompt`](../modules.md#simpleprompt) |
| `init.queryEngine` | [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md) |
| `init.serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Defined in
[ChatEngine.ts:75](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L75)
## Properties
### chatHistory
**chatHistory**: [`ChatMessage`](../interfaces/ChatMessage.md)[]
#### Defined in
[ChatEngine.ts:71](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L71)
___
### condenseMessagePrompt
**condenseMessagePrompt**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[ChatEngine.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L73)
___
### queryEngine
**queryEngine**: [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
#### Defined in
[ChatEngine.ts:70](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L70)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[ChatEngine.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L72)
## Methods
### achat
**achat**(`message`, `chatHistory?`): `Promise`<[`Response`](Response.md)\>
Send message along with the class's current chat history to the LLM.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `message` | `string` | |
| `chatHistory?` | [`ChatMessage`](../interfaces/ChatMessage.md)[] | optional chat history if you want to customize the chat history |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[achat](../interfaces/ChatEngine.md#achat)
#### Defined in
[ChatEngine.ts:104](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L104)
___
### acondenseQuestion
`Private` **acondenseQuestion**(`chatHistory`, `question`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `chatHistory` | [`ChatMessage`](../interfaces/ChatMessage.md)[] |
| `question` | `string` |
#### Returns
`Promise`<`string`\>
#### Defined in
[ChatEngine.ts:89](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L89)
___
### reset
**reset**(): `void`
Resets the chat history so that it's empty.
#### Returns
`void`
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[reset](../interfaces/ChatEngine.md#reset)
#### Defined in
[ChatEngine.ts:123](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L123)
@@ -0,0 +1,125 @@
---
id: "ContextChatEngine"
title: "Class: ContextChatEngine"
sidebar_label: "ContextChatEngine"
sidebar_position: 0
custom_edit_url: null
---
ContextChatEngine uses the Index to get the appropriate context for each query.
The context is stored in the system prompt, and the chat history is preserved,
ideally allowing the appropriate context to be surfaced for each query.
## Implements
- [`ChatEngine`](../interfaces/ChatEngine.md)
## Constructors
### constructor
**new ContextChatEngine**(`init`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | `Object` |
| `init.chatHistory?` | [`ChatMessage`](../interfaces/ChatMessage.md)[] |
| `init.chatModel?` | [`OpenAI`](OpenAI.md) |
| `init.retriever` | [`BaseRetriever`](../interfaces/BaseRetriever.md) |
#### Defined in
[ChatEngine.ts:138](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L138)
## Properties
### chatHistory
**chatHistory**: [`ChatMessage`](../interfaces/ChatMessage.md)[]
#### Defined in
[ChatEngine.ts:136](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L136)
___
### chatModel
**chatModel**: [`OpenAI`](OpenAI.md)
#### Defined in
[ChatEngine.ts:135](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L135)
___
### retriever
**retriever**: [`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Defined in
[ChatEngine.ts:134](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L134)
## Methods
### achat
**achat**(`message`, `chatHistory?`): `Promise`<[`Response`](Response.md)\>
Send message along with the class's current chat history to the LLM.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `message` | `string` | |
| `chatHistory?` | [`ChatMessage`](../interfaces/ChatMessage.md)[] | optional chat history if you want to customize the chat history |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[achat](../interfaces/ChatEngine.md#achat)
#### Defined in
[ChatEngine.ts:153](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L153)
___
### chatRepl
**chatRepl**(): `void`
#### Returns
`void`
#### Defined in
[ChatEngine.ts:149](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L149)
___
### reset
**reset**(): `void`
Resets the chat history so that it's empty.
#### Returns
`void`
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[reset](../interfaces/ChatEngine.md#reset)
#### Defined in
[ChatEngine.ts:191](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L191)
+496
View File
@@ -0,0 +1,496 @@
---
id: "Document"
title: "Class: Document"
sidebar_label: "Document"
sidebar_position: 0
custom_edit_url: null
---
A document is just a special text node with a docId.
## Hierarchy
- [`TextNode`](TextNode.md)
**`Document`**
## Constructors
### constructor
**new Document**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`Document`](Document.md)\> |
#### Overrides
[TextNode](TextNode.md).[constructor](TextNode.md#constructor)
#### Defined in
[Node.ts:216](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L216)
## Properties
### embedding
`Optional` **embedding**: `number`[]
#### Inherited from
[TextNode](TextNode.md).[embedding](TextNode.md#embedding)
#### Defined in
[Node.ts:39](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L39)
___
### endCharIdx
`Optional` **endCharIdx**: `number`
#### Inherited from
[TextNode](TextNode.md).[endCharIdx](TextNode.md#endcharidx)
#### Defined in
[Node.ts:139](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L139)
___
### excludedEmbedMetadataKeys
**excludedEmbedMetadataKeys**: `string`[] = `[]`
#### Inherited from
[TextNode](TextNode.md).[excludedEmbedMetadataKeys](TextNode.md#excludedembedmetadatakeys)
#### Defined in
[Node.ts:43](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L43)
___
### excludedLlmMetadataKeys
**excludedLlmMetadataKeys**: `string`[] = `[]`
#### Inherited from
[TextNode](TextNode.md).[excludedLlmMetadataKeys](TextNode.md#excludedllmmetadatakeys)
#### Defined in
[Node.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L44)
___
### hash
**hash**: `string` = `""`
#### Inherited from
[TextNode](TextNode.md).[hash](TextNode.md#hash)
#### Defined in
[Node.ts:46](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L46)
___
### id\_
**id\_**: `string`
#### Inherited from
[TextNode](TextNode.md).[id_](TextNode.md#id_)
#### Defined in
[Node.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L38)
___
### metadata
**metadata**: `Record`<`string`, `any`\> = `{}`
#### Inherited from
[TextNode](TextNode.md).[metadata](TextNode.md#metadata)
#### Defined in
[Node.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L42)
___
### metadataSeparator
**metadataSeparator**: `string` = `"\n"`
#### Inherited from
[TextNode](TextNode.md).[metadataSeparator](TextNode.md#metadataseparator)
#### Defined in
[Node.ts:142](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L142)
___
### relationships
**relationships**: `Partial`<`Record`<[`NodeRelationship`](../enums/NodeRelationship.md), [`RelatedNodeType`](../modules.md#relatednodetype)\>\> = `{}`
#### Inherited from
[TextNode](TextNode.md).[relationships](TextNode.md#relationships)
#### Defined in
[Node.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L45)
___
### startCharIdx
`Optional` **startCharIdx**: `number`
#### Inherited from
[TextNode](TextNode.md).[startCharIdx](TextNode.md#startcharidx)
#### Defined in
[Node.ts:138](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L138)
___
### text
**text**: `string` = `""`
#### Inherited from
[TextNode](TextNode.md).[text](TextNode.md#text)
#### Defined in
[Node.ts:137](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L137)
## Accessors
### childNodes
`get` **childNodes**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Inherited from
TextNode.childNodes
#### Defined in
[Node.ts:104](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L104)
___
### docId
`get` **docId**(): `string`
#### Returns
`string`
#### Defined in
[Node.ts:225](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L225)
___
### nextNode
`get` **nextNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.nextNode
#### Defined in
[Node.ts:84](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L84)
___
### nodeId
`get` **nodeId**(): `string`
#### Returns
`string`
#### Inherited from
TextNode.nodeId
#### Defined in
[Node.ts:58](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L58)
___
### parentNode
`get` **parentNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.parentNode
#### Defined in
[Node.ts:94](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L94)
___
### prevNode
`get` **prevNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.prevNode
#### Defined in
[Node.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L72)
___
### sourceNode
`get` **sourceNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.sourceNode
#### Defined in
[Node.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L62)
## Methods
### asRelatedNodeInfo
**asRelatedNodeInfo**(): [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
[`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
[TextNode](TextNode.md).[asRelatedNodeInfo](TextNode.md#asrelatednodeinfo)
#### Defined in
[Node.ts:124](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L124)
___
### generateHash
**generateHash**(): `void`
#### Returns
`void`
#### Inherited from
[TextNode](TextNode.md).[generateHash](TextNode.md#generatehash)
#### Defined in
[Node.ts:149](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L149)
___
### getContent
**getContent**(`metadataMode?`): `string`
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) | `MetadataMode.NONE` |
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getContent](TextNode.md#getcontent)
#### Defined in
[Node.ts:157](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L157)
___
### getEmbedding
**getEmbedding**(): `number`[]
#### Returns
`number`[]
#### Inherited from
[TextNode](TextNode.md).[getEmbedding](TextNode.md#getembedding)
#### Defined in
[Node.ts:116](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L116)
___
### getMetadataStr
**getMetadataStr**(`metadataMode`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) |
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getMetadataStr](TextNode.md#getmetadatastr)
#### Defined in
[Node.ts:162](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L162)
___
### getNodeInfo
**getNodeInfo**(): `Object`
#### Returns
`Object`
| Name | Type |
| :------ | :------ |
| `end` | `undefined` \| `number` |
| `start` | `undefined` \| `number` |
#### Inherited from
[TextNode](TextNode.md).[getNodeInfo](TextNode.md#getnodeinfo)
#### Defined in
[Node.ts:187](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L187)
___
### getText
**getText**(): `string`
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getText](TextNode.md#gettext)
#### Defined in
[Node.ts:191](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L191)
___
### getType
**getType**(): [`ObjectType`](../enums/ObjectType.md)
#### Returns
[`ObjectType`](../enums/ObjectType.md)
#### Overrides
[TextNode](TextNode.md).[getType](TextNode.md#gettype)
#### Defined in
[Node.ts:221](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L221)
___
### setContent
**setContent**(`value`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `string` |
#### Returns
`void`
#### Inherited from
[TextNode](TextNode.md).[setContent](TextNode.md#setcontent)
#### Defined in
[Node.ts:183](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L183)
@@ -0,0 +1,129 @@
---
id: "InMemoryFileSystem"
title: "Class: InMemoryFileSystem"
sidebar_label: "InMemoryFileSystem"
sidebar_position: 0
custom_edit_url: null
---
A filesystem implementation that stores files in memory.
## Implements
- [`GenericFileSystem`](../interfaces/GenericFileSystem.md)
## Constructors
### constructor
**new InMemoryFileSystem**()
## Properties
### files
`Private` **files**: `Record`<`string`, `any`\> = `{}`
#### Defined in
[storage/FileSystem.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L25)
## Methods
### access
**access**(`path`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
#### Returns
`Promise`<`void`\>
#### Implementation of
[GenericFileSystem](../interfaces/GenericFileSystem.md).[access](../interfaces/GenericFileSystem.md#access)
#### Defined in
[storage/FileSystem.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L38)
___
### mkdir
**mkdir**(`path`, `options?`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`void`\>
#### Implementation of
[GenericFileSystem](../interfaces/GenericFileSystem.md).[mkdir](../interfaces/GenericFileSystem.md#mkdir)
#### Defined in
[storage/FileSystem.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L44)
___
### readFile
**readFile**(`path`, `options?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`string`\>
#### Implementation of
[GenericFileSystem](../interfaces/GenericFileSystem.md).[readFile](../interfaces/GenericFileSystem.md#readfile)
#### Defined in
[storage/FileSystem.ts:31](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L31)
___
### writeFile
**writeFile**(`path`, `content`, `options?`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `content` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`void`\>
#### Implementation of
[GenericFileSystem](../interfaces/GenericFileSystem.md).[writeFile](../interfaces/GenericFileSystem.md#writefile)
#### Defined in
[storage/FileSystem.ts:27](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L27)
+123
View File
@@ -0,0 +1,123 @@
---
id: "IndexDict"
title: "Class: IndexDict"
sidebar_label: "IndexDict"
sidebar_position: 0
custom_edit_url: null
---
The underlying structure of each index.
## Hierarchy
- [`IndexStruct`](IndexStruct.md)
**`IndexDict`**
## Constructors
### constructor
**new IndexDict**(`indexId?`, `summary?`)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `indexId` | `string` | `undefined` |
| `summary` | `undefined` | `undefined` |
#### Inherited from
[IndexStruct](IndexStruct.md).[constructor](IndexStruct.md#constructor)
#### Defined in
[BaseIndex.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L21)
## Properties
### docStore
**docStore**: `Record`<`string`, [`Document`](Document.md)\> = `{}`
#### Defined in
[BaseIndex.ts:36](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L36)
___
### indexId
**indexId**: `string`
#### Inherited from
[IndexStruct](IndexStruct.md).[indexId](IndexStruct.md#indexid)
#### Defined in
[BaseIndex.ts:18](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L18)
___
### nodesDict
**nodesDict**: `Record`<`string`, [`BaseNode`](BaseNode.md)\> = `{}`
#### Defined in
[BaseIndex.ts:35](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L35)
___
### summary
`Optional` **summary**: `string`
#### Inherited from
[IndexStruct](IndexStruct.md).[summary](IndexStruct.md#summary)
#### Defined in
[BaseIndex.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L19)
## Methods
### addNode
**addNode**(`node`, `textId?`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `node` | [`BaseNode`](BaseNode.md) |
| `textId?` | `string` |
#### Returns
`void`
#### Defined in
[BaseIndex.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L45)
___
### getSummary
**getSummary**(): `string`
#### Returns
`string`
#### Overrides
[IndexStruct](IndexStruct.md).[getSummary](IndexStruct.md#getsummary)
#### Defined in
[BaseIndex.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L38)
+112
View File
@@ -0,0 +1,112 @@
---
id: "IndexList"
title: "Class: IndexList"
sidebar_label: "IndexList"
sidebar_position: 0
custom_edit_url: null
---
The underlying structure of each index.
## Hierarchy
- [`IndexStruct`](IndexStruct.md)
**`IndexList`**
## Constructors
### constructor
**new IndexList**(`indexId?`, `summary?`)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `indexId` | `string` | `undefined` |
| `summary` | `undefined` | `undefined` |
#### Inherited from
[IndexStruct](IndexStruct.md).[constructor](IndexStruct.md#constructor)
#### Defined in
[BaseIndex.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L21)
## Properties
### indexId
**indexId**: `string`
#### Inherited from
[IndexStruct](IndexStruct.md).[indexId](IndexStruct.md#indexid)
#### Defined in
[BaseIndex.ts:18](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L18)
___
### nodes
**nodes**: `string`[] = `[]`
#### Defined in
[BaseIndex.ts:52](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L52)
___
### summary
`Optional` **summary**: `string`
#### Inherited from
[IndexStruct](IndexStruct.md).[summary](IndexStruct.md#summary)
#### Defined in
[BaseIndex.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L19)
## Methods
### addNode
**addNode**(`node`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `node` | [`BaseNode`](BaseNode.md) |
#### Returns
`void`
#### Defined in
[BaseIndex.ts:54](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L54)
___
### getSummary
**getSummary**(): `string`
#### Returns
`string`
#### Inherited from
[IndexStruct](IndexStruct.md).[getSummary](IndexStruct.md#getsummary)
#### Defined in
[BaseIndex.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L26)
+492
View File
@@ -0,0 +1,492 @@
---
id: "IndexNode"
title: "Class: IndexNode"
sidebar_label: "IndexNode"
sidebar_position: 0
custom_edit_url: null
---
TextNode is the default node type for text. Most common node type in LlamaIndex.TS
## Hierarchy
- [`TextNode`](TextNode.md)
**`IndexNode`**
## Constructors
### constructor
**new IndexNode**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`TextNode`](TextNode.md)\> |
#### Inherited from
[TextNode](TextNode.md).[constructor](TextNode.md#constructor)
#### Defined in
[Node.ts:144](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L144)
## Properties
### embedding
`Optional` **embedding**: `number`[]
#### Inherited from
[TextNode](TextNode.md).[embedding](TextNode.md#embedding)
#### Defined in
[Node.ts:39](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L39)
___
### endCharIdx
`Optional` **endCharIdx**: `number`
#### Inherited from
[TextNode](TextNode.md).[endCharIdx](TextNode.md#endcharidx)
#### Defined in
[Node.ts:139](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L139)
___
### excludedEmbedMetadataKeys
**excludedEmbedMetadataKeys**: `string`[] = `[]`
#### Inherited from
[TextNode](TextNode.md).[excludedEmbedMetadataKeys](TextNode.md#excludedembedmetadatakeys)
#### Defined in
[Node.ts:43](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L43)
___
### excludedLlmMetadataKeys
**excludedLlmMetadataKeys**: `string`[] = `[]`
#### Inherited from
[TextNode](TextNode.md).[excludedLlmMetadataKeys](TextNode.md#excludedllmmetadatakeys)
#### Defined in
[Node.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L44)
___
### hash
**hash**: `string` = `""`
#### Inherited from
[TextNode](TextNode.md).[hash](TextNode.md#hash)
#### Defined in
[Node.ts:46](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L46)
___
### id\_
**id\_**: `string`
#### Inherited from
[TextNode](TextNode.md).[id_](TextNode.md#id_)
#### Defined in
[Node.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L38)
___
### indexId
**indexId**: `string` = `""`
#### Defined in
[Node.ts:205](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L205)
___
### metadata
**metadata**: `Record`<`string`, `any`\> = `{}`
#### Inherited from
[TextNode](TextNode.md).[metadata](TextNode.md#metadata)
#### Defined in
[Node.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L42)
___
### metadataSeparator
**metadataSeparator**: `string` = `"\n"`
#### Inherited from
[TextNode](TextNode.md).[metadataSeparator](TextNode.md#metadataseparator)
#### Defined in
[Node.ts:142](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L142)
___
### relationships
**relationships**: `Partial`<`Record`<[`NodeRelationship`](../enums/NodeRelationship.md), [`RelatedNodeType`](../modules.md#relatednodetype)\>\> = `{}`
#### Inherited from
[TextNode](TextNode.md).[relationships](TextNode.md#relationships)
#### Defined in
[Node.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L45)
___
### startCharIdx
`Optional` **startCharIdx**: `number`
#### Inherited from
[TextNode](TextNode.md).[startCharIdx](TextNode.md#startcharidx)
#### Defined in
[Node.ts:138](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L138)
___
### text
**text**: `string` = `""`
#### Inherited from
[TextNode](TextNode.md).[text](TextNode.md#text)
#### Defined in
[Node.ts:137](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L137)
## Accessors
### childNodes
`get` **childNodes**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Inherited from
TextNode.childNodes
#### Defined in
[Node.ts:104](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L104)
___
### nextNode
`get` **nextNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.nextNode
#### Defined in
[Node.ts:84](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L84)
___
### nodeId
`get` **nodeId**(): `string`
#### Returns
`string`
#### Inherited from
TextNode.nodeId
#### Defined in
[Node.ts:58](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L58)
___
### parentNode
`get` **parentNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.parentNode
#### Defined in
[Node.ts:94](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L94)
___
### prevNode
`get` **prevNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.prevNode
#### Defined in
[Node.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L72)
___
### sourceNode
`get` **sourceNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
TextNode.sourceNode
#### Defined in
[Node.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L62)
## Methods
### asRelatedNodeInfo
**asRelatedNodeInfo**(): [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
[`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
[TextNode](TextNode.md).[asRelatedNodeInfo](TextNode.md#asrelatednodeinfo)
#### Defined in
[Node.ts:124](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L124)
___
### generateHash
**generateHash**(): `void`
#### Returns
`void`
#### Inherited from
[TextNode](TextNode.md).[generateHash](TextNode.md#generatehash)
#### Defined in
[Node.ts:149](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L149)
___
### getContent
**getContent**(`metadataMode?`): `string`
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) | `MetadataMode.NONE` |
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getContent](TextNode.md#getcontent)
#### Defined in
[Node.ts:157](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L157)
___
### getEmbedding
**getEmbedding**(): `number`[]
#### Returns
`number`[]
#### Inherited from
[TextNode](TextNode.md).[getEmbedding](TextNode.md#getembedding)
#### Defined in
[Node.ts:116](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L116)
___
### getMetadataStr
**getMetadataStr**(`metadataMode`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) |
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getMetadataStr](TextNode.md#getmetadatastr)
#### Defined in
[Node.ts:162](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L162)
___
### getNodeInfo
**getNodeInfo**(): `Object`
#### Returns
`Object`
| Name | Type |
| :------ | :------ |
| `end` | `undefined` \| `number` |
| `start` | `undefined` \| `number` |
#### Inherited from
[TextNode](TextNode.md).[getNodeInfo](TextNode.md#getnodeinfo)
#### Defined in
[Node.ts:187](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L187)
___
### getText
**getText**(): `string`
#### Returns
`string`
#### Inherited from
[TextNode](TextNode.md).[getText](TextNode.md#gettext)
#### Defined in
[Node.ts:191](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L191)
___
### getType
**getType**(): [`ObjectType`](../enums/ObjectType.md)
#### Returns
[`ObjectType`](../enums/ObjectType.md)
#### Overrides
[TextNode](TextNode.md).[getType](TextNode.md#gettype)
#### Defined in
[Node.ts:207](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L207)
___
### setContent
**setContent**(`value`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `string` |
#### Returns
`void`
#### Inherited from
[TextNode](TextNode.md).[setContent](TextNode.md#setcontent)
#### Defined in
[Node.ts:183](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L183)
+68
View File
@@ -0,0 +1,68 @@
---
id: "IndexStruct"
title: "Class: IndexStruct"
sidebar_label: "IndexStruct"
sidebar_position: 0
custom_edit_url: null
---
The underlying structure of each index.
## Hierarchy
- **`IndexStruct`**
↳ [`IndexDict`](IndexDict.md)
↳ [`IndexList`](IndexList.md)
## Constructors
### constructor
**new IndexStruct**(`indexId?`, `summary?`)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `indexId` | `string` | `undefined` |
| `summary` | `undefined` | `undefined` |
#### Defined in
[BaseIndex.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L21)
## Properties
### indexId
**indexId**: `string`
#### Defined in
[BaseIndex.ts:18](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L18)
___
### summary
`Optional` **summary**: `string`
#### Defined in
[BaseIndex.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L19)
## Methods
### getSummary
**getSummary**(): `string`
#### Returns
`string`
#### Defined in
[BaseIndex.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L26)
@@ -0,0 +1,84 @@
---
id: "LLMQuestionGenerator"
title: "Class: LLMQuestionGenerator"
sidebar_label: "LLMQuestionGenerator"
sidebar_position: 0
custom_edit_url: null
---
LLMQuestionGenerator uses the LLM to generate new questions for the LLM using tools and a user query.
## Implements
- [`BaseQuestionGenerator`](../interfaces/BaseQuestionGenerator.md)
## Constructors
### constructor
**new LLMQuestionGenerator**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`LLMQuestionGenerator`](LLMQuestionGenerator.md)\> |
#### Defined in
[QuestionGenerator.ts:34](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L34)
## Properties
### llmPredictor
**llmPredictor**: [`BaseLLMPredictor`](../interfaces/BaseLLMPredictor.md)
#### Defined in
[QuestionGenerator.ts:30](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L30)
___
### outputParser
**outputParser**: [`BaseOutputParser`](../interfaces/BaseOutputParser.md)<[`StructuredOutput`](../interfaces/StructuredOutput.md)<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>\>
#### Defined in
[QuestionGenerator.ts:32](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L32)
___
### prompt
**prompt**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[QuestionGenerator.ts:31](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L31)
## Methods
### agenerate
**agenerate**(`tools`, `query`): `Promise`<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `tools` | [`ToolMetadata`](../interfaces/ToolMetadata.md)[] |
| `query` | `string` |
#### Returns
`Promise`<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>
#### Implementation of
[BaseQuestionGenerator](../interfaces/BaseQuestionGenerator.md).[agenerate](../interfaces/BaseQuestionGenerator.md#agenerate)
#### Defined in
[QuestionGenerator.ts:40](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L40)
+281
View File
@@ -0,0 +1,281 @@
---
id: "ListIndex"
title: "Class: ListIndex"
sidebar_label: "ListIndex"
sidebar_position: 0
custom_edit_url: null
---
A ListIndex keeps nodes in a sequential list structure
## Hierarchy
- [`BaseIndex`](BaseIndex.md)<[`IndexList`](IndexList.md)\>
**`ListIndex`**
## Constructors
### constructor
**new ListIndex**(`init`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | [`BaseIndexInit`](../interfaces/BaseIndexInit.md)<[`IndexList`](IndexList.md)\> |
#### Overrides
[BaseIndex](BaseIndex.md).[constructor](BaseIndex.md#constructor)
#### Defined in
[index/list/ListIndex.ts:37](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L37)
## Properties
### docStore
**docStore**: `BaseDocumentStore`
#### Inherited from
[BaseIndex](BaseIndex.md).[docStore](BaseIndex.md#docstore)
#### Defined in
[BaseIndex.ts:75](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L75)
___
### indexStore
`Optional` **indexStore**: `BaseIndexStore`
#### Inherited from
[BaseIndex](BaseIndex.md).[indexStore](BaseIndex.md#indexstore)
#### Defined in
[BaseIndex.ts:77](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L77)
___
### indexStruct
**indexStruct**: [`IndexList`](IndexList.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[indexStruct](BaseIndex.md#indexstruct)
#### Defined in
[BaseIndex.ts:78](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L78)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[serviceContext](BaseIndex.md#servicecontext)
#### Defined in
[BaseIndex.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L73)
___
### storageContext
**storageContext**: [`StorageContext`](../interfaces/StorageContext.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[storageContext](BaseIndex.md#storagecontext)
#### Defined in
[BaseIndex.ts:74](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L74)
___
### vectorStore
`Optional` **vectorStore**: `VectorStore`
#### Inherited from
[BaseIndex](BaseIndex.md).[vectorStore](BaseIndex.md#vectorstore)
#### Defined in
[BaseIndex.ts:76](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L76)
## Methods
### \_deleteNode
`Protected` **_deleteNode**(`nodeId`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `nodeId` | `string` |
#### Returns
`void`
#### Defined in
[index/list/ListIndex.ts:140](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L140)
___
### \_insert
`Protected` **_insert**(`nodes`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `nodes` | [`BaseNode`](BaseNode.md)[] |
#### Returns
`void`
#### Defined in
[index/list/ListIndex.ts:134](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L134)
___
### asQueryEngine
**asQueryEngine**(`mode?`): [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `mode` | [`ListRetrieverMode`](../enums/ListRetrieverMode.md) | `ListRetrieverMode.DEFAULT` |
#### Returns
[`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
#### Defined in
[index/list/ListIndex.ts:113](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L113)
___
### asRetriever
**asRetriever**(`mode?`): [`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `mode` | [`ListRetrieverMode`](../enums/ListRetrieverMode.md) | `ListRetrieverMode.DEFAULT` |
#### Returns
[`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Overrides
[BaseIndex](BaseIndex.md).[asRetriever](BaseIndex.md#asretriever)
#### Defined in
[index/list/ListIndex.ts:100](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L100)
___
### getRefDocInfo
**getRefDocInfo**(): `Promise`<`Record`<`string`, `RefDocInfo`\>\>
#### Returns
`Promise`<`Record`<`string`, `RefDocInfo`\>\>
#### Defined in
[index/list/ListIndex.ts:146](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L146)
___
### \_buildIndexFromNodes
`Static` **_buildIndexFromNodes**(`nodes`, `docStore`, `indexStruct?`): `Promise`<[`IndexList`](IndexList.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `nodes` | [`BaseNode`](BaseNode.md)[] |
| `docStore` | `BaseDocumentStore` |
| `indexStruct?` | [`IndexList`](IndexList.md) |
#### Returns
`Promise`<[`IndexList`](IndexList.md)\>
#### Defined in
[index/list/ListIndex.ts:119](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L119)
___
### fromDocuments
`Static` **fromDocuments**(`documents`, `storageContext?`, `serviceContext?`): `Promise`<[`ListIndex`](ListIndex.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `documents` | [`Document`](Document.md)[] |
| `storageContext?` | [`StorageContext`](../interfaces/StorageContext.md) |
| `serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Returns
`Promise`<[`ListIndex`](ListIndex.md)\>
#### Defined in
[index/list/ListIndex.ts:77](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L77)
___
### init
`Static` **init**(`options`): `Promise`<[`ListIndex`](ListIndex.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `options` | `ListIndexOptions` |
#### Returns
`Promise`<[`ListIndex`](ListIndex.md)\>
#### Defined in
[index/list/ListIndex.ts:41](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L41)
@@ -0,0 +1,137 @@
---
id: "ListIndexLLMRetriever"
title: "Class: ListIndexLLMRetriever"
sidebar_label: "ListIndexLLMRetriever"
sidebar_position: 0
custom_edit_url: null
---
LLM retriever for ListIndex.
## Implements
- [`BaseRetriever`](../interfaces/BaseRetriever.md)
## Constructors
### constructor
**new ListIndexLLMRetriever**(`index`, `choiceSelectPrompt?`, `choiceBatchSize?`, `formatNodeBatchFn?`, `parseChoiceSelectAnswerFn?`, `serviceContext?`)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `index` | [`ListIndex`](ListIndex.md) | `undefined` |
| `choiceSelectPrompt?` | [`SimplePrompt`](../modules.md#simpleprompt) | `undefined` |
| `choiceBatchSize` | `number` | `10` |
| `formatNodeBatchFn?` | `NodeFormatterFunction` | `undefined` |
| `parseChoiceSelectAnswerFn?` | `ChoiceSelectParserFunction` | `undefined` |
| `serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) | `undefined` |
#### Defined in
[index/list/ListIndexRetriever.ts:67](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L67)
## Properties
### choiceBatchSize
**choiceBatchSize**: `number`
#### Defined in
[index/list/ListIndexRetriever.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L62)
___
### choiceSelectPrompt
**choiceSelectPrompt**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[index/list/ListIndexRetriever.ts:61](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L61)
___
### formatNodeBatchFn
**formatNodeBatchFn**: `NodeFormatterFunction`
#### Defined in
[index/list/ListIndexRetriever.ts:63](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L63)
___
### index
**index**: [`ListIndex`](ListIndex.md)
#### Defined in
[index/list/ListIndexRetriever.ts:60](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L60)
___
### parseChoiceSelectAnswerFn
**parseChoiceSelectAnswerFn**: `ChoiceSelectParserFunction`
#### Defined in
[index/list/ListIndexRetriever.ts:64](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L64)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[index/list/ListIndexRetriever.ts:65](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L65)
## Methods
### aretrieve
**aretrieve**(`query`, `parentEvent?`): `Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[aretrieve](../interfaces/BaseRetriever.md#aretrieve)
#### Defined in
[index/list/ListIndexRetriever.ts:84](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L84)
___
### getServiceContext
**getServiceContext**(): [`ServiceContext`](../interfaces/ServiceContext.md)
#### Returns
[`ServiceContext`](../interfaces/ServiceContext.md)
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[getServiceContext](../interfaces/BaseRetriever.md#getservicecontext)
#### Defined in
[index/list/ListIndexRetriever.ts:134](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L134)
@@ -0,0 +1,82 @@
---
id: "ListIndexRetriever"
title: "Class: ListIndexRetriever"
sidebar_label: "ListIndexRetriever"
sidebar_position: 0
custom_edit_url: null
---
Simple retriever for ListIndex that returns all nodes
## Implements
- [`BaseRetriever`](../interfaces/BaseRetriever.md)
## Constructors
### constructor
**new ListIndexRetriever**(`index`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `index` | [`ListIndex`](ListIndex.md) |
#### Defined in
[index/list/ListIndexRetriever.ts:22](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L22)
## Properties
### index
**index**: [`ListIndex`](ListIndex.md)
#### Defined in
[index/list/ListIndexRetriever.ts:20](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L20)
## Methods
### aretrieve
**aretrieve**(`query`, `parentEvent?`): `Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[aretrieve](../interfaces/BaseRetriever.md#aretrieve)
#### Defined in
[index/list/ListIndexRetriever.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L26)
___
### getServiceContext
**getServiceContext**(): [`ServiceContext`](../interfaces/ServiceContext.md)
#### Returns
[`ServiceContext`](../interfaces/ServiceContext.md)
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[getServiceContext](../interfaces/BaseRetriever.md#getservicecontext)
#### Defined in
[index/list/ListIndexRetriever.ts:51](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndexRetriever.ts#L51)
+193
View File
@@ -0,0 +1,193 @@
---
id: "OpenAI"
title: "Class: OpenAI"
sidebar_label: "OpenAI"
sidebar_position: 0
custom_edit_url: null
---
OpenAI LLM implementation
## Implements
- [`LLM`](../interfaces/LLM.md)
## Constructors
### constructor
**new OpenAI**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`OpenAI`](OpenAI.md)\> |
#### Defined in
[LLM.ts:76](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L76)
## Properties
### callbackManager
`Optional` **callbackManager**: [`CallbackManager`](CallbackManager.md)
#### Defined in
[LLM.ts:74](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L74)
___
### maxRetries
**maxRetries**: `number`
#### Defined in
[LLM.ts:69](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L69)
___
### maxTokens
`Optional` **maxTokens**: `number`
#### Defined in
[LLM.ts:71](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L71)
___
### model
**model**: ``"gpt-3.5-turbo"`` \| ``"gpt-3.5-turbo-16k"`` \| ``"gpt-4"`` \| ``"gpt-4-32k"``
#### Defined in
[LLM.ts:66](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L66)
___
### n
• **n**: `number` = `1`
#### Defined in
[LLM.ts:70](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L70)
___
### openAIKey
• **openAIKey**: ``null`` \| `string` = `null`
#### Defined in
[LLM.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L72)
___
### requestTimeout
• **requestTimeout**: ``null`` \| `number`
#### Defined in
[LLM.ts:68](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L68)
___
### session
• **session**: `OpenAISession`
#### Defined in
[LLM.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L73)
___
### temperature
• **temperature**: `number`
#### Defined in
[LLM.ts:67](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L67)
## Methods
### achat
▸ **achat**(`messages`, `parentEvent?`): `Promise`<[`ChatResponse`](../interfaces/ChatResponse.md)\>
Get a chat response from the LLM
#### Parameters
| Name | Type |
| :------ | :------ |
| `messages` | [`ChatMessage`](../interfaces/ChatMessage.md)[] |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`ChatResponse`](../interfaces/ChatResponse.md)\>
#### Implementation of
[LLM](../interfaces/LLM.md).[achat](../interfaces/LLM.md#achat)
#### Defined in
[LLM.ts:103](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L103)
___
### acomplete
▸ **acomplete**(`prompt`, `parentEvent?`): `Promise`<[`ChatResponse`](../interfaces/ChatResponse.md)\>
Get a prompt completion from the LLM
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `prompt` | `string` | the prompt to complete |
| `parentEvent?` | [`Event`](../interfaces/Event.md) | - |
#### Returns
`Promise`<[`ChatResponse`](../interfaces/ChatResponse.md)\>
#### Implementation of
[LLM](../interfaces/LLM.md).[acomplete](../interfaces/LLM.md#acomplete)
#### Defined in
[LLM.ts:145](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L145)
___
### mapMessageType
▸ **mapMessageType**(`type`): `ChatCompletionRequestMessageRoleEnum`
#### Parameters
| Name | Type |
| :------ | :------ |
| `type` | `MessageType` |
#### Returns
`ChatCompletionRequestMessageRoleEnum`
#### Defined in
[LLM.ts:88](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L88)
@@ -0,0 +1,141 @@
---
id: "OpenAIEmbedding"
title: "Class: OpenAIEmbedding"
sidebar_label: "OpenAIEmbedding"
sidebar_position: 0
custom_edit_url: null
---
## Hierarchy
- [`BaseEmbedding`](BaseEmbedding.md)
**`OpenAIEmbedding`**
## Constructors
### constructor
**new OpenAIEmbedding**()
#### Overrides
[BaseEmbedding](BaseEmbedding.md).[constructor](BaseEmbedding.md#constructor)
#### Defined in
[Embedding.ts:217](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L217)
## Properties
### model
**model**: `TEXT_EMBED_ADA_002`
#### Defined in
[Embedding.ts:215](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L215)
___
### session
**session**: `OpenAISession`
#### Defined in
[Embedding.ts:214](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L214)
## Methods
### \_aGetOpenAIEmbedding
`Private` **_aGetOpenAIEmbedding**(`input`): `Promise`<`number`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `string` |
#### Returns
`Promise`<`number`[]\>
#### Defined in
[Embedding.ts:224](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L224)
___
### aGetQueryEmbedding
**aGetQueryEmbedding**(`query`): `Promise`<`number`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
#### Returns
`Promise`<`number`[]\>
#### Overrides
[BaseEmbedding](BaseEmbedding.md).[aGetQueryEmbedding](BaseEmbedding.md#agetqueryembedding)
#### Defined in
[Embedding.ts:240](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L240)
___
### aGetTextEmbedding
**aGetTextEmbedding**(`text`): `Promise`<`number`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
#### Returns
`Promise`<`number`[]\>
#### Overrides
[BaseEmbedding](BaseEmbedding.md).[aGetTextEmbedding](BaseEmbedding.md#agettextembedding)
#### Defined in
[Embedding.ts:236](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L236)
___
### similarity
**similarity**(`embedding1`, `embedding2`, `mode?`): `number`
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `embedding1` | `number`[] | `undefined` |
| `embedding2` | `number`[] | `undefined` |
| `mode` | [`SimilarityType`](../enums/SimilarityType.md) | `SimilarityType.DEFAULT` |
#### Returns
`number`
#### Inherited from
[BaseEmbedding](BaseEmbedding.md).[similarity](BaseEmbedding.md#similarity)
#### Defined in
[Embedding.ts:197](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L197)
+136
View File
@@ -0,0 +1,136 @@
---
id: "Refine"
title: "Class: Refine"
sidebar_label: "Refine"
sidebar_position: 0
custom_edit_url: null
---
A response builder that uses the query to ask the LLM generate a better response using multiple text chunks.
## Hierarchy
- **`Refine`**
↳ [`CompactAndRefine`](CompactAndRefine.md)
## Implements
- `BaseResponseBuilder`
## Constructors
### constructor
**new Refine**(`serviceContext`, `textQATemplate?`, `refineTemplate?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext` | [`ServiceContext`](../interfaces/ServiceContext.md) |
| `textQATemplate?` | [`SimplePrompt`](../modules.md#simpleprompt) |
| `refineTemplate?` | [`SimplePrompt`](../modules.md#simpleprompt) |
#### Defined in
[ResponseSynthesizer.ts:66](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L66)
## Properties
### refineTemplate
**refineTemplate**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[ResponseSynthesizer.ts:64](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L64)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[ResponseSynthesizer.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L62)
___
### textQATemplate
**textQATemplate**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[ResponseSynthesizer.ts:63](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L63)
## Methods
### agetResponse
**agetResponse**(`query`, `textChunks`, `prevResponse?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `textChunks` | `string`[] |
| `prevResponse?` | `any` |
#### Returns
`Promise`<`string`\>
#### Implementation of
BaseResponseBuilder.agetResponse
#### Defined in
[ResponseSynthesizer.ts:76](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L76)
___
### giveResponseSingle
`Private` **giveResponseSingle**(`queryStr`, `textChunk`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `queryStr` | `string` |
| `textChunk` | `string` |
#### Returns
`Promise`<`string`\>
#### Defined in
[ResponseSynthesizer.ts:95](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L95)
___
### refineResponseSingle
`Private` **refineResponseSingle**(`response`, `queryStr`, `textChunk`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `response` | `string` |
| `queryStr` | `string` |
| `textChunk` | `string` |
#### Returns
`Promise`<`string`\>
#### Defined in
[ResponseSynthesizer.ts:123](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L123)
+74
View File
@@ -0,0 +1,74 @@
---
id: "Response"
title: "Class: Response"
sidebar_label: "Response"
sidebar_position: 0
custom_edit_url: null
---
Respone is the output of a LLM
## Constructors
### constructor
**new Response**(`response`, `sourceNodes?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `response` | `string` |
| `sourceNodes?` | [`BaseNode`](BaseNode.md)[] |
#### Defined in
[Response.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Response.ts#L10)
## Properties
### response
**response**: `string`
#### Defined in
[Response.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Response.ts#L7)
___
### sourceNodes
`Optional` **sourceNodes**: [`BaseNode`](BaseNode.md)[]
#### Defined in
[Response.ts:8](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Response.ts#L8)
## Methods
### getFormattedSources
**getFormattedSources**(): `void`
#### Returns
`void`
#### Defined in
[Response.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Response.ts#L15)
___
### toString
**toString**(): `string`
#### Returns
`string`
#### Defined in
[Response.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Response.ts#L19)
@@ -0,0 +1,69 @@
---
id: "ResponseSynthesizer"
title: "Class: ResponseSynthesizer"
sidebar_label: "ResponseSynthesizer"
sidebar_position: 0
custom_edit_url: null
---
A ResponseSynthesizer is used to generate a response from a query and a list of nodes.
## Constructors
### constructor
**new ResponseSynthesizer**(`«destructured»?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `«destructured»` | `Object` |
|  `responseBuilder?` | `BaseResponseBuilder` |
|  `serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Defined in
[ResponseSynthesizer.ts:225](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L225)
## Properties
### responseBuilder
**responseBuilder**: `BaseResponseBuilder`
#### Defined in
[ResponseSynthesizer.ts:222](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L222)
___
### serviceContext
`Optional` **serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[ResponseSynthesizer.ts:223](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L223)
## Methods
### asynthesize
**asynthesize**(`query`, `nodes`, `parentEvent?`): `Promise`<[`Response`](Response.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `nodes` | [`NodeWithScore`](../interfaces/NodeWithScore.md)[] |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Defined in
[ResponseSynthesizer.ts:237](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L237)
@@ -0,0 +1,74 @@
---
id: "RetrieverQueryEngine"
title: "Class: RetrieverQueryEngine"
sidebar_label: "RetrieverQueryEngine"
sidebar_position: 0
custom_edit_url: null
---
A query engine that uses a retriever to query an index and then synthesizes the response.
## Implements
- [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
## Constructors
### constructor
**new RetrieverQueryEngine**(`retriever`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `retriever` | [`BaseRetriever`](../interfaces/BaseRetriever.md) |
#### Defined in
[QueryEngine.ts:29](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L29)
## Properties
### responseSynthesizer
**responseSynthesizer**: [`ResponseSynthesizer`](ResponseSynthesizer.md)
#### Defined in
[QueryEngine.ts:27](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L27)
___
### retriever
**retriever**: [`BaseRetriever`](../interfaces/BaseRetriever.md)
#### Defined in
[QueryEngine.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L26)
## Methods
### aquery
**aquery**(`query`, `parentEvent?`): `Promise`<[`Response`](Response.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Implementation of
[BaseQueryEngine](../interfaces/BaseQueryEngine.md).[aquery](../interfaces/BaseQueryEngine.md#aquery)
#### Defined in
[QueryEngine.ts:36](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L36)
@@ -0,0 +1,236 @@
---
id: "SentenceSplitter"
title: "Class: SentenceSplitter"
sidebar_label: "SentenceSplitter"
sidebar_position: 0
custom_edit_url: null
---
SentenceSplitter is our default text splitter that supports splitting into sentences, paragraphs, or fixed length chunks with overlap.
## Constructors
### constructor
**new SentenceSplitter**(`chunkSize?`, `chunkOverlap?`, `tokenizer?`, `tokenizerDecoder?`, `paragraphSeparator?`, `chunkingTokenizerFn?`)
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `chunkSize` | `number` | `DEFAULT_CHUNK_SIZE` |
| `chunkOverlap` | `number` | `DEFAULT_CHUNK_OVERLAP` |
| `tokenizer` | `any` | `null` |
| `tokenizerDecoder` | `any` | `null` |
| `paragraphSeparator` | `string` | `"\n\n\n"` |
| `chunkingTokenizerFn` | `any` | `undefined` |
#### Defined in
[TextSplitter.ts:33](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L33)
## Properties
### chunkOverlap
`Private` **chunkOverlap**: `number`
#### Defined in
[TextSplitter.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L26)
___
### chunkSize
`Private` **chunkSize**: `number`
#### Defined in
[TextSplitter.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L25)
___
### chunkingTokenizerFn
`Private` **chunkingTokenizerFn**: `any`
#### Defined in
[TextSplitter.ts:30](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L30)
___
### paragraphSeparator
`Private` **paragraphSeparator**: `string`
#### Defined in
[TextSplitter.ts:29](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L29)
___
### tokenizer
`Private` **tokenizer**: `any`
#### Defined in
[TextSplitter.ts:27](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L27)
___
### tokenizerDecoder
`Private` **tokenizerDecoder**: `any`
#### Defined in
[TextSplitter.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L28)
## Methods
### combineTextSplits
**combineTextSplits**(`newSentenceSplits`, `effectiveChunkSize`): `TextSplit`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `newSentenceSplits` | `SplitRep`[] |
| `effectiveChunkSize` | `number` |
#### Returns
`TextSplit`[]
#### Defined in
[TextSplitter.ts:153](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L153)
___
### getEffectiveChunkSize
`Private` **getEffectiveChunkSize**(`extraInfoStr?`): `number`
#### Parameters
| Name | Type |
| :------ | :------ |
| `extraInfoStr?` | `string` |
#### Returns
`number`
#### Defined in
[TextSplitter.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L72)
___
### getParagraphSplits
**getParagraphSplits**(`text`, `effectiveChunkSize?`): `string`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
| `effectiveChunkSize?` | `number` |
#### Returns
`string`[]
#### Defined in
[TextSplitter.ts:89](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L89)
___
### getSentenceSplits
**getSentenceSplits**(`text`, `effectiveChunkSize?`): `string`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
| `effectiveChunkSize?` | `number` |
#### Returns
`string`[]
#### Defined in
[TextSplitter.ts:115](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L115)
___
### processSentenceSplits
`Private` **processSentenceSplits**(`sentenceSplits`, `effectiveChunkSize`): `SplitRep`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `sentenceSplits` | `string`[] |
| `effectiveChunkSize` | `number` |
#### Returns
`SplitRep`[]
#### Defined in
[TextSplitter.ts:128](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L128)
___
### splitText
**splitText**(`text`, `extraInfoStr?`): `string`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
| `extraInfoStr?` | `string` |
#### Returns
`string`[]
#### Defined in
[TextSplitter.ts:233](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L233)
___
### splitTextWithOverlaps
**splitTextWithOverlaps**(`text`, `extraInfoStr?`): `TextSplit`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `text` | `string` |
| `extraInfoStr?` | `string` |
#### Returns
`TextSplit`[]
#### Defined in
[TextSplitter.ts:205](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/TextSplitter.ts#L205)
@@ -0,0 +1,96 @@
---
id: "SimpleChatEngine"
title: "Class: SimpleChatEngine"
sidebar_label: "SimpleChatEngine"
sidebar_position: 0
custom_edit_url: null
---
SimpleChatEngine is the simplest possible chat engine. Useful for using your own custom prompts.
## Implements
- [`ChatEngine`](../interfaces/ChatEngine.md)
## Constructors
### constructor
**new SimpleChatEngine**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`SimpleChatEngine`](SimpleChatEngine.md)\> |
#### Defined in
[ChatEngine.ts:40](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L40)
## Properties
### chatHistory
**chatHistory**: [`ChatMessage`](../interfaces/ChatMessage.md)[]
#### Defined in
[ChatEngine.ts:37](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L37)
___
### llm
**llm**: [`LLM`](../interfaces/LLM.md)
#### Defined in
[ChatEngine.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L38)
## Methods
### achat
**achat**(`message`, `chatHistory?`): `Promise`<[`Response`](Response.md)\>
Send message along with the class's current chat history to the LLM.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `message` | `string` | |
| `chatHistory?` | [`ChatMessage`](../interfaces/ChatMessage.md)[] | optional chat history if you want to customize the chat history |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[achat](../interfaces/ChatEngine.md#achat)
#### Defined in
[ChatEngine.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L45)
___
### reset
**reset**(): `void`
Resets the chat history so that it's empty.
#### Returns
`void`
#### Implementation of
[ChatEngine](../interfaces/ChatEngine.md).[reset](../interfaces/ChatEngine.md#reset)
#### Defined in
[ChatEngine.ts:54](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L54)
@@ -0,0 +1,114 @@
---
id: "SimpleNodeParser"
title: "Class: SimpleNodeParser"
sidebar_label: "SimpleNodeParser"
sidebar_position: 0
custom_edit_url: null
---
SimpleNodeParser is the default NodeParser. It splits documents into TextNodes using a splitter, by default SentenceSplitter
## Implements
- [`NodeParser`](../interfaces/NodeParser.md)
## Constructors
### constructor
**new SimpleNodeParser**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Object` |
| `init.chunkOverlap?` | `number` |
| `init.chunkSize?` | `number` |
| `init.includeMetadata?` | `boolean` |
| `init.includePrevNextRel?` | `boolean` |
| `init.textSplitter?` | [`SentenceSplitter`](SentenceSplitter.md) |
#### Defined in
[NodeParser.ts:64](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L64)
## Properties
### includeMetadata
**includeMetadata**: `boolean`
#### Defined in
[NodeParser.ts:61](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L61)
___
### includePrevNextRel
**includePrevNextRel**: `boolean`
#### Defined in
[NodeParser.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L62)
___
### textSplitter
**textSplitter**: [`SentenceSplitter`](SentenceSplitter.md)
#### Defined in
[NodeParser.ts:60](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L60)
## Methods
### getNodesFromDocuments
**getNodesFromDocuments**(`documents`): [`TextNode`](TextNode.md)[]
Generate Node objects from documents
#### Parameters
| Name | Type |
| :------ | :------ |
| `documents` | [`Document`](Document.md)[] |
#### Returns
[`TextNode`](TextNode.md)[]
#### Implementation of
[NodeParser](../interfaces/NodeParser.md).[getNodesFromDocuments](../interfaces/NodeParser.md#getnodesfromdocuments)
#### Defined in
[NodeParser.ts:95](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L95)
___
### fromDefaults
`Static` **fromDefaults**(`init?`): [`SimpleNodeParser`](SimpleNodeParser.md)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Object` |
| `init.chunkOverlap?` | `number` |
| `init.chunkSize?` | `number` |
| `init.includeMetadata?` | `boolean` |
| `init.includePrevNextRel?` | `boolean` |
#### Returns
[`SimpleNodeParser`](SimpleNodeParser.md)
#### Defined in
[NodeParser.ts:82](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L82)
@@ -0,0 +1,75 @@
---
id: "SimpleResponseBuilder"
title: "Class: SimpleResponseBuilder"
sidebar_label: "SimpleResponseBuilder"
sidebar_position: 0
custom_edit_url: null
---
A response builder that just concatenates responses.
## Implements
- `BaseResponseBuilder`
## Constructors
### constructor
**new SimpleResponseBuilder**(`serviceContext?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Defined in
[ResponseSynthesizer.ts:37](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L37)
## Properties
### llmPredictor
**llmPredictor**: [`BaseLLMPredictor`](../interfaces/BaseLLMPredictor.md)
#### Defined in
[ResponseSynthesizer.ts:34](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L34)
___
### textQATemplate
**textQATemplate**: [`SimplePrompt`](../modules.md#simpleprompt)
#### Defined in
[ResponseSynthesizer.ts:35](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L35)
## Methods
### agetResponse
**agetResponse**(`query`, `textChunks`, `parentEvent?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `textChunks` | `string`[] |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<`string`\>
#### Implementation of
BaseResponseBuilder.agetResponse
#### Defined in
[ResponseSynthesizer.ts:43](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L43)
@@ -0,0 +1,67 @@
---
id: "SubQuestionOutputParser"
title: "Class: SubQuestionOutputParser"
sidebar_label: "SubQuestionOutputParser"
sidebar_position: 0
custom_edit_url: null
---
SubQuestionOutputParser is used to parse the output of the SubQuestionGenerator.
## Implements
- [`BaseOutputParser`](../interfaces/BaseOutputParser.md)<[`StructuredOutput`](../interfaces/StructuredOutput.md)<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>\>
## Constructors
### constructor
**new SubQuestionOutputParser**()
## Methods
### format
**format**(`output`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `output` | `string` |
#### Returns
`string`
#### Implementation of
[BaseOutputParser](../interfaces/BaseOutputParser.md).[format](../interfaces/BaseOutputParser.md#format)
#### Defined in
[OutputParser.ts:97](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L97)
___
### parse
**parse**(`output`): [`StructuredOutput`](../interfaces/StructuredOutput.md)<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `output` | `string` |
#### Returns
[`StructuredOutput`](../interfaces/StructuredOutput.md)<[`SubQuestion`](../interfaces/SubQuestion.md)[]\>
#### Implementation of
[BaseOutputParser](../interfaces/BaseOutputParser.md).[parse](../interfaces/BaseOutputParser.md#parse)
#### Defined in
[OutputParser.ts:89](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L89)
@@ -0,0 +1,141 @@
---
id: "SubQuestionQueryEngine"
title: "Class: SubQuestionQueryEngine"
sidebar_label: "SubQuestionQueryEngine"
sidebar_position: 0
custom_edit_url: null
---
SubQuestionQueryEngine decomposes a question into subquestions and then
## Implements
- [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
## Constructors
### constructor
**new SubQuestionQueryEngine**(`init`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | `Object` |
| `init.queryEngineTools` | [`QueryEngineTool`](../interfaces/QueryEngineTool.md)[] |
| `init.questionGen` | [`BaseQuestionGenerator`](../interfaces/BaseQuestionGenerator.md) |
| `init.responseSynthesizer` | [`ResponseSynthesizer`](ResponseSynthesizer.md) |
#### Defined in
[QueryEngine.ts:56](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L56)
## Properties
### metadatas
**metadatas**: [`ToolMetadata`](../interfaces/ToolMetadata.md)[]
#### Defined in
[QueryEngine.ts:54](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L54)
___
### queryEngines
**queryEngines**: `Record`<`string`, [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)\>
#### Defined in
[QueryEngine.ts:53](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L53)
___
### questionGen
**questionGen**: [`BaseQuestionGenerator`](../interfaces/BaseQuestionGenerator.md)
#### Defined in
[QueryEngine.ts:52](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L52)
___
### responseSynthesizer
**responseSynthesizer**: [`ResponseSynthesizer`](ResponseSynthesizer.md)
#### Defined in
[QueryEngine.ts:51](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L51)
## Methods
### aquery
**aquery**(`query`): `Promise`<[`Response`](Response.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
#### Returns
`Promise`<[`Response`](Response.md)\>
#### Implementation of
[BaseQueryEngine](../interfaces/BaseQueryEngine.md).[aquery](../interfaces/BaseQueryEngine.md#aquery)
#### Defined in
[QueryEngine.ts:97](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L97)
___
### aquerySubQ
`Private` **aquerySubQ**(`subQ`, `parentEvent?`): `Promise`<``null`` \| [`NodeWithScore`](../interfaces/NodeWithScore.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `subQ` | [`SubQuestion`](../interfaces/SubQuestion.md) |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<``null`` \| [`NodeWithScore`](../interfaces/NodeWithScore.md)\>
#### Defined in
[QueryEngine.ts:128](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L128)
___
### fromDefaults
▸ `Static` **fromDefaults**(`init`): [`SubQuestionQueryEngine`](SubQuestionQueryEngine.md)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | `Object` |
| `init.queryEngineTools` | [`QueryEngineTool`](../interfaces/QueryEngineTool.md)[] |
| `init.questionGen?` | [`BaseQuestionGenerator`](../interfaces/BaseQuestionGenerator.md) |
| `init.responseSynthesizer?` | [`ResponseSynthesizer`](ResponseSynthesizer.md) |
| `init.serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Returns
[`SubQuestionQueryEngine`](SubQuestionQueryEngine.md)
#### Defined in
[QueryEngine.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L73)
@@ -0,0 +1,44 @@
---
id: "TextFileReader"
title: "Class: TextFileReader"
sidebar_label: "TextFileReader"
sidebar_position: 0
custom_edit_url: null
---
Read a .txt file
## Implements
- [`BaseReader`](../interfaces/BaseReader.md)
## Constructors
### constructor
**new TextFileReader**()
## Methods
### loadData
**loadData**(`file`, `fs?`): `Promise`<[`Document`](Document.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `file` | `string` |
| `fs` | [`CompleteFileSystem`](../modules.md#completefilesystem) |
#### Returns
`Promise`<[`Document`](Document.md)[]\>
#### Implementation of
[BaseReader](../interfaces/BaseReader.md).[loadData](../interfaces/BaseReader.md#loaddata)
#### Defined in
[readers/SimpleDirectoryReader.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/readers/SimpleDirectoryReader.ts#L12)
+458
View File
@@ -0,0 +1,458 @@
---
id: "TextNode"
title: "Class: TextNode"
sidebar_label: "TextNode"
sidebar_position: 0
custom_edit_url: null
---
TextNode is the default node type for text. Most common node type in LlamaIndex.TS
## Hierarchy
- [`BaseNode`](BaseNode.md)
**`TextNode`**
↳↳ [`IndexNode`](IndexNode.md)
↳↳ [`Document`](Document.md)
## Constructors
### constructor
**new TextNode**(`init?`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init?` | `Partial`<[`TextNode`](TextNode.md)\> |
#### Overrides
[BaseNode](BaseNode.md).[constructor](BaseNode.md#constructor)
#### Defined in
[Node.ts:144](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L144)
## Properties
### embedding
`Optional` **embedding**: `number`[]
#### Inherited from
[BaseNode](BaseNode.md).[embedding](BaseNode.md#embedding)
#### Defined in
[Node.ts:39](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L39)
___
### endCharIdx
`Optional` **endCharIdx**: `number`
#### Defined in
[Node.ts:139](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L139)
___
### excludedEmbedMetadataKeys
**excludedEmbedMetadataKeys**: `string`[] = `[]`
#### Inherited from
[BaseNode](BaseNode.md).[excludedEmbedMetadataKeys](BaseNode.md#excludedembedmetadatakeys)
#### Defined in
[Node.ts:43](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L43)
___
### excludedLlmMetadataKeys
**excludedLlmMetadataKeys**: `string`[] = `[]`
#### Inherited from
[BaseNode](BaseNode.md).[excludedLlmMetadataKeys](BaseNode.md#excludedllmmetadatakeys)
#### Defined in
[Node.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L44)
___
### hash
**hash**: `string` = `""`
#### Inherited from
[BaseNode](BaseNode.md).[hash](BaseNode.md#hash)
#### Defined in
[Node.ts:46](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L46)
___
### id\_
**id\_**: `string`
#### Inherited from
[BaseNode](BaseNode.md).[id_](BaseNode.md#id_)
#### Defined in
[Node.ts:38](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L38)
___
### metadata
**metadata**: `Record`<`string`, `any`\> = `{}`
#### Inherited from
[BaseNode](BaseNode.md).[metadata](BaseNode.md#metadata)
#### Defined in
[Node.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L42)
___
### metadataSeparator
**metadataSeparator**: `string` = `"\n"`
#### Defined in
[Node.ts:142](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L142)
___
### relationships
**relationships**: `Partial`<`Record`<[`NodeRelationship`](../enums/NodeRelationship.md), [`RelatedNodeType`](../modules.md#relatednodetype)\>\> = `{}`
#### Inherited from
[BaseNode](BaseNode.md).[relationships](BaseNode.md#relationships)
#### Defined in
[Node.ts:45](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L45)
___
### startCharIdx
`Optional` **startCharIdx**: `number`
#### Defined in
[Node.ts:138](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L138)
___
### text
**text**: `string` = `""`
#### Defined in
[Node.ts:137](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L137)
## Accessors
### childNodes
`get` **childNodes**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)[]
#### Inherited from
BaseNode.childNodes
#### Defined in
[Node.ts:104](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L104)
___
### nextNode
`get` **nextNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
BaseNode.nextNode
#### Defined in
[Node.ts:84](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L84)
___
### nodeId
`get` **nodeId**(): `string`
#### Returns
`string`
#### Inherited from
BaseNode.nodeId
#### Defined in
[Node.ts:58](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L58)
___
### parentNode
`get` **parentNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
BaseNode.parentNode
#### Defined in
[Node.ts:94](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L94)
___
### prevNode
`get` **prevNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
BaseNode.prevNode
#### Defined in
[Node.ts:72](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L72)
___
### sourceNode
`get` **sourceNode**(): `undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
`undefined` \| [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
BaseNode.sourceNode
#### Defined in
[Node.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L62)
## Methods
### asRelatedNodeInfo
**asRelatedNodeInfo**(): [`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Returns
[`RelatedNodeInfo`](../interfaces/RelatedNodeInfo.md)
#### Inherited from
[BaseNode](BaseNode.md).[asRelatedNodeInfo](BaseNode.md#asrelatednodeinfo)
#### Defined in
[Node.ts:124](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L124)
___
### generateHash
**generateHash**(): `void`
#### Returns
`void`
#### Defined in
[Node.ts:149](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L149)
___
### getContent
**getContent**(`metadataMode?`): `string`
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) | `MetadataMode.NONE` |
#### Returns
`string`
#### Overrides
[BaseNode](BaseNode.md).[getContent](BaseNode.md#getcontent)
#### Defined in
[Node.ts:157](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L157)
___
### getEmbedding
**getEmbedding**(): `number`[]
#### Returns
`number`[]
#### Inherited from
[BaseNode](BaseNode.md).[getEmbedding](BaseNode.md#getembedding)
#### Defined in
[Node.ts:116](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L116)
___
### getMetadataStr
**getMetadataStr**(`metadataMode`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `metadataMode` | [`MetadataMode`](../enums/MetadataMode.md) |
#### Returns
`string`
#### Overrides
[BaseNode](BaseNode.md).[getMetadataStr](BaseNode.md#getmetadatastr)
#### Defined in
[Node.ts:162](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L162)
___
### getNodeInfo
**getNodeInfo**(): `Object`
#### Returns
`Object`
| Name | Type |
| :------ | :------ |
| `end` | `undefined` \| `number` |
| `start` | `undefined` \| `number` |
#### Defined in
[Node.ts:187](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L187)
___
### getText
**getText**(): `string`
#### Returns
`string`
#### Defined in
[Node.ts:191](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L191)
___
### getType
**getType**(): [`ObjectType`](../enums/ObjectType.md)
#### Returns
[`ObjectType`](../enums/ObjectType.md)
#### Overrides
[BaseNode](BaseNode.md).[getType](BaseNode.md#gettype)
#### Defined in
[Node.ts:153](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L153)
___
### setContent
**setContent**(`value`): `void`
#### Parameters
| Name | Type |
| :------ | :------ |
| `value` | `string` |
#### Returns
`void`
#### Overrides
[BaseNode](BaseNode.md).[setContent](BaseNode.md#setcontent)
#### Defined in
[Node.ts:183](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L183)
@@ -0,0 +1,64 @@
---
id: "TreeSummarize"
title: "Class: TreeSummarize"
sidebar_label: "TreeSummarize"
sidebar_position: 0
custom_edit_url: null
---
TreeSummarize repacks the text chunks into the smallest possible number of chunks and then summarizes them, then recursively does so until there's one chunk left.
## Implements
- `BaseResponseBuilder`
## Constructors
### constructor
**new TreeSummarize**(`serviceContext`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Defined in
[ResponseSynthesizer.ts:177](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L177)
## Properties
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[ResponseSynthesizer.ts:175](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L175)
## Methods
### agetResponse
**agetResponse**(`query`, `textChunks`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `textChunks` | `string`[] |
#### Returns
`Promise`<`string`\>
#### Implementation of
BaseResponseBuilder.agetResponse
#### Defined in
[ResponseSynthesizer.ts:181](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L181)
@@ -0,0 +1,102 @@
---
id: "VectorIndexRetriever"
title: "Class: VectorIndexRetriever"
sidebar_label: "VectorIndexRetriever"
sidebar_position: 0
custom_edit_url: null
---
VectorIndexRetriever retrieves nodes from a VectorIndex.
## Implements
- [`BaseRetriever`](../interfaces/BaseRetriever.md)
## Constructors
### constructor
**new VectorIndexRetriever**(`index`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `index` | [`VectorStoreIndex`](VectorStoreIndex.md) |
#### Defined in
[Retriever.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L28)
## Properties
### index
**index**: [`VectorStoreIndex`](VectorStoreIndex.md)
#### Defined in
[Retriever.ts:24](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L24)
___
### serviceContext
`Private` **serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Defined in
[Retriever.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L26)
___
### similarityTopK
**similarityTopK**: `number` = `DEFAULT_SIMILARITY_TOP_K`
#### Defined in
[Retriever.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L25)
## Methods
### aretrieve
**aretrieve**(`query`, `parentEvent?`): `Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](../interfaces/Event.md) |
#### Returns
`Promise`<[`NodeWithScore`](../interfaces/NodeWithScore.md)[]\>
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[aretrieve](../interfaces/BaseRetriever.md#aretrieve)
#### Defined in
[Retriever.ts:33](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L33)
___
### getServiceContext
**getServiceContext**(): [`ServiceContext`](../interfaces/ServiceContext.md)
#### Returns
[`ServiceContext`](../interfaces/ServiceContext.md)
#### Implementation of
[BaseRetriever](../interfaces/BaseRetriever.md).[getServiceContext](../interfaces/BaseRetriever.md#getservicecontext)
#### Defined in
[Retriever.ts:70](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L70)
@@ -0,0 +1,253 @@
---
id: "VectorStoreIndex"
title: "Class: VectorStoreIndex"
sidebar_label: "VectorStoreIndex"
sidebar_position: 0
custom_edit_url: null
---
The VectorStoreIndex, an index that stores the nodes only according to their vector embedings.
## Hierarchy
- [`BaseIndex`](BaseIndex.md)<[`IndexDict`](IndexDict.md)\>
**`VectorStoreIndex`**
## Constructors
### constructor
`Private` **new VectorStoreIndex**(`init`)
#### Parameters
| Name | Type |
| :------ | :------ |
| `init` | `VectorIndexConstructorProps` |
#### Overrides
[BaseIndex](BaseIndex.md).[constructor](BaseIndex.md#constructor)
#### Defined in
[BaseIndex.ts:109](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L109)
## Properties
### docStore
**docStore**: `BaseDocumentStore`
#### Inherited from
[BaseIndex](BaseIndex.md).[docStore](BaseIndex.md#docstore)
#### Defined in
[BaseIndex.ts:75](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L75)
___
### indexStore
`Optional` **indexStore**: `BaseIndexStore`
#### Inherited from
[BaseIndex](BaseIndex.md).[indexStore](BaseIndex.md#indexstore)
#### Defined in
[BaseIndex.ts:77](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L77)
___
### indexStruct
**indexStruct**: [`IndexDict`](IndexDict.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[indexStruct](BaseIndex.md#indexstruct)
#### Defined in
[BaseIndex.ts:78](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L78)
___
### serviceContext
**serviceContext**: [`ServiceContext`](../interfaces/ServiceContext.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[serviceContext](BaseIndex.md#servicecontext)
#### Defined in
[BaseIndex.ts:73](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L73)
___
### storageContext
**storageContext**: [`StorageContext`](../interfaces/StorageContext.md)
#### Inherited from
[BaseIndex](BaseIndex.md).[storageContext](BaseIndex.md#storagecontext)
#### Defined in
[BaseIndex.ts:74](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L74)
___
### vectorStore
**vectorStore**: `VectorStore`
#### Overrides
[BaseIndex](BaseIndex.md).[vectorStore](BaseIndex.md#vectorstore)
#### Defined in
[BaseIndex.ts:107](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L107)
## Methods
### asQueryEngine
**asQueryEngine**(): [`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
Get a retriever query engine for this index.
NOTE: if you are using a custom query engine you don't have to use this method.
#### Returns
[`BaseQueryEngine`](../interfaces/BaseQueryEngine.md)
#### Defined in
[BaseIndex.ts:252](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L252)
___
### asRetriever
**asRetriever**(): [`VectorIndexRetriever`](VectorIndexRetriever.md)
Get a VectorIndexRetriever for this index.
NOTE: if you want to use a custom retriever you don't have to use this method.
#### Returns
[`VectorIndexRetriever`](VectorIndexRetriever.md)
retriever for the index
#### Overrides
[BaseIndex](BaseIndex.md).[asRetriever](BaseIndex.md#asretriever)
#### Defined in
[BaseIndex.ts:242](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L242)
___
### agetNodeEmbeddingResults
`Static` **agetNodeEmbeddingResults**(`nodes`, `serviceContext`, `logProgress?`): `Promise`<[`NodeWithEmbedding`](../interfaces/NodeWithEmbedding.md)[]\>
Get the embeddings for nodes.
#### Parameters
| Name | Type | Default value | Description |
| :------ | :------ | :------ | :------ |
| `nodes` | [`BaseNode`](BaseNode.md)[] | `undefined` | |
| `serviceContext` | [`ServiceContext`](../interfaces/ServiceContext.md) | `undefined` | |
| `logProgress` | `boolean` | `false` | log progress to console (useful for debugging) |
#### Returns
`Promise`<[`NodeWithEmbedding`](../interfaces/NodeWithEmbedding.md)[]\>
#### Defined in
[BaseIndex.ts:159](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L159)
___
### buildIndexFromNodes
`Static` **buildIndexFromNodes**(`nodes`, `serviceContext`, `vectorStore`): `Promise`<[`IndexDict`](IndexDict.md)\>
Get embeddings for nodes and place them into the index.
#### Parameters
| Name | Type |
| :------ | :------ |
| `nodes` | [`BaseNode`](BaseNode.md)[] |
| `serviceContext` | [`ServiceContext`](../interfaces/ServiceContext.md) |
| `vectorStore` | `VectorStore` |
#### Returns
`Promise`<[`IndexDict`](IndexDict.md)\>
#### Defined in
[BaseIndex.ts:187](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L187)
___
### fromDocuments
`Static` **fromDocuments**(`documents`, `storageContext?`, `serviceContext?`): `Promise`<[`VectorStoreIndex`](VectorStoreIndex.md)\>
High level API: split documents, get embeddings, and build index.
#### Parameters
| Name | Type |
| :------ | :------ |
| `documents` | [`Document`](Document.md)[] |
| `storageContext?` | [`StorageContext`](../interfaces/StorageContext.md) |
| `serviceContext?` | [`ServiceContext`](../interfaces/ServiceContext.md) |
#### Returns
`Promise`<[`VectorStoreIndex`](VectorStoreIndex.md)\>
#### Defined in
[BaseIndex.ts:214](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L214)
___
### init
`Static` **init**(`options`): `Promise`<[`VectorStoreIndex`](VectorStoreIndex.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `options` | [`VectorIndexOptions`](../interfaces/VectorIndexOptions.md) |
#### Returns
`Promise`<[`VectorStoreIndex`](VectorStoreIndex.md)\>
#### Defined in
[BaseIndex.ts:114](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L114)
@@ -0,0 +1,2 @@
label: "Classes"
position: 3
@@ -0,0 +1,27 @@
---
id: "ListRetrieverMode"
title: "Enumeration: ListRetrieverMode"
sidebar_label: "ListRetrieverMode"
sidebar_position: 0
custom_edit_url: null
---
## Enumeration Members
### DEFAULT
**DEFAULT** = ``"default"``
#### Defined in
[index/list/ListIndex.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L21)
___
### LLM
• **LLM** = ``"llm"``
#### Defined in
[index/list/ListIndex.ts:23](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/index/list/ListIndex.ts#L23)
+47
View File
@@ -0,0 +1,47 @@
---
id: "MetadataMode"
title: "Enumeration: MetadataMode"
sidebar_label: "MetadataMode"
sidebar_position: 0
custom_edit_url: null
---
## Enumeration Members
### ALL
**ALL** = ``"ALL"``
#### Defined in
[Node.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L19)
___
### EMBED
• **EMBED** = ``"EMBED"``
#### Defined in
[Node.ts:20](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L20)
___
### LLM
• **LLM** = ``"LLM"``
#### Defined in
[Node.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L21)
___
### NONE
• **NONE** = ``"NONE"``
#### Defined in
[Node.ts:22](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L22)
@@ -0,0 +1,57 @@
---
id: "NodeRelationship"
title: "Enumeration: NodeRelationship"
sidebar_label: "NodeRelationship"
sidebar_position: 0
custom_edit_url: null
---
## Enumeration Members
### CHILD
**CHILD** = ``"CHILD"``
#### Defined in
[Node.ts:8](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L8)
___
### NEXT
• **NEXT** = ``"NEXT"``
#### Defined in
[Node.ts:6](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L6)
___
### PARENT
• **PARENT** = ``"PARENT"``
#### Defined in
[Node.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L7)
___
### PREVIOUS
• **PREVIOUS** = ``"PREVIOUS"``
#### Defined in
[Node.ts:5](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L5)
___
### SOURCE
• **SOURCE** = ``"SOURCE"``
#### Defined in
[Node.ts:4](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L4)
+47
View File
@@ -0,0 +1,47 @@
---
id: "ObjectType"
title: "Enumeration: ObjectType"
sidebar_label: "ObjectType"
sidebar_position: 0
custom_edit_url: null
---
## Enumeration Members
### DOCUMENT
**DOCUMENT** = ``"DOCUMENT"``
#### Defined in
[Node.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L15)
___
### IMAGE
• **IMAGE** = ``"IMAGE"``
#### Defined in
[Node.ts:13](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L13)
___
### INDEX
• **INDEX** = ``"INDEX"``
#### Defined in
[Node.ts:14](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L14)
___
### TEXT
• **TEXT** = ``"TEXT"``
#### Defined in
[Node.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L12)
@@ -0,0 +1,40 @@
---
id: "SimilarityType"
title: "Enumeration: SimilarityType"
sidebar_label: "SimilarityType"
sidebar_position: 0
custom_edit_url: null
---
Similarity type
Default is cosine similarity. Dot product and negative Euclidean distance are also supported.
## Enumeration Members
### DEFAULT
**DEFAULT** = ``"cosine"``
#### Defined in
[Embedding.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L10)
___
### DOT\_PRODUCT
• **DOT\_PRODUCT** = ``"dot_product"``
#### Defined in
[Embedding.ts:11](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L11)
___
### EUCLIDEAN
• **EUCLIDEAN** = ``"euclidean"``
#### Defined in
[Embedding.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L12)
+2
View File
@@ -0,0 +1,2 @@
label: "Enumerations"
position: 2
+85
View File
@@ -0,0 +1,85 @@
---
id: "index"
title: "llamaindex"
sidebar_label: "Readme"
sidebar_position: 0
custom_edit_url: null
---
# LlamaIndex.TS
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.
## What is LlamaIndex.TS?
LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.
## Getting started with an example:
LlamaIndex.TS requries Node v18 or higher. You can download it from https://nodejs.org or use https://nvm.sh (our preferred option).
In a new folder:
```bash
export OPEN_AI_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
npx tsc -init # if needed
pnpm install llamaindex
```
Create the file example.ts
```ts
// example.ts
import fs from "fs/promises";
import { Document, VectorStoreIndex } from "llamaindex";
async function main() {
// Load essay from abramov.txt in Node
const essay = await fs.readFile(
"node_modules/llamaindex/examples/abramov.txt",
"utf-8"
);
// Create Document object with essay
const document = new Document({ text: essay });
// Split text and create embeddings. Store them in a VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments([document]);
// Query the index
const queryEngine = index.asQueryEngine();
const response = await queryEngine.aquery(
"What did the author do in college?"
);
// Output response
console.log(response.toString());
}
```
Then you can run it using
```bash
npx ts-node example.ts
```
## Core concepts:
- [Document](packages/core/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
- [Node](packages/core/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
- Indexes: indexes store the Nodes and the embeddings of those nodes.
- [QueryEngine](packages/core/src/QueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected nodes from your Index to give the LLM the context it needs to answer your query.
- [ChatEngine](packages/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indexes.
## Contributing:
We are in the very early days of LlamaIndex.TS. If youre interested in hacking on it with us check out our [contributing guide](CONTRIBUTING.md)
## Bugs? Questions?
Please join our Discord! https://discord.com/invite/eN6D2HQ4aX
@@ -0,0 +1,73 @@
---
id: "BaseIndexInit"
title: "Interface: BaseIndexInit<T>"
sidebar_label: "BaseIndexInit"
sidebar_position: 0
custom_edit_url: null
---
## Type parameters
| Name |
| :------ |
| `T` |
## Properties
### docStore
**docStore**: `BaseDocumentStore`
#### Defined in
[BaseIndex.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L62)
___
### indexStore
`Optional` **indexStore**: `BaseIndexStore`
#### Defined in
[BaseIndex.ts:64](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L64)
___
### indexStruct
**indexStruct**: `T`
#### Defined in
[BaseIndex.ts:65](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L65)
___
### serviceContext
**serviceContext**: [`ServiceContext`](ServiceContext.md)
#### Defined in
[BaseIndex.ts:60](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L60)
___
### storageContext
**storageContext**: [`StorageContext`](StorageContext.md)
#### Defined in
[BaseIndex.ts:61](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L61)
___
### vectorStore
`Optional` **vectorStore**: `VectorStore`
#### Defined in
[BaseIndex.ts:63](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L63)
@@ -0,0 +1,49 @@
---
id: "BaseLLMPredictor"
title: "Interface: BaseLLMPredictor"
sidebar_label: "BaseLLMPredictor"
sidebar_position: 0
custom_edit_url: null
---
LLM Predictors are an abstraction to predict the response to a prompt.
## Implemented by
- [`ChatGPTLLMPredictor`](../classes/ChatGPTLLMPredictor.md)
## Methods
### apredict
**apredict**(`prompt`, `input?`, `parentEvent?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `prompt` | `string` \| [`SimplePrompt`](../modules.md#simpleprompt) |
| `input?` | `Record`<`string`, `string`\> |
| `parentEvent?` | [`Event`](Event.md) |
#### Returns
`Promise`<`string`\>
#### Defined in
[LLMPredictor.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L10)
___
### getLlmMetadata
**getLlmMetadata**(): `Promise`<`any`\>
#### Returns
`Promise`<`any`\>
#### Defined in
[LLMPredictor.ts:9](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLMPredictor.ts#L9)
@@ -0,0 +1,59 @@
---
id: "BaseOutputParser"
title: "Interface: BaseOutputParser<T>"
sidebar_label: "BaseOutputParser"
sidebar_position: 0
custom_edit_url: null
---
An OutputParser is used to extract structured data from the raw output of the LLM.
## Type parameters
| Name |
| :------ |
| `T` |
## Implemented by
- [`SubQuestionOutputParser`](../classes/SubQuestionOutputParser.md)
## Methods
### format
**format**(`output`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `output` | `string` |
#### Returns
`string`
#### Defined in
[OutputParser.ts:8](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L8)
___
### parse
**parse**(`output`): `T`
#### Parameters
| Name | Type |
| :------ | :------ |
| `output` | `string` |
#### Returns
`T`
#### Defined in
[OutputParser.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L7)
@@ -0,0 +1,35 @@
---
id: "BaseQueryEngine"
title: "Interface: BaseQueryEngine"
sidebar_label: "BaseQueryEngine"
sidebar_position: 0
custom_edit_url: null
---
A query engine is a question answerer that can use one or more steps.
## Implemented by
- [`RetrieverQueryEngine`](../classes/RetrieverQueryEngine.md)
- [`SubQuestionQueryEngine`](../classes/SubQuestionQueryEngine.md)
## Methods
### aquery
**aquery**(`query`, `parentEvent?`): `Promise`<[`Response`](../classes/Response.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](Event.md) |
#### Returns
`Promise`<[`Response`](../classes/Response.md)\>
#### Defined in
[QueryEngine.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QueryEngine.ts#L19)
@@ -0,0 +1,34 @@
---
id: "BaseQuestionGenerator"
title: "Interface: BaseQuestionGenerator"
sidebar_label: "BaseQuestionGenerator"
sidebar_position: 0
custom_edit_url: null
---
QuestionGenerators generate new questions for the LLM using tools and a user query.
## Implemented by
- [`LLMQuestionGenerator`](../classes/LLMQuestionGenerator.md)
## Methods
### agenerate
**agenerate**(`tools`, `query`): `Promise`<[`SubQuestion`](SubQuestion.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `tools` | [`ToolMetadata`](ToolMetadata.md)[] |
| `query` | `string` |
#### Returns
`Promise`<[`SubQuestion`](SubQuestion.md)[]\>
#### Defined in
[QuestionGenerator.ts:23](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L23)
@@ -0,0 +1,33 @@
---
id: "BaseReader"
title: "Interface: BaseReader"
sidebar_label: "BaseReader"
sidebar_position: 0
custom_edit_url: null
---
A reader takes imports data into Document objects.
## Implemented by
- [`TextFileReader`](../classes/TextFileReader.md)
## Methods
### loadData
**loadData**(`...args`): `Promise`<[`Document`](../classes/Document.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `...args` | `any`[] |
#### Returns
`Promise`<[`Document`](../classes/Document.md)[]\>
#### Defined in
[readers/base.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/readers/base.ts#L7)
@@ -0,0 +1,50 @@
---
id: "BaseRetriever"
title: "Interface: BaseRetriever"
sidebar_label: "BaseRetriever"
sidebar_position: 0
custom_edit_url: null
---
Retrievers retrieve the nodes that most closely match our query in similarity.
## Implemented by
- [`ListIndexLLMRetriever`](../classes/ListIndexLLMRetriever.md)
- [`ListIndexRetriever`](../classes/ListIndexRetriever.md)
- [`VectorIndexRetriever`](../classes/VectorIndexRetriever.md)
## Methods
### aretrieve
**aretrieve**(`query`, `parentEvent?`): `Promise`<[`NodeWithScore`](NodeWithScore.md)[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `query` | `string` |
| `parentEvent?` | [`Event`](Event.md) |
#### Returns
`Promise`<[`NodeWithScore`](NodeWithScore.md)[]\>
#### Defined in
[Retriever.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L16)
___
### getServiceContext
**getServiceContext**(): [`ServiceContext`](ServiceContext.md)
#### Returns
[`ServiceContext`](ServiceContext.md)
#### Defined in
[Retriever.ts:17](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Retriever.ts#L17)
+25
View File
@@ -0,0 +1,25 @@
---
id: "BaseTool"
title: "Interface: BaseTool"
sidebar_label: "BaseTool"
sidebar_position: 0
custom_edit_url: null
---
Simple Tool interface. Likely to change.
## Hierarchy
- **`BaseTool`**
↳ [`QueryEngineTool`](QueryEngineTool.md)
## Properties
### metadata
**metadata**: [`ToolMetadata`](ToolMetadata.md)
#### Defined in
[Tool.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Tool.ts#L12)
@@ -0,0 +1,54 @@
---
id: "ChatEngine"
title: "Interface: ChatEngine"
sidebar_label: "ChatEngine"
sidebar_position: 0
custom_edit_url: null
---
A ChatEngine is used to handle back and forth chats between the application and the LLM.
## Implemented by
- [`CondenseQuestionChatEngine`](../classes/CondenseQuestionChatEngine.md)
- [`ContextChatEngine`](../classes/ContextChatEngine.md)
- [`SimpleChatEngine`](../classes/SimpleChatEngine.md)
## Methods
### achat
**achat**(`message`, `chatHistory?`): `Promise`<[`Response`](../classes/Response.md)\>
Send message along with the class's current chat history to the LLM.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `message` | `string` | |
| `chatHistory?` | [`ChatMessage`](ChatMessage.md)[] | optional chat history if you want to customize the chat history |
#### Returns
`Promise`<[`Response`](../classes/Response.md)\>
#### Defined in
[ChatEngine.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L25)
___
### reset
**reset**(): `void`
Resets the chat history so that it's empty.
#### Returns
`void`
#### Defined in
[ChatEngine.ts:30](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ChatEngine.ts#L30)
@@ -0,0 +1,27 @@
---
id: "ChatMessage"
title: "Interface: ChatMessage"
sidebar_label: "ChatMessage"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### content
**content**: `string`
#### Defined in
[LLM.ts:14](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L14)
___
### role
**role**: `MessageType`
#### Defined in
[LLM.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L15)
@@ -0,0 +1,37 @@
---
id: "ChatResponse"
title: "Interface: ChatResponse"
sidebar_label: "ChatResponse"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### delta
`Optional` **delta**: `string`
#### Defined in
[LLM.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L21)
___
### message
**message**: [`ChatMessage`](ChatMessage.md)
#### Defined in
[LLM.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L19)
___
### raw
`Optional` **raw**: `Record`<`string`, `any`\>
#### Defined in
[LLM.ts:20](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L20)
+47
View File
@@ -0,0 +1,47 @@
---
id: "Event"
title: "Interface: Event"
sidebar_label: "Event"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### id
**id**: `string`
#### Defined in
[callbacks/CallbackManager.ts:14](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L14)
___
### parentId
`Optional` **parentId**: `string`
#### Defined in
[callbacks/CallbackManager.ts:17](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L17)
___
### tags
`Optional` **tags**: [`EventTag`](../modules.md#eventtag)[]
#### Defined in
[callbacks/CallbackManager.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L16)
___
### type
**type**: [`EventType`](../modules.md#eventtype)
#### Defined in
[callbacks/CallbackManager.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L15)
@@ -0,0 +1,100 @@
---
id: "GenericFileSystem"
title: "Interface: GenericFileSystem"
sidebar_label: "GenericFileSystem"
sidebar_position: 0
custom_edit_url: null
---
A filesystem interface that is meant to be compatible with
the 'fs' module from Node.js.
Allows for the use of similar inteface implementation on
browsers.
## Implemented by
- [`InMemoryFileSystem`](../classes/InMemoryFileSystem.md)
## Methods
### access
**access**(`path`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
#### Returns
`Promise`<`void`\>
#### Defined in
[storage/FileSystem.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L12)
___
### mkdir
**mkdir**(`path`, `options?`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`void`\>
#### Defined in
[storage/FileSystem.ts:13](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L13)
___
### readFile
**readFile**(`path`, `options?`): `Promise`<`string`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`string`\>
#### Defined in
[storage/FileSystem.ts:11](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L11)
___
### writeFile
**writeFile**(`path`, `content`, `options?`): `Promise`<`void`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
| `content` | `string` |
| `options?` | `any` |
#### Returns
`Promise`<`void`\>
#### Defined in
[storage/FileSystem.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L10)
+57
View File
@@ -0,0 +1,57 @@
---
id: "LLM"
title: "Interface: LLM"
sidebar_label: "LLM"
sidebar_position: 0
custom_edit_url: null
---
Unified language model interface
## Implemented by
- [`OpenAI`](../classes/OpenAI.md)
## Methods
### achat
**achat**(`messages`): `Promise`<[`ChatResponse`](ChatResponse.md)\>
Get a chat response from the LLM
#### Parameters
| Name | Type |
| :------ | :------ |
| `messages` | [`ChatMessage`](ChatMessage.md)[] |
#### Returns
`Promise`<[`ChatResponse`](ChatResponse.md)\>
#### Defined in
[LLM.ts:35](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L35)
___
### acomplete
**acomplete**(`prompt`): `Promise`<[`ChatResponse`](ChatResponse.md)\>
Get a prompt completion from the LLM
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `prompt` | `string` | the prompt to complete |
#### Returns
`Promise`<[`ChatResponse`](ChatResponse.md)\>
#### Defined in
[LLM.ts:41](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L41)
@@ -0,0 +1,33 @@
---
id: "NodeParser"
title: "Interface: NodeParser"
sidebar_label: "NodeParser"
sidebar_position: 0
custom_edit_url: null
---
A node parser generates TextNodes from Documents
## Implemented by
- [`SimpleNodeParser`](../classes/SimpleNodeParser.md)
## Methods
### getNodesFromDocuments
**getNodesFromDocuments**(`documents`): [`TextNode`](../classes/TextNode.md)[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `documents` | [`Document`](../classes/Document.md)[] |
#### Returns
[`TextNode`](../classes/TextNode.md)[]
#### Defined in
[NodeParser.ts:53](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L53)
@@ -0,0 +1,29 @@
---
id: "NodeWithEmbedding"
title: "Interface: NodeWithEmbedding"
sidebar_label: "NodeWithEmbedding"
sidebar_position: 0
custom_edit_url: null
---
A node with an embedding
## Properties
### embedding
**embedding**: `number`[]
#### Defined in
[Node.ts:247](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L247)
___
### node
**node**: [`BaseNode`](../classes/BaseNode.md)
#### Defined in
[Node.ts:246](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L246)
@@ -0,0 +1,29 @@
---
id: "NodeWithScore"
title: "Interface: NodeWithScore"
sidebar_label: "NodeWithScore"
sidebar_position: 0
custom_edit_url: null
---
A node with a similarity score
## Properties
### node
**node**: [`BaseNode`](../classes/BaseNode.md)
#### Defined in
[Node.ts:238](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L238)
___
### score
**score**: `number`
#### Defined in
[Node.ts:239](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L239)
@@ -0,0 +1,39 @@
---
id: "QueryEngineTool"
title: "Interface: QueryEngineTool"
sidebar_label: "QueryEngineTool"
sidebar_position: 0
custom_edit_url: null
---
A Tool that uses a QueryEngine.
## Hierarchy
- [`BaseTool`](BaseTool.md)
**`QueryEngineTool`**
## Properties
### metadata
**metadata**: [`ToolMetadata`](ToolMetadata.md)
#### Inherited from
[BaseTool](BaseTool.md).[metadata](BaseTool.md#metadata)
#### Defined in
[Tool.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Tool.ts#L12)
___
### queryEngine
**queryEngine**: [`BaseQueryEngine`](BaseQueryEngine.md)
#### Defined in
[Tool.ts:19](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Tool.ts#L19)
@@ -0,0 +1,47 @@
---
id: "RelatedNodeInfo"
title: "Interface: RelatedNodeInfo"
sidebar_label: "RelatedNodeInfo"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### hash
`Optional` **hash**: `string`
#### Defined in
[Node.ts:29](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L29)
___
### metadata
**metadata**: `Record`<`string`, `any`\>
#### Defined in
[Node.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L28)
___
### nodeId
**nodeId**: `string`
#### Defined in
[Node.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L26)
___
### nodeType
`Optional` **nodeType**: [`ObjectType`](../enums/ObjectType.md)
#### Defined in
[Node.ts:27](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L27)
@@ -0,0 +1,47 @@
---
id: "RetrievalCallbackResponse"
title: "Interface: RetrievalCallbackResponse"
sidebar_label: "RetrievalCallbackResponse"
sidebar_position: 0
custom_edit_url: null
---
## Hierarchy
- `BaseCallbackResponse`
**`RetrievalCallbackResponse`**
## Properties
### event
**event**: [`Event`](Event.md)
#### Inherited from
BaseCallbackResponse.event
#### Defined in
[callbacks/CallbackManager.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L21)
___
### nodes
**nodes**: [`NodeWithScore`](NodeWithScore.md)[]
#### Defined in
[callbacks/CallbackManager.ts:47](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L47)
___
### query
**query**: `string`
#### Defined in
[callbacks/CallbackManager.ts:46](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L46)
@@ -0,0 +1,59 @@
---
id: "ServiceContext"
title: "Interface: ServiceContext"
sidebar_label: "ServiceContext"
sidebar_position: 0
custom_edit_url: null
---
The ServiceContext is a collection of components that are used in different parts of the application.
## Properties
### callbackManager
**callbackManager**: [`CallbackManager`](../classes/CallbackManager.md)
#### Defined in
[ServiceContext.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L16)
___
### embedModel
**embedModel**: [`BaseEmbedding`](../classes/BaseEmbedding.md)
#### Defined in
[ServiceContext.ts:14](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L14)
___
### llmPredictor
**llmPredictor**: [`BaseLLMPredictor`](BaseLLMPredictor.md)
#### Defined in
[ServiceContext.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L12)
___
### nodeParser
**nodeParser**: [`NodeParser`](NodeParser.md)
#### Defined in
[ServiceContext.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L15)
___
### promptHelper
**promptHelper**: `PromptHelper`
#### Defined in
[ServiceContext.ts:13](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L13)
@@ -0,0 +1,87 @@
---
id: "ServiceContextOptions"
title: "Interface: ServiceContextOptions"
sidebar_label: "ServiceContextOptions"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### callbackManager
`Optional` **callbackManager**: [`CallbackManager`](../classes/CallbackManager.md)
#### Defined in
[ServiceContext.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L26)
___
### chunkOverlap
`Optional` **chunkOverlap**: `number`
#### Defined in
[ServiceContext.ts:29](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L29)
___
### chunkSize
`Optional` **chunkSize**: `number`
#### Defined in
[ServiceContext.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L28)
___
### embedModel
`Optional` **embedModel**: [`BaseEmbedding`](../classes/BaseEmbedding.md)
#### Defined in
[ServiceContext.ts:24](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L24)
___
### llm
`Optional` **llm**: [`OpenAI`](../classes/OpenAI.md)
#### Defined in
[ServiceContext.ts:22](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L22)
___
### llmPredictor
`Optional` **llmPredictor**: [`BaseLLMPredictor`](BaseLLMPredictor.md)
#### Defined in
[ServiceContext.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L21)
___
### nodeParser
`Optional` **nodeParser**: [`NodeParser`](NodeParser.md)
#### Defined in
[ServiceContext.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L25)
___
### promptHelper
`Optional` **promptHelper**: `PromptHelper`
#### Defined in
[ServiceContext.ts:23](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L23)
@@ -0,0 +1,37 @@
---
id: "StorageContext"
title: "Interface: StorageContext"
sidebar_label: "StorageContext"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### docStore
**docStore**: `BaseDocumentStore`
#### Defined in
[storage/StorageContext.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/StorageContext.ts#L15)
___
### indexStore
**indexStore**: `BaseIndexStore`
#### Defined in
[storage/StorageContext.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/StorageContext.ts#L16)
___
### vectorStore
**vectorStore**: `VectorStore`
#### Defined in
[storage/StorageContext.ts:17](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/StorageContext.ts#L17)
@@ -0,0 +1,57 @@
---
id: "StreamCallbackResponse"
title: "Interface: StreamCallbackResponse"
sidebar_label: "StreamCallbackResponse"
sidebar_position: 0
custom_edit_url: null
---
## Hierarchy
- `BaseCallbackResponse`
**`StreamCallbackResponse`**
## Properties
### event
**event**: [`Event`](Event.md)
#### Inherited from
BaseCallbackResponse.event
#### Defined in
[callbacks/CallbackManager.ts:21](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L21)
___
### index
**index**: `number`
#### Defined in
[callbacks/CallbackManager.ts:40](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L40)
___
### isDone
`Optional` **isDone**: `boolean`
#### Defined in
[callbacks/CallbackManager.ts:41](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L41)
___
### token
`Optional` **token**: [`StreamToken`](StreamToken.md)
#### Defined in
[callbacks/CallbackManager.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L42)
@@ -0,0 +1,57 @@
---
id: "StreamToken"
title: "Interface: StreamToken"
sidebar_label: "StreamToken"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### choices
**choices**: { `delta`: { `content?`: `string` ; `role?`: `ChatCompletionResponseMessageRoleEnum` } ; `finish_reason`: ``null`` \| `string` ; `index`: `number` }[]
#### Defined in
[callbacks/CallbackManager.ts:29](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L29)
___
### created
• **created**: `number`
#### Defined in
[callbacks/CallbackManager.ts:27](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L27)
___
### id
• **id**: `string`
#### Defined in
[callbacks/CallbackManager.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L25)
___
### model
• **model**: `string`
#### Defined in
[callbacks/CallbackManager.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L28)
___
### object
• **object**: `string`
#### Defined in
[callbacks/CallbackManager.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L26)
@@ -0,0 +1,35 @@
---
id: "StructuredOutput"
title: "Interface: StructuredOutput<T>"
sidebar_label: "StructuredOutput"
sidebar_position: 0
custom_edit_url: null
---
StructuredOutput is just a combo of the raw output and the parsed output.
## Type parameters
| Name |
| :------ |
| `T` |
## Properties
### parsedOutput
**parsedOutput**: `T`
#### Defined in
[OutputParser.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L16)
___
### rawOutput
**rawOutput**: `string`
#### Defined in
[OutputParser.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/OutputParser.ts#L15)
@@ -0,0 +1,27 @@
---
id: "SubQuestion"
title: "Interface: SubQuestion"
sidebar_label: "SubQuestion"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### subQuestion
**subQuestion**: `string`
#### Defined in
[QuestionGenerator.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L15)
___
### toolName
**toolName**: `string`
#### Defined in
[QuestionGenerator.ts:16](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/QuestionGenerator.ts#L16)
@@ -0,0 +1,27 @@
---
id: "ToolMetadata"
title: "Interface: ToolMetadata"
sidebar_label: "ToolMetadata"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### description
**description**: `string`
#### Defined in
[Tool.ts:4](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Tool.ts#L4)
___
### name
**name**: `string`
#### Defined in
[Tool.ts:5](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Tool.ts#L5)
@@ -0,0 +1,47 @@
---
id: "VectorIndexOptions"
title: "Interface: VectorIndexOptions"
sidebar_label: "VectorIndexOptions"
sidebar_position: 0
custom_edit_url: null
---
## Properties
### indexStruct
`Optional` **indexStruct**: [`IndexDict`](../classes/IndexDict.md)
#### Defined in
[BaseIndex.ts:94](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L94)
___
### nodes
`Optional` **nodes**: [`BaseNode`](../classes/BaseNode.md)[]
#### Defined in
[BaseIndex.ts:93](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L93)
___
### serviceContext
`Optional` **serviceContext**: [`ServiceContext`](ServiceContext.md)
#### Defined in
[BaseIndex.ts:95](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L95)
___
### storageContext
`Optional` **storageContext**: [`StorageContext`](StorageContext.md)
#### Defined in
[BaseIndex.ts:96](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/BaseIndex.ts#L96)
@@ -0,0 +1,47 @@
---
id: "WalkableFileSystem"
title: "Interface: WalkableFileSystem"
sidebar_label: "WalkableFileSystem"
sidebar_position: 0
custom_edit_url: null
---
## Methods
### readdir
**readdir**(`path`): `Promise`<`string`[]\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
#### Returns
`Promise`<`string`[]\>
#### Defined in
[storage/FileSystem.ts:17](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L17)
___
### stat
**stat**(`path`): `Promise`<`any`\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `path` | `string` |
#### Returns
`Promise`<`any`\>
#### Defined in
[storage/FileSystem.ts:18](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L18)
@@ -0,0 +1,2 @@
label: "Interfaces"
position: 4
+914
View File
@@ -0,0 +1,914 @@
---
id: "modules"
title: "llamaindex"
sidebar_label: "Exports"
sidebar_position: 0.5
custom_edit_url: null
---
## Enumerations
- [ListRetrieverMode](enums/ListRetrieverMode.md)
- [MetadataMode](enums/MetadataMode.md)
- [NodeRelationship](enums/NodeRelationship.md)
- [ObjectType](enums/ObjectType.md)
- [SimilarityType](enums/SimilarityType.md)
## Classes
- [BaseEmbedding](classes/BaseEmbedding.md)
- [BaseIndex](classes/BaseIndex.md)
- [BaseNode](classes/BaseNode.md)
- [CallbackManager](classes/CallbackManager.md)
- [ChatGPTLLMPredictor](classes/ChatGPTLLMPredictor.md)
- [CompactAndRefine](classes/CompactAndRefine.md)
- [CondenseQuestionChatEngine](classes/CondenseQuestionChatEngine.md)
- [ContextChatEngine](classes/ContextChatEngine.md)
- [Document](classes/Document.md)
- [InMemoryFileSystem](classes/InMemoryFileSystem.md)
- [IndexDict](classes/IndexDict.md)
- [IndexList](classes/IndexList.md)
- [IndexNode](classes/IndexNode.md)
- [IndexStruct](classes/IndexStruct.md)
- [LLMQuestionGenerator](classes/LLMQuestionGenerator.md)
- [ListIndex](classes/ListIndex.md)
- [ListIndexLLMRetriever](classes/ListIndexLLMRetriever.md)
- [ListIndexRetriever](classes/ListIndexRetriever.md)
- [OpenAI](classes/OpenAI.md)
- [OpenAIEmbedding](classes/OpenAIEmbedding.md)
- [Refine](classes/Refine.md)
- [Response](classes/Response.md)
- [ResponseSynthesizer](classes/ResponseSynthesizer.md)
- [RetrieverQueryEngine](classes/RetrieverQueryEngine.md)
- [SentenceSplitter](classes/SentenceSplitter.md)
- [SimpleChatEngine](classes/SimpleChatEngine.md)
- [SimpleNodeParser](classes/SimpleNodeParser.md)
- [SimpleResponseBuilder](classes/SimpleResponseBuilder.md)
- [SubQuestionOutputParser](classes/SubQuestionOutputParser.md)
- [SubQuestionQueryEngine](classes/SubQuestionQueryEngine.md)
- [TextFileReader](classes/TextFileReader.md)
- [TextNode](classes/TextNode.md)
- [TreeSummarize](classes/TreeSummarize.md)
- [VectorIndexRetriever](classes/VectorIndexRetriever.md)
- [VectorStoreIndex](classes/VectorStoreIndex.md)
## Interfaces
- [BaseIndexInit](interfaces/BaseIndexInit.md)
- [BaseLLMPredictor](interfaces/BaseLLMPredictor.md)
- [BaseOutputParser](interfaces/BaseOutputParser.md)
- [BaseQueryEngine](interfaces/BaseQueryEngine.md)
- [BaseQuestionGenerator](interfaces/BaseQuestionGenerator.md)
- [BaseReader](interfaces/BaseReader.md)
- [BaseRetriever](interfaces/BaseRetriever.md)
- [BaseTool](interfaces/BaseTool.md)
- [ChatEngine](interfaces/ChatEngine.md)
- [ChatMessage](interfaces/ChatMessage.md)
- [ChatResponse](interfaces/ChatResponse.md)
- [Event](interfaces/Event.md)
- [GenericFileSystem](interfaces/GenericFileSystem.md)
- [LLM](interfaces/LLM.md)
- [NodeParser](interfaces/NodeParser.md)
- [NodeWithEmbedding](interfaces/NodeWithEmbedding.md)
- [NodeWithScore](interfaces/NodeWithScore.md)
- [QueryEngineTool](interfaces/QueryEngineTool.md)
- [RelatedNodeInfo](interfaces/RelatedNodeInfo.md)
- [RetrievalCallbackResponse](interfaces/RetrievalCallbackResponse.md)
- [ServiceContext](interfaces/ServiceContext.md)
- [ServiceContextOptions](interfaces/ServiceContextOptions.md)
- [StorageContext](interfaces/StorageContext.md)
- [StreamCallbackResponse](interfaces/StreamCallbackResponse.md)
- [StreamToken](interfaces/StreamToken.md)
- [StructuredOutput](interfaces/StructuredOutput.md)
- [SubQuestion](interfaces/SubQuestion.md)
- [ToolMetadata](interfaces/ToolMetadata.md)
- [VectorIndexOptions](interfaces/VectorIndexOptions.md)
- [WalkableFileSystem](interfaces/WalkableFileSystem.md)
## Type Aliases
### CompleteFileSystem
Ƭ **CompleteFileSystem**: [`GenericFileSystem`](interfaces/GenericFileSystem.md) & [`WalkableFileSystem`](interfaces/WalkableFileSystem.md)
#### Defined in
[storage/FileSystem.ts:49](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L49)
___
### CompletionResponse
Ƭ **CompletionResponse**: [`ChatResponse`](interfaces/ChatResponse.md)
#### Defined in
[LLM.ts:25](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L25)
___
### EventTag
Ƭ **EventTag**: ``"intermediate"`` \| ``"final"``
#### Defined in
[callbacks/CallbackManager.ts:11](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L11)
___
### EventType
Ƭ **EventType**: ``"retrieve"`` \| ``"llmPredict"`` \| ``"wrapper"``
#### Defined in
[callbacks/CallbackManager.ts:12](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/callbacks/CallbackManager.ts#L12)
___
### RelatedNodeType
Ƭ **RelatedNodeType**: [`RelatedNodeInfo`](interfaces/RelatedNodeInfo.md) \| [`RelatedNodeInfo`](interfaces/RelatedNodeInfo.md)[]
#### Defined in
[Node.ts:32](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Node.ts#L32)
___
### SimpleDirectoryReaderLoadDataProps
Ƭ **SimpleDirectoryReaderLoadDataProps**: `Object`
#### Type declaration
| Name | Type |
| :------ | :------ |
| `defaultReader?` | [`BaseReader`](interfaces/BaseReader.md) \| ``null`` |
| `directoryPath` | `string` |
| `fileExtToReader?` | `Record`<`string`, [`BaseReader`](interfaces/BaseReader.md)\> |
| `fs?` | [`CompleteFileSystem`](modules.md#completefilesystem) |
#### Defined in
[readers/SimpleDirectoryReader.ts:26](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/readers/SimpleDirectoryReader.ts#L26)
___
### SimplePrompt
Ƭ **SimplePrompt**: (`input`: `Record`<`string`, `string`\>) => `string`
#### Type declaration
▸ (`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
##### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
##### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
## Variables
### ALL\_AVAILABLE\_MODELS
• `Const` **ALL\_AVAILABLE\_MODELS**: `Object`
We currently support GPT-3.5 and GPT-4 models
#### Type declaration
| Name | Type |
| :------ | :------ |
| `gpt-3.5-turbo` | `number` |
| `gpt-3.5-turbo-16k` | `number` |
| `gpt-4` | `number` |
| `gpt-4-32k` | `number` |
#### Defined in
[LLM.ts:57](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L57)
___
### DEFAULT\_CHUNK\_OVERLAP
• `Const` **DEFAULT\_CHUNK\_OVERLAP**: ``20``
#### Defined in
[constants.ts:5](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L5)
___
### DEFAULT\_CHUNK\_OVERLAP\_RATIO
• `Const` **DEFAULT\_CHUNK\_OVERLAP\_RATIO**: ``0.1``
#### Defined in
[constants.ts:6](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L6)
___
### DEFAULT\_CHUNK\_SIZE
• `Const` **DEFAULT\_CHUNK\_SIZE**: ``1024``
#### Defined in
[constants.ts:4](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L4)
___
### DEFAULT\_COLLECTION
• `Const` **DEFAULT\_COLLECTION**: ``"data"``
#### Defined in
[storage/constants.ts:1](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L1)
___
### DEFAULT\_CONTEXT\_WINDOW
• `Const` **DEFAULT\_CONTEXT\_WINDOW**: ``3900``
#### Defined in
[constants.ts:1](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L1)
___
### DEFAULT\_DOC\_STORE\_PERSIST\_FILENAME
• `Const` **DEFAULT\_DOC\_STORE\_PERSIST\_FILENAME**: ``"docstore.json"``
#### Defined in
[storage/constants.ts:4](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L4)
___
### DEFAULT\_EMBEDDING\_DIM
• `Const` **DEFAULT\_EMBEDDING\_DIM**: ``1536``
#### Defined in
[constants.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L10)
___
### DEFAULT\_FS
• `Const` **DEFAULT\_FS**: [`GenericFileSystem`](interfaces/GenericFileSystem.md) \| [`CompleteFileSystem`](modules.md#completefilesystem)
#### Defined in
[storage/FileSystem.ts:62](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L62)
___
### DEFAULT\_GRAPH\_STORE\_PERSIST\_FILENAME
• `Const` **DEFAULT\_GRAPH\_STORE\_PERSIST\_FILENAME**: ``"graph_store.json"``
#### Defined in
[storage/constants.ts:6](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L6)
___
### DEFAULT\_INDEX\_STORE\_PERSIST\_FILENAME
• `Const` **DEFAULT\_INDEX\_STORE\_PERSIST\_FILENAME**: ``"index_store.json"``
#### Defined in
[storage/constants.ts:3](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L3)
___
### DEFAULT\_NAMESPACE
• `Const` **DEFAULT\_NAMESPACE**: ``"docstore"``
#### Defined in
[storage/constants.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L7)
___
### DEFAULT\_NUM\_OUTPUTS
• `Const` **DEFAULT\_NUM\_OUTPUTS**: ``256``
#### Defined in
[constants.ts:2](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L2)
___
### DEFAULT\_PADDING
• `Const` **DEFAULT\_PADDING**: ``5``
#### Defined in
[constants.ts:11](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L11)
___
### DEFAULT\_PERSIST\_DIR
• `Const` **DEFAULT\_PERSIST\_DIR**: ``"./storage"``
#### Defined in
[storage/constants.ts:2](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L2)
___
### DEFAULT\_SIMILARITY\_TOP\_K
• `Const` **DEFAULT\_SIMILARITY\_TOP\_K**: ``2``
#### Defined in
[constants.ts:7](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/constants.ts#L7)
___
### DEFAULT\_VECTOR\_STORE\_PERSIST\_FILENAME
• `Const` **DEFAULT\_VECTOR\_STORE\_PERSIST\_FILENAME**: ``"vector_store.json"``
#### Defined in
[storage/constants.ts:5](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/constants.ts#L5)
___
### GPT4\_MODELS
• `Const` **GPT4\_MODELS**: `Object`
#### Type declaration
| Name | Type |
| :------ | :------ |
| `gpt-4` | `number` |
| `gpt-4-32k` | `number` |
#### Defined in
[LLM.ts:44](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L44)
___
### TURBO\_MODELS
• `Const` **TURBO\_MODELS**: `Object`
#### Type declaration
| Name | Type |
| :------ | :------ |
| `gpt-3.5-turbo` | `number` |
| `gpt-3.5-turbo-16k` | `number` |
#### Defined in
[LLM.ts:49](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/LLM.ts#L49)
___
### globalsHelper
• `Const` **globalsHelper**: `GlobalsHelper`
#### Defined in
[GlobalsHelper.ts:42](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/GlobalsHelper.ts#L42)
## Functions
### buildToolsText
▸ **buildToolsText**(`tools`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `tools` | [`ToolMetadata`](interfaces/ToolMetadata.md)[] |
#### Returns
`string`
#### Defined in
[Prompt.ts:198](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L198)
___
### contextSystemPrompt
▸ **contextSystemPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultChoiceSelectPrompt
▸ **defaultChoiceSelectPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultCondenseQuestionPrompt
▸ **defaultCondenseQuestionPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultRefinePrompt
▸ **defaultRefinePrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultSubQuestionPrompt
▸ **defaultSubQuestionPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultSummaryPrompt
▸ **defaultSummaryPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### defaultTextQaPrompt
▸ **defaultTextQaPrompt**(`input`): `string`
A SimplePrompt is a function that takes a dictionary of inputs and returns a string.
NOTE this is a different interface compared to LlamaIndex Python
NOTE 2: we default to empty string to make it easy to calculate prompt sizes
#### Parameters
| Name | Type |
| :------ | :------ |
| `input` | `Record`<`string`, `string`\> |
#### Returns
`string`
#### Defined in
[Prompt.ts:10](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L10)
___
### exists
▸ **exists**(`fs`, `path`): `Promise`<`boolean`\>
Checks if a file exists.
Analogous to the os.path.exists function from Python.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `fs` | [`GenericFileSystem`](interfaces/GenericFileSystem.md) | The filesystem to use. |
| `path` | `string` | The path to the file to check. |
#### Returns
`Promise`<`boolean`\>
A promise that resolves to true if the file exists, false otherwise.
#### Defined in
[storage/FileSystem.ts:74](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L74)
___
### getNodeFS
▸ **getNodeFS**(): [`CompleteFileSystem`](modules.md#completefilesystem)
#### Returns
[`CompleteFileSystem`](modules.md#completefilesystem)
#### Defined in
[storage/FileSystem.ts:51](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L51)
___
### getNodesFromDocument
▸ **getNodesFromDocument**(`document`, `textSplitter`, `includeMetadata?`, `includePrevNextRel?`): [`TextNode`](classes/TextNode.md)[]
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `document` | [`Document`](classes/Document.md) | `undefined` |
| `textSplitter` | [`SentenceSplitter`](classes/SentenceSplitter.md) | `undefined` |
| `includeMetadata` | `boolean` | `true` |
| `includePrevNextRel` | `boolean` | `true` |
#### Returns
[`TextNode`](classes/TextNode.md)[]
#### Defined in
[NodeParser.ts:15](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L15)
___
### getResponseBuilder
▸ **getResponseBuilder**(`serviceContext?`): [`SimpleResponseBuilder`](classes/SimpleResponseBuilder.md)
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext?` | [`ServiceContext`](interfaces/ServiceContext.md) |
#### Returns
[`SimpleResponseBuilder`](classes/SimpleResponseBuilder.md)
#### Defined in
[ResponseSynthesizer.ts:212](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ResponseSynthesizer.ts#L212)
___
### getTextSplitsFromDocument
▸ **getTextSplitsFromDocument**(`document`, `textSplitter`): `string`[]
#### Parameters
| Name | Type |
| :------ | :------ |
| `document` | [`Document`](classes/Document.md) |
| `textSplitter` | [`SentenceSplitter`](classes/SentenceSplitter.md) |
#### Returns
`string`[]
#### Defined in
[NodeParser.ts:5](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/NodeParser.ts#L5)
___
### getTopKEmbeddings
▸ **getTopKEmbeddings**(`queryEmbedding`, `embeddings`, `similarityTopK?`, `embeddingIds?`, `similarityCutoff?`): [`number`[], `any`[]]
Get the top K embeddings from a list of embeddings ordered by similarity to the query.
#### Parameters
| Name | Type | Default value | Description |
| :------ | :------ | :------ | :------ |
| `queryEmbedding` | `number`[] | `undefined` | |
| `embeddings` | `number`[][] | `undefined` | list of embeddings to consider |
| `similarityTopK` | `number` | `DEFAULT_SIMILARITY_TOP_K` | max number of embeddings to return, default 2 |
| `embeddingIds` | ``null`` \| `any`[] | `null` | ids of embeddings in the embeddings list |
| `similarityCutoff` | ``null`` \| `number` | `null` | minimum similarity score |
#### Returns
[`number`[], `any`[]]
#### Defined in
[Embedding.ts:77](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L77)
___
### getTopKEmbeddingsLearner
▸ **getTopKEmbeddingsLearner**(`queryEmbedding`, `embeddings`, `similarityTopK?`, `embeddingsIds?`, `queryMode?`): [`number`[], `any`[]]
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `queryEmbedding` | `number`[] | `undefined` |
| `embeddings` | `number`[][] | `undefined` |
| `similarityTopK?` | `number` | `undefined` |
| `embeddingsIds?` | `any`[] | `undefined` |
| `queryMode` | `VectorStoreQueryMode` | `VectorStoreQueryMode.SVM` |
#### Returns
[`number`[], `any`[]]
#### Defined in
[Embedding.ts:119](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L119)
___
### getTopKMMREmbeddings
▸ **getTopKMMREmbeddings**(`queryEmbedding`, `embeddings`, `similarityFn?`, `similarityTopK?`, `embeddingIds?`, `_similarityCutoff?`, `mmrThreshold?`): [`number`[], `any`[]]
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `queryEmbedding` | `number`[] | `undefined` |
| `embeddings` | `number`[][] | `undefined` |
| `similarityFn` | ``null`` \| (...`args`: `any`[]) => `number` | `null` |
| `similarityTopK` | ``null`` \| `number` | `null` |
| `embeddingIds` | ``null`` \| `any`[] | `null` |
| `_similarityCutoff` | ``null`` \| `number` | `null` |
| `mmrThreshold` | ``null`` \| `number` | `null` |
#### Returns
[`number`[], `any`[]]
#### Defined in
[Embedding.ts:131](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L131)
___
### messagesToHistoryStr
▸ **messagesToHistoryStr**(`messages`): `string`
#### Parameters
| Name | Type |
| :------ | :------ |
| `messages` | [`ChatMessage`](interfaces/ChatMessage.md)[] |
#### Returns
`string`
#### Defined in
[Prompt.ts:300](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Prompt.ts#L300)
___
### serviceContextFromDefaults
▸ **serviceContextFromDefaults**(`options?`): [`ServiceContext`](interfaces/ServiceContext.md)
#### Parameters
| Name | Type |
| :------ | :------ |
| `options?` | [`ServiceContextOptions`](interfaces/ServiceContextOptions.md) |
#### Returns
[`ServiceContext`](interfaces/ServiceContext.md)
#### Defined in
[ServiceContext.ts:32](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L32)
___
### serviceContextFromServiceContext
▸ **serviceContextFromServiceContext**(`serviceContext`, `options`): `Object`
#### Parameters
| Name | Type |
| :------ | :------ |
| `serviceContext` | [`ServiceContext`](interfaces/ServiceContext.md) |
| `options` | [`ServiceContextOptions`](interfaces/ServiceContextOptions.md) |
#### Returns
`Object`
| Name | Type |
| :------ | :------ |
| `callbackManager` | [`CallbackManager`](classes/CallbackManager.md) |
| `embedModel` | [`BaseEmbedding`](classes/BaseEmbedding.md) |
| `llmPredictor` | [`BaseLLMPredictor`](interfaces/BaseLLMPredictor.md) |
| `nodeParser` | [`NodeParser`](interfaces/NodeParser.md) |
| `promptHelper` | `PromptHelper` |
#### Defined in
[ServiceContext.ts:52](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/ServiceContext.ts#L52)
___
### similarity
▸ **similarity**(`embedding1`, `embedding2`, `mode?`): `number`
The similarity between two embeddings.
#### Parameters
| Name | Type | Default value |
| :------ | :------ | :------ |
| `embedding1` | `number`[] | `undefined` |
| `embedding2` | `number`[] | `undefined` |
| `mode` | [`SimilarityType`](enums/SimilarityType.md) | `SimilarityType.DEFAULT` |
#### Returns
`number`
similartiy score with higher numbers meaning the two embeddings are more similar
#### Defined in
[Embedding.ts:22](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/Embedding.ts#L22)
___
### storageContextFromDefaults
▸ **storageContextFromDefaults**(`«destructured»`): `Promise`<[`StorageContext`](interfaces/StorageContext.md)\>
#### Parameters
| Name | Type |
| :------ | :------ |
| `«destructured»` | `BuilderParams` |
#### Returns
`Promise`<[`StorageContext`](interfaces/StorageContext.md)\>
#### Defined in
[storage/StorageContext.ts:28](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/StorageContext.ts#L28)
___
### walk
▸ **walk**(`fs`, `dirPath`): `AsyncIterable`<`string`\>
Recursively traverses a directory and yields all the paths to the files in it.
#### Parameters
| Name | Type | Description |
| :------ | :------ | :------ |
| `fs` | [`WalkableFileSystem`](interfaces/WalkableFileSystem.md) | The filesystem to use. |
| `dirPath` | `string` | The path to the directory to traverse. |
#### Returns
`AsyncIterable`<`string`\>
#### Defined in
[storage/FileSystem.ts:91](https://github.com/run-llama/LlamaIndexTS/blob/d73ac8e/packages/core/src/storage/FileSystem.ts#L91)
+76
View File
@@ -0,0 +1,76 @@
---
sidebar_position: 3
---
# High-Level Concepts
LlamaIndex.TS helps you build LLM-powered applications (e.g. Q&A, chatbot) over custom data.
In this high-level concepts guide, you will learn:
* how an LLM can answer questions using your own data.
* key concepts and modules in LlamaIndex.TS for composing your own query pipeline.
## Answering Questions Across Your Data
LlamaIndex uses a two stage method when using an LLM with your data:
1) **indexing stage**: preparing a knowledge base, and
2) **querying stage**: retrieving relevant context from the knowledge to assist the LLM in responding to a question
![](./_static/concepts/rag.jpg)
This process is also known as Retrieval Augmented Generation (RAG).
LlamaIndex.TS provides the essential toolkit for making both steps super easy.
Let's explore each stage in detail.
### Indexing Stage
LlamaIndex.TS help you prepare the knowledge base with a suite of data connectors and indexes.
![](./_static/concepts/indexing.jpg)
[**Data Loaders**](./modules/high_level/data_loader.md):
A data connector (i.e. `Reader`) ingest data from different data sources and data formats into a simple `Document` representation (text and simple metadata).
[**Documents / Nodes**](./modules/high_level/documents_and_nodes.md): A `Document` is a generic container around any data source - for instance, a PDF, an API output, or retrieved data from a database. A `Node` is the atomic unit of data in LlamaIndex and represents a "chunk" of a source `Document`. It's a rich representation that includes metadata and relationships (to other nodes) to enable accurate and expressive retrieval operations.
[**Data Indexes**](./modules/high_level/data_index.md):
Once you've ingested your data, LlamaIndex helps you index data into a format that's easy to retrieve.
Under the hood, LlamaIndex parses the raw documents into intermediate representations, calculates vector embeddings, and stores your data in-memory or to disk.
### Querying Stage
In the querying stage, the query pipeline retrieves the most relevant context given a user query,
and pass that to the LLM (along with the query) to synthesize a response.
This gives the LLM up-to-date knowledge that is not in its original training data,
(also reducing hallucination).
The key challenge in the querying stage is retrieval, orchestration, and reasoning over (potentially many) knowledge bases.
LlamaIndex provides composable modules that help you build and integrate RAG pipelines for Q&A (query engine), chatbot (chat engine), or as part of an agent.
These building blocks can be customized to reflect ranking preferences, as well as composed to reason over multiple knowledge bases in a structured way.
![](./_static/concepts/querying.jpg)
#### Building Blocks
[**Retrievers**](./modules/low_level/retriever.md):
A retriever defines how to efficiently retrieve relevant context from a knowledge base (i.e. index) when given a query.
The specific retrieval logic differs for difference indices, the most popular being dense retrieval against a vector index.
[**Response Synthesizers**](./modules/low_level/response_synthesizer.md):
A response synthesizer generates a response from an LLM, using a user query and a given set of retrieved text chunks.
#### Pipelines
[**Query Engines**](./modules/high_level/query_engine.md):
A query engine is an end-to-end pipeline that allow you to ask question over your data.
It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.
[**Chat Engines**](./modules/high_level/chat_engine.md):
A chat engine is an end-to-end pipeline for having a conversation with your data
(multiple back-and-forth instead of a single question & answer).
+31
View File
@@ -0,0 +1,31 @@
---
sidebar_position: 3
---
# End to End Examples
We include several end-to-end examples using LlamaIndex.TS in the repository
## [Chat Engine](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/chatEngine.ts)
Read a file and chat about it with the LLM.
## [List Index](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/listIndex.ts)
Create a list index and query it. This example also use the `LLMRetriever`, which will use the LLM to select the best nodes to use when generating answer.
## [Vector Index](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/vectorIndex.ts)
Create a vector index and query it. The vector index will use embeddings to fetch the top k most relevant nodes. By default, the top k is 2.
## [OpenAI LLM](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/openai.ts)
Create an OpenAI LLM and directly use it for chat.
## [SubQuestionQueryEngine](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/subquestion.ts)
Uses the `SubQuestionQueryEngine`, which breaks complex queries into multiple questions, and then aggreates a response across the answers to all sub-questions.
## [Low Level Modules](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/lowlevel.ts)
This example uses several low-level components, which removes the need for an actual query engine. These components can be used anywhere, in any application, or customized and sub-classed to meet your own needs.
+25
View File
@@ -0,0 +1,25 @@
---
sidebar_position: 1
---
# Installation and Setup
## Installation from NPM
Make sure you have NodeJS v18 or higher.
```bash npm2yarn
npm install llamaindex
```
## Environment variables
Our examples use OpenAI by default. You'll need to set up your Open AI key like so:
```bash
export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
```
If you want to have it automatically loaded every time, add it to your .zshrc/.bashrc.
WARNING: do not check in your OpenAI key into version control.
+55
View File
@@ -0,0 +1,55 @@
---
sidebar_position: 0
---
# What is LlamaIndex.TS?
LlamaIndex.TS is a data framework for LLM applications to ingest, structure, and access private or domain-specific data. While a python package is also available (see [here](https://gpt-index.readthedocs.io/en/latest/)), LlamaIndex.TS offers core features in a simple package, optimized for usage with TypeScript.
## 🚀 Why LlamaIndex.TS?
At their core, LLMs offer a natural language interface between humans and inferred data. Widely available models come pre-trained on huge amounts of publicly available data, from Wikipedia and mailing lists to textbooks and source code.
Applications built on top of LLMs often require augmenting these models with private or domain-specific data. Unfortunately, that data can be distributed across siloed applications and data stores. It's behind APIs, in SQL databases, or trapped in PDFs and slide decks.
That's where **LlamaIndex.TS** comes in.
## 🦙 How can LlamaIndex.TS help?
LlamaIndex.TS provides the following tools:
- **Data loading** ingest your existing `txt` and `pdf` data directly
- **Data indexes** structure your data in intermediate representations that are easy and performant for LLMs to consume.
- **Engines** provide natural language access to your data. For example:
- Query engines are powerful retrieval interfaces for knowledge-augmented output.
- Chat engines are conversational interfaces for multi-message, "back and forth" interactions with your data.
## 👨‍👩‍👧‍👦 Who is LlamaIndex for?
LlamaIndex.TS provides a core set of tools, essential for anyone building LLM apps with JavaScript and TypeScript.
Our high-level API allows beginner users to use LlamaIndex.TS to ingest and query their data.
For more complex applications, our lower-level APIs allow advanced users to customize and extend any module—data connectors, indices, retrievers, and query engines, to fit their needs.
## Getting Started
`npm install llamaindex`
Our documentation includes [Installation Instructions](./installation.md) and a [Starter Tutorial](./starter.md) to build your first application.
Once you're up and running, [High-Level Concepts](./concepts.md) has an overview of LlamaIndex's modular architecture. For more hands-on practical examples, look through our [End-to-End Tutorials](LINK TO EXAMPLES FOLDER).
## 🗺️ Ecosystem
To download or contribute, find LlamaIndex on:
- Github: https://github.com/jerryjliu/llama_index
- LlamaIndex (NPM): LINK TO NPM PACKAGE
- LlamaIndex (Python): https://pypi.org/project/llama-index/.
## Community
Need help? Have a feature suggestion? Join the LlamaIndex community:
- Twitter: https://twitter.com/llama_index
- Discord https://discord.gg/dGcwcsnxhU
+3
View File
@@ -0,0 +1,3 @@
label: "Modules"
collapsed: false
position: 4
@@ -0,0 +1 @@
label: High-Level Modules
@@ -0,0 +1,20 @@
---
sidebar_position: 4
---
# ChatEngine
The chat engine is a quick and simple way to chat with the data in your index.
```typescript
const retriever = index.asRetriever();
const chatEngine = new ContextChatEngine({ retriever });
// start chatting
const response = await chatEngine.chat(query);
```
## Api References
- [ContextChatEngine](../../api/classes/ContextChatEngine.md)
- [CondenseQuestionChatEngine](../../api/classes/ContextChatEngine.md)
@@ -0,0 +1,28 @@
---
sidebar_position: 2
---
# Index
An index is the basic container and organization for your data. LlamaIndex.TS supports two indexes:
- `ListIndex` - will send every `Node` in the index to the LLM in order to generate a response
- `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
```typescript
import {
Document,
VectorStoreIndex,
} from "llamaindex";
const document = new Document({ text: "test" });
const index = await VectorStoreIndex.fromDocuments(
[document]
);
```
## API Reference
- [ListIndex](../../api/classes/ListIndex.md)
- [VectorStoreIndex](../../api/classes/VectorStoreIndex.md)
@@ -0,0 +1,17 @@
---
sidebar_position: 1
---
# Reader / Loader
LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class. Currently, `.txt` and `.pdf` files are supported, with more planned in the future!
```typescript
import { SimpleDirectoryReader } from "llamaindex";
documents = new SimpleDirectoryReader().loadData("./data");
```
## API Reference
- [SimpleDirectoryReader](../../api/classes/SimpleDirectoryReader.md)
@@ -0,0 +1,18 @@
---
sidebar_position: 0
---
# Documents and Nodes
`Document`s and `Node`s are the basic building blocks of any index. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.
```typescript
import { Document } from "llamaindex";
document = new Document({ text: "text", metadata: { "key": "val" }});
```
## API Reference
- [Document](../../api/classes/Document.md)
- [TextNode](../../api/classes/TextNode.md)
@@ -0,0 +1,36 @@
---
sidebar_position: 3
---
# QueryEngine
A query engine wraps a `Retriever` and a `ResponseSynthesizer` into a pipeline, that will use the query string to fetech nodes and then send them to the LLM to generate a response.
```typescript
const queryEngine = index.asQueryEngine();
const response = queryEngine.query("query string");
```
## Sub Question Query Engine
The basic concept of the Sub Question Query Engine is that it splits a single query into multiple queries, gets an answer for each of those queries, and then combines those different answers into a single coherent response for the user. You can think of it as the "think this through step by step" prompt technique but iterating over your data sources!
### Getting Started
The easiest way to start trying the Sub Question Query Engine is running the subquestion.ts file in [apps/simple](https://github.com/run-llama/LlamaIndexTS/blob/main/apps/simple/subquestion.ts).
```bash
npx ts-node subquestion.ts
```
### Tools
SubQuestionQueryEngine is implemented with Tools. The basic idea of Tools is that they are executable options for the large language model. In this case, our SubQuestionQueryEngine relies on QueryEngineTool, which as you guessed it is a tool to run queries on a QueryEngine. This allows us to give the model an option to query different documents for different questions for example. You could also imagine that the SubQuestionQueryEngine could use a Tool that searches for something on the web or gets an answer using Wolfram Alpha.
You can learn more about Tools by taking a look at the LlamaIndex Python documentation https://gpt-index.readthedocs.io/en/latest/core_modules/agent_modules/tools/root.html
## API Reference
- [RetrieverQueryEngine](../../api/classes/RetrieverQueryEngine.md)
- [SubQuestionQueryEngine](../../api/classes/SubQuestionQueryEngine.md)
- [QueryEngineTool](../../api/interfaces/QueryEngineTool.md)

Some files were not shown because too many files have changed in this diff Show More