mirror of
https://github.com/run-llama/LlamaIndexTS.git
synced 2026-07-11 00:04:07 -04:00
Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Alex Yang
|
aa0301d870 | ||
|
Alex Yang
|
fc29ef8f5d |
@@ -0,0 +1,40 @@
|
||||
name: Build Docs
|
||||
|
||||
on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
env:
|
||||
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
|
||||
TURBO_TEAM: ${{ vars.TURBO_TEAM }}
|
||||
TURBO_REMOTE_ONLY: true
|
||||
|
||||
jobs:
|
||||
doc:
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
node-version: [20.x, 21.x, 22.x, 23.x]
|
||||
os: [ubuntu-latest, macos-latest, windows-latest]
|
||||
name: Build Docs on Node.js ${{ matrix.node-version }} (${{ matrix.os }})
|
||||
runs-on: ${{ matrix.os }}
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: pnpm/action-setup@v4
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v4
|
||||
with:
|
||||
node-version: ${{ matrix.node-version }}
|
||||
cache: "pnpm"
|
||||
- name: Install dependencies
|
||||
run: pnpm install
|
||||
- name: Run Build
|
||||
run: pnpx turbo run build --filter @llamaindex/doc
|
||||
@@ -119,7 +119,7 @@ jobs:
|
||||
run: pnpm run build
|
||||
- name: Build ${{ matrix.packages }}
|
||||
run: pnpm run build
|
||||
working-directory: e2e/examples/${{ matrix.packages }}
|
||||
working-directory: packages/llamaindex/e2e/examples/${{ matrix.packages }}
|
||||
|
||||
typecheck-examples:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
+55
-35
@@ -2,58 +2,78 @@
|
||||
|
||||
## Structure
|
||||
|
||||
LlamaIndex.TS uses pnpm monorepo.
|
||||
This is a monorepo built with Turborepo
|
||||
|
||||
We recommend you to understand the basics of Node.js, TypeScript, pnpm, and of course, LLM before contributing.
|
||||
Right now, for first-time contributors, these three packages are of the highest importance:
|
||||
|
||||
There are some important folders in the repository:
|
||||
- `packages/llamaindex` which is the main NPM library `llamaindex`
|
||||
- `examples` is where the demo code lives
|
||||
- `apps/next` is where the code for the documentation of https://ts.llamaindex.ai/ is located
|
||||
|
||||
- `packages/*`: Contains the source code of the packages. Each package is a separate npm package.
|
||||
- `llamaindex`: The starter package for LlamaIndex.TS, which contains the all sub-packages.
|
||||
- `core`: The core package of LlamaIndex.TS, which contains the abstract classes and interfaces. It is designed for
|
||||
all JS runtime environments.
|
||||
- `env`: The environment package of LlamaIndex.TS, which contains the environment-specific classes and interfaces. It
|
||||
includes compatibility layers for Node.js, Deno, Vercel Edge Runtime, Cloudflare Workers...
|
||||
- `apps/*`: The applications based on LlamaIndex.TS.
|
||||
- `next`: Our documentation website based on Next.js.
|
||||
- `examples`: The code examples of LlamaIndex.TS using Node.js.
|
||||
### Turborepo docs
|
||||
|
||||
You can checkout how Turborepo works using the default [README-turborepo.md](/README-turborepo.md)
|
||||
|
||||
## Getting Started
|
||||
|
||||
Make sure you have Node.js LIS (Long-term Support) installed. You can check your Node.js version by running:
|
||||
Install NodeJS. Preferably v18 using nvm or n.
|
||||
|
||||
Inside the LlamaIndexTS directory:
|
||||
|
||||
```shell
|
||||
node -v
|
||||
# v20.x.x
|
||||
```
|
||||
|
||||
### Use pnpm
|
||||
|
||||
```shell
|
||||
corepack enable
|
||||
```
|
||||
|
||||
### Install dependencies
|
||||
|
||||
```shell
|
||||
pnpm install
|
||||
```
|
||||
|
||||
### Build the packages
|
||||
### Running Typescript
|
||||
|
||||
```shell
|
||||
# Build all packages
|
||||
turbo build --filter "./packages/*"
|
||||
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
|
||||
```
|
||||
|
||||
### Docs
|
||||
To write new test cases write them in [packages/llamaindex/tests](/packages/llamaindex/tests)
|
||||
|
||||
See the [docs](./apps/next/README.md) for more information.
|
||||
We use Vitest https://vitest.dev to write our test cases. Vitest comes with a bunch of built-in assertions using the expect function: https://vitest.dev/api/expect.html#expect
|
||||
|
||||
### Demo applications
|
||||
|
||||
There is an existing ["example"](/examples/README.md) demos folder with mainly NodeJS scripts. Feel free to add additional demos to that folder. If you would like to try out your changes in the `llamaindex` package with a new demo, you need to run the build command in the README.
|
||||
|
||||
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. llamaindex or docs]
|
||||
```
|
||||
|
||||
To install packages for every package or application run
|
||||
|
||||
```
|
||||
pnpm add -w [NPM Package]
|
||||
```
|
||||
|
||||
### Doc
|
||||
|
||||
To contribute to the docs, go to the docs website folder and run the Next.js server:
|
||||
|
||||
```bash
|
||||
# run this if you are first time
|
||||
pnpx turbo run build --filter @llamaindex/doc
|
||||
cd apps/next
|
||||
pnpm run dev
|
||||
```
|
||||
|
||||
## Changeset
|
||||
|
||||
We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
|
||||
changeset, run in the root folder:
|
||||
We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new changeset, run in the root folder:
|
||||
|
||||
```
|
||||
pnpm changeset
|
||||
@@ -67,6 +87,6 @@ The [Release Github Action](.github/workflows/release.yml) is automatically gene
|
||||
PR called "Release {version}".
|
||||
|
||||
This PR will update the `package.json` and `CHANGELOG.md` files of each package according to
|
||||
the current changesets in the [.changeset](.changeset) folder.
|
||||
the current changesets in the [.changeset](.changeset/) folder.
|
||||
|
||||
If this PR is merged it will automatically add version tags to the repository and publish the updated packages to NPM.
|
||||
|
||||
@@ -1,63 +1,5 @@
|
||||
# docs
|
||||
|
||||
## 0.0.116
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.12
|
||||
|
||||
## 0.0.115
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.11
|
||||
|
||||
## 0.0.114
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- llamaindex@0.8.10
|
||||
- @llamaindex/examples@0.0.14
|
||||
|
||||
## 0.0.113
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- Updated dependencies [4d4cd8a]
|
||||
- llamaindex@0.8.9
|
||||
|
||||
## 0.0.112
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- llamaindex@0.8.8
|
||||
- @llamaindex/examples@0.0.13
|
||||
|
||||
## 0.0.111
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.7
|
||||
|
||||
## 0.0.110
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- llamaindex@0.8.6
|
||||
|
||||
## 0.0.109
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- Updated dependencies [a6db5dd]
|
||||
- Updated dependencies [396b1e1]
|
||||
- llamaindex@0.8.5
|
||||
|
||||
## 0.0.108
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -25,7 +25,6 @@ ANTHROPIC_CLAUDE_3_SONNET = "anthropic.claude-3-sonnet-20240229-v1:0";
|
||||
ANTHROPIC_CLAUDE_3_HAIKU = "anthropic.claude-3-haiku-20240307-v1:0";
|
||||
ANTHROPIC_CLAUDE_3_OPUS = "anthropic.claude-3-opus-20240229-v1:0"; // available on us-west-2
|
||||
ANTHROPIC_CLAUDE_3_5_SONNET = "anthropic.claude-3-5-sonnet-20240620-v1:0";
|
||||
ANTHROPIC_CLAUDE_3_5_HAIKU = "anthropic.claude-3-5-haiku-20241022-v1:0";
|
||||
META_LLAMA2_13B_CHAT = "meta.llama2-13b-chat-v1";
|
||||
META_LLAMA2_70B_CHAT = "meta.llama2-70b-chat-v1";
|
||||
META_LLAMA3_8B_INSTRUCT = "meta.llama3-8b-instruct-v1:0";
|
||||
|
||||
+17
-17
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "docs",
|
||||
"version": "0.0.116",
|
||||
"version": "0.0.108",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"docusaurus": "docusaurus",
|
||||
@@ -15,29 +15,29 @@
|
||||
"typecheck": "tsc"
|
||||
},
|
||||
"dependencies": {
|
||||
"@docusaurus/core": "3.6.0",
|
||||
"@docusaurus/remark-plugin-npm2yarn": "3.6.0",
|
||||
"@docusaurus/core": "3.5.2",
|
||||
"@docusaurus/remark-plugin-npm2yarn": "3.5.2",
|
||||
"@llamaindex/examples": "workspace:*",
|
||||
"@mdx-js/react": "^3.1.0",
|
||||
"clsx": "^2.1.1",
|
||||
"@mdx-js/react": "3.0.1",
|
||||
"clsx": "2.1.1",
|
||||
"llamaindex": "workspace:*",
|
||||
"postcss": "^8.4.47",
|
||||
"prism-react-renderer": "^2.4.0",
|
||||
"raw-loader": "^4.0.2",
|
||||
"react": "^18.3.1",
|
||||
"postcss": "8.4.41",
|
||||
"prism-react-renderer": "2.4.0",
|
||||
"raw-loader": "4.0.2",
|
||||
"react": "18.3.1",
|
||||
"react-dom": "18.3.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@docusaurus/module-type-aliases": "3.6.0",
|
||||
"@docusaurus/preset-classic": "3.6.0",
|
||||
"@docusaurus/theme-classic": "3.6.0",
|
||||
"@docusaurus/types": "3.6.0",
|
||||
"@docusaurus/module-type-aliases": "3.5.2",
|
||||
"@docusaurus/preset-classic": "3.5.2",
|
||||
"@docusaurus/theme-classic": "3.5.2",
|
||||
"@docusaurus/types": "3.5.2",
|
||||
"@tsconfig/docusaurus": "2.0.3",
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"docusaurus-plugin-typedoc": "1.0.5",
|
||||
"typedoc": "0.26.11",
|
||||
"typedoc-plugin-markdown": "4.2.10",
|
||||
"typescript": "^5.6.3"
|
||||
"typedoc": "0.26.6",
|
||||
"typedoc-plugin-markdown": "4.2.6",
|
||||
"typescript": "^5.6.2"
|
||||
},
|
||||
"browserslist": {
|
||||
"production": [
|
||||
|
||||
@@ -1,108 +1,5 @@
|
||||
# @llamaindex/doc
|
||||
|
||||
## 0.0.14
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [7ae6eaa]
|
||||
- @llamaindex/core@0.4.9
|
||||
- @llamaindex/openai@0.1.34
|
||||
- @llamaindex/cloud@2.0.9
|
||||
- llamaindex@0.8.12
|
||||
- @llamaindex/node-parser@0.0.10
|
||||
- @llamaindex/readers@1.0.10
|
||||
|
||||
## 0.0.13
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f865c98]
|
||||
- @llamaindex/core@0.4.8
|
||||
- @llamaindex/cloud@2.0.8
|
||||
- llamaindex@0.8.11
|
||||
- @llamaindex/node-parser@0.0.9
|
||||
- @llamaindex/openai@0.1.33
|
||||
- @llamaindex/readers@1.0.9
|
||||
|
||||
## 0.0.12
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- Updated dependencies [d89ebe0]
|
||||
- Updated dependencies [fd8c882]
|
||||
- Updated dependencies [fd8c882]
|
||||
- llamaindex@0.8.10
|
||||
- @llamaindex/core@0.4.7
|
||||
- @llamaindex/workflow@0.0.4
|
||||
- @llamaindex/cloud@2.0.7
|
||||
- @llamaindex/node-parser@0.0.8
|
||||
- @llamaindex/openai@0.1.32
|
||||
- @llamaindex/readers@1.0.8
|
||||
|
||||
## 0.0.11
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- Updated dependencies [4d4cd8a]
|
||||
- llamaindex@0.8.9
|
||||
- @llamaindex/cloud@2.0.6
|
||||
- @llamaindex/core@0.4.6
|
||||
- @llamaindex/node-parser@0.0.7
|
||||
- @llamaindex/openai@0.1.31
|
||||
- @llamaindex/readers@1.0.7
|
||||
|
||||
## 0.0.10
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- @llamaindex/core@0.4.5
|
||||
- llamaindex@0.8.8
|
||||
- @llamaindex/node-parser@0.0.6
|
||||
- @llamaindex/workflow@0.0.3
|
||||
- @llamaindex/cloud@2.0.5
|
||||
- @llamaindex/openai@0.1.30
|
||||
- @llamaindex/readers@1.0.6
|
||||
|
||||
## 0.0.9
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- @llamaindex/cloud@2.0.4
|
||||
- @llamaindex/core@0.4.4
|
||||
- llamaindex@0.8.7
|
||||
- @llamaindex/node-parser@0.0.5
|
||||
- @llamaindex/openai@0.1.29
|
||||
- @llamaindex/readers@1.0.5
|
||||
|
||||
## 0.0.8
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- @llamaindex/core@0.4.3
|
||||
- llamaindex@0.8.6
|
||||
- @llamaindex/cloud@2.0.3
|
||||
- @llamaindex/node-parser@0.0.4
|
||||
- @llamaindex/openai@0.1.28
|
||||
- @llamaindex/readers@1.0.4
|
||||
|
||||
## 0.0.7
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- Updated dependencies [a6db5dd]
|
||||
- Updated dependencies [396b1e1]
|
||||
- llamaindex@0.8.5
|
||||
- @llamaindex/cloud@2.0.2
|
||||
- @llamaindex/core@0.4.2
|
||||
- @llamaindex/node-parser@0.0.3
|
||||
- @llamaindex/openai@0.1.27
|
||||
- @llamaindex/readers@1.0.3
|
||||
|
||||
## 0.0.6
|
||||
|
||||
### Patch Changes
|
||||
|
||||
+8
-3
@@ -1,4 +1,4 @@
|
||||
# Docs
|
||||
# next
|
||||
|
||||
This is a Next.js application generated with
|
||||
[Create Fumadocs](https://github.com/fuma-nama/fumadocs).
|
||||
@@ -6,10 +6,15 @@ This is a Next.js application generated with
|
||||
Run development server:
|
||||
|
||||
```bash
|
||||
turbo run dev
|
||||
# turbo will build all required packages before running the dev server
|
||||
npm run dev
|
||||
# or
|
||||
pnpm dev
|
||||
# or
|
||||
yarn dev
|
||||
```
|
||||
|
||||
Open http://localhost:3000 with your browser to see the result.
|
||||
|
||||
## Learn More
|
||||
|
||||
To learn more about Next.js and Fumadocs, take a look at the following
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@llamaindex/doc",
|
||||
"version": "0.0.14",
|
||||
"version": "0.0.6",
|
||||
"private": true,
|
||||
"scripts": {
|
||||
"build": "pnpm run build:docs && next build",
|
||||
@@ -12,7 +12,6 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@icons-pack/react-simple-icons": "^10.1.0",
|
||||
"@llamaindex/chat-ui": "0.0.5",
|
||||
"@llamaindex/cloud": "workspace:*",
|
||||
"@llamaindex/core": "workspace:*",
|
||||
"@llamaindex/node-parser": "workspace:*",
|
||||
@@ -68,7 +67,7 @@
|
||||
"devDependencies": {
|
||||
"@next/env": "^15.0.2",
|
||||
"@types/mdx": "^2.0.13",
|
||||
"@types/node": "22.9.0",
|
||||
"@types/node": "22.8.6",
|
||||
"@types/react": "^18.3.12",
|
||||
"@types/react-dom": "^18.3.1",
|
||||
"autoprefixer": "^10.4.20",
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut } from "@llamaindex/cloud/api";
|
||||
import { PipelinesService } from "@llamaindex/cloud/api";
|
||||
import fg from "fast-glob";
|
||||
import {
|
||||
fileGenerator,
|
||||
@@ -30,8 +30,9 @@ async function processContent(content: string): Promise<string> {
|
||||
}
|
||||
|
||||
export async function updateLlamaCloud(): Promise<void> {
|
||||
// eslint-disable-next-line turbo/no-undeclared-env-vars
|
||||
const apiKey = process.env.LLAMA_CLOUD_API_KEY;
|
||||
|
||||
// eslint-disable-next-line turbo/no-undeclared-env-vars
|
||||
const index = process.env.LLAMA_CLOUD_PIPELINE_ID;
|
||||
|
||||
if (!apiKey || !index) {
|
||||
@@ -82,26 +83,28 @@ export async function updateLlamaCloud(): Promise<void> {
|
||||
|
||||
console.log(`added ${records.length} records`);
|
||||
|
||||
await upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut({
|
||||
baseUrl: "https://api.cloud.llamaindex.ai/",
|
||||
body: records.map((record) => ({
|
||||
id: record.id,
|
||||
metadata: {
|
||||
title: record.title,
|
||||
description: record.description,
|
||||
documentUrl: record.id,
|
||||
category: record.category,
|
||||
await PipelinesService.upsertBatchPipelineDocumentsApiV1PipelinesPipelineIdDocumentsPut(
|
||||
{
|
||||
baseUrl: "https://api.cloud.llamaindex.ai/",
|
||||
body: records.map((record) => ({
|
||||
id: record.id,
|
||||
metadata: {
|
||||
title: record.title,
|
||||
description: record.description,
|
||||
documentUrl: record.id,
|
||||
category: record.category,
|
||||
},
|
||||
text: record.content,
|
||||
})),
|
||||
path: {
|
||||
pipeline_id: index,
|
||||
},
|
||||
throwOnError: true,
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
text: record.content,
|
||||
})),
|
||||
path: {
|
||||
pipeline_id: index,
|
||||
},
|
||||
throwOnError: true,
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
});
|
||||
);
|
||||
|
||||
console.log("done");
|
||||
}
|
||||
|
||||
@@ -25,16 +25,15 @@ export default function HomePage() {
|
||||
return (
|
||||
<main className="container mx-auto px-4 py-12">
|
||||
<h1 className="text-4xl md:text-6xl font-bold text-center mb-4">
|
||||
Build context-augmented web apps using
|
||||
Build RAG Web App using
|
||||
<br /> <span className="text-blue-500">LlamaIndex.TS</span>
|
||||
</h1>
|
||||
<p className="text-xl text-center text-fd-muted-foreground mb-12 ">
|
||||
LlamaIndex.TS is the JS/TS version of{" "}
|
||||
<a href="https://llamaindex.ai">LlamaIndex</a>, the framework for
|
||||
building agentic generative AI applications connected to your data.
|
||||
LlamaIndex.TS is the JS/TS library from our popular Python library
|
||||
llama-index for building LLM applications
|
||||
</p>
|
||||
<div className="text-center text-lg text-fd-muted-foreground mb-12">
|
||||
<span>Designed for building web applications in </span>
|
||||
<span>Designed for building web applications under </span>
|
||||
<TextEffect />
|
||||
</div>
|
||||
|
||||
@@ -59,8 +58,8 @@ export default function HomePage() {
|
||||
<Feature
|
||||
icon={Footprints}
|
||||
subheading="Progressive"
|
||||
heading="From the simplest to the most complex"
|
||||
description="LlamaIndex.TS is designed to be simple to get started, but powerful enough to build complex, agentic AI applications."
|
||||
heading="Adding AI feature from simple to complex"
|
||||
description="LlamaIndex.TS is designed to be simple to start with and can be extended to build complex AI applications."
|
||||
>
|
||||
<Suspense
|
||||
fallback={
|
||||
@@ -114,9 +113,9 @@ const response = await agent.chat({
|
||||
</Feature>
|
||||
<Feature
|
||||
icon={Bot}
|
||||
subheading="Agents"
|
||||
heading="Build agentic RAG applications"
|
||||
description="Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them."
|
||||
subheading="Agent"
|
||||
heading="Build agent for RAG"
|
||||
description="Build agents for RAG using LlamaIndex.TS. Agents are the core building blocks of RAG applications."
|
||||
>
|
||||
<CodeBlock
|
||||
code={`import { FunctionTool } from "llamaindex";
|
||||
@@ -138,19 +137,19 @@ await agent.chat('...');`}
|
||||
<Feature
|
||||
icon={Blocks}
|
||||
subheading="Providers"
|
||||
heading="LLMs, Data Loaders, Vector Stores and more!"
|
||||
description="LlamaIndex.TS has hundreds of integrations to connect to your data, index it, and query it with LLMs."
|
||||
heading="LLM / Data Loader / Vector Store"
|
||||
description="LlamaIndex.TS provides various providers to turn your data into valuable insights."
|
||||
>
|
||||
<div className="mt-8 flex flex-col gap-8">
|
||||
<div>
|
||||
<h3 className="text-lg font-semibold text-fd-muted-foreground mb-2">
|
||||
LLMs
|
||||
LLM
|
||||
</h3>
|
||||
<InfiniteLLMProviders />
|
||||
</div>
|
||||
<div>
|
||||
<h3 className="text-lg font-semibold text-fd-muted-foreground mb-2">
|
||||
Vector Stores
|
||||
Vector Store
|
||||
</h3>
|
||||
<InfiniteVectorStoreProviders />
|
||||
</div>
|
||||
@@ -158,8 +157,8 @@ await agent.chat('...');`}
|
||||
</Feature>
|
||||
<Feature
|
||||
icon={Terminal}
|
||||
subheading="create-llama CLI"
|
||||
heading="Build a RAG app with a single command"
|
||||
subheading="Create Llama CLI"
|
||||
heading="CLI for starting RAG app with one line"
|
||||
description="A command line tool to generate LlamaIndex apps, the easiest way to get started with LlamaIndex."
|
||||
>
|
||||
<div className="my-6">
|
||||
|
||||
@@ -1,30 +0,0 @@
|
||||
import { LlamaIndexAdapter, type Message } from "ai";
|
||||
import { SimpleChatEngine, type ChatMessage } from "llamaindex";
|
||||
import { NextResponse, type NextRequest } from "next/server";
|
||||
|
||||
export async function POST(request: NextRequest) {
|
||||
try {
|
||||
const { messages } = (await request.json()) as { messages: Message[] };
|
||||
const userMessage = messages[messages.length - 1];
|
||||
if (!userMessage || userMessage.role !== "user") {
|
||||
return NextResponse.json(
|
||||
{ detail: "Last message is not a user message" },
|
||||
{ status: 400 },
|
||||
);
|
||||
}
|
||||
|
||||
const chatEngine = new SimpleChatEngine();
|
||||
|
||||
return LlamaIndexAdapter.toDataStreamResponse(
|
||||
await chatEngine.chat({
|
||||
message: userMessage.content,
|
||||
chatHistory: messages as ChatMessage[],
|
||||
stream: true,
|
||||
}),
|
||||
{},
|
||||
);
|
||||
} catch (error) {
|
||||
const detail = (error as Error).message;
|
||||
return NextResponse.json({ detail }, { status: 500 });
|
||||
}
|
||||
}
|
||||
@@ -7,8 +7,9 @@ import { ReactElement } from "react";
|
||||
export function Contributing(): ReactElement {
|
||||
return (
|
||||
<div className="flex flex-col items-center border-x border-t px-4 py-16 text-center">
|
||||
<Heart className="mb-4" />
|
||||
<h2 className="mb-4 text-xl font-semibold sm:text-2xl">
|
||||
Made possible by you <Heart className="inline align-middle" />
|
||||
Made Possible by You.
|
||||
</h2>
|
||||
<p className="mb-4 text-fd-muted-foreground">
|
||||
LlamaIndex.TS is powered by the open source community.
|
||||
|
||||
@@ -53,6 +53,9 @@ export default async function ContributorCounter({
|
||||
</div>
|
||||
) : null}
|
||||
</div>
|
||||
<div className="text-center text-sm text-fd-muted-foreground">
|
||||
Some of our best contributors.
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
}
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
"use client";
|
||||
import { ChatSection } from "@llamaindex/chat-ui";
|
||||
import { useChat } from "ai/react";
|
||||
|
||||
export const ChatDemo = () => {
|
||||
const handler = useChat();
|
||||
return <ChatSection handler={handler} />;
|
||||
};
|
||||
@@ -1,46 +0,0 @@
|
||||
---
|
||||
title: Chat-UI
|
||||
description: Use chat-ui to add a chat interface to your LlamaIndexTS application.
|
||||
---
|
||||
import { ChatDemo } from '../../../../components/demo/chat';
|
||||
import "@llamaindex/chat-ui/styles/code.css";
|
||||
import "@llamaindex/chat-ui/styles/katex.css";
|
||||
|
||||
Using [chat-ui](https://github.com/run-llama/chat-ui), it's easy to add a chat interface to your LlamaIndexTS application.
|
||||
You just need to create an API route that provides an `api/chat` endpoint and a chat component to consume the API.
|
||||
|
||||
## API route
|
||||
|
||||
As an example, this is an API route for the Next.js App Router. Copy the following code into your `app/api/chat/route.ts` file to get started:
|
||||
|
||||
```json doc-gen:file
|
||||
{
|
||||
"file": "./src/app/api/chat/route.ts",
|
||||
"codeblock": true
|
||||
}
|
||||
```
|
||||
|
||||
## Chat UI
|
||||
|
||||
This is the simplest way to add a chat interface to your application. Copy the following code into your application to consume the API:
|
||||
|
||||
```json doc-gen:file
|
||||
{
|
||||
"file": "./src/components/demo/chat.tsx",
|
||||
"codeblock": true
|
||||
}
|
||||
```
|
||||
|
||||
## Try it out ⬇️
|
||||
|
||||
Combining both, you're getting a fully functional chat interface:
|
||||
|
||||
<ChatDemo />
|
||||
|
||||
## Next Steps
|
||||
|
||||
The steps above are the bare minimum to get a chat interface working. From here, you can go two ways:
|
||||
|
||||
1. Use [create-llama](https://github.com/run-llama/create-llama) to scaffold a new LlamaIndexTS project including complex API routes and chat interfaces or
|
||||
2. Learn more about [chat-ui](https://github.com/run-llama/chat-ui) and [LlamaIndexTS](https://github.com/run-llama/llamaindex-ts) to customize the chat interface and API routes to your needs.
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"title": "Guide",
|
||||
"description": "See our guide",
|
||||
"pages": ["workflow", "chat"]
|
||||
"pages": ["workflow"]
|
||||
}
|
||||
|
||||
@@ -93,35 +93,6 @@ See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/m
|
||||
</Accordion>
|
||||
</Accordions>
|
||||
|
||||
## Enable AsyncIterable for `Web Stream` API
|
||||
|
||||
Some modules uses `Web Stream` API like `ReadableStream` and `WritableStream`, you need to enable `DOM.AsyncIterable` in your `tsconfig.json`.
|
||||
|
||||
```json5
|
||||
{
|
||||
compilerOptions: {
|
||||
// ⬇️ add this lib to your tsconfig.json
|
||||
lib: ["DOM.AsyncIterable"],
|
||||
},
|
||||
}
|
||||
```
|
||||
|
||||
```ts twoslash
|
||||
import { OpenAIAgent } from '@llamaindex/openai'
|
||||
|
||||
const agent = new OpenAIAgent({
|
||||
tools: []
|
||||
})
|
||||
|
||||
const response = await agent.chat({
|
||||
message: 'Hello, how are you?',
|
||||
stream: true
|
||||
})
|
||||
for await (const _ of response) {
|
||||
//^?
|
||||
// ...
|
||||
}
|
||||
```
|
||||
|
||||
## Run TypeScript Script in Node.js
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
import {
|
||||
type MetadataFilter,
|
||||
type MetadataFilters,
|
||||
PipelinesService,
|
||||
type RetrievalParams,
|
||||
runSearchApiV1PipelinesPipelineIdRetrievePost,
|
||||
type TextNodeWithScore,
|
||||
} from "@llamaindex/cloud/api";
|
||||
import { QueryBundle } from "@llamaindex/core/query-engine";
|
||||
@@ -74,7 +74,7 @@ export class LlamaCloudRetriever extends BaseRetriever {
|
||||
const pipelineId = this.pipelineId;
|
||||
|
||||
const { data: results } =
|
||||
await runSearchApiV1PipelinesPipelineIdRetrievePost({
|
||||
await PipelinesService.runSearchApiV1PipelinesPipelineIdRetrievePost({
|
||||
throwOnError: true,
|
||||
path: {
|
||||
pipeline_id: pipelineId,
|
||||
|
||||
@@ -10,7 +10,6 @@ export default {
|
||||
"./src/mdx-components.{ts,tsx}",
|
||||
"./node_modules/fumadocs-ui/dist/**/*.js",
|
||||
"./node_modules/fumadocs-openapi/dist/**/*.js",
|
||||
"./node_modules/@llamaindex/chat-ui/**/*.{ts,tsx}",
|
||||
],
|
||||
presets: [createPreset()],
|
||||
// eslint-disable-next-line @typescript-eslint/no-require-imports
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
{
|
||||
"extends": ["//"],
|
||||
"tasks": {
|
||||
"build": {
|
||||
"outputs": [
|
||||
".next",
|
||||
".source",
|
||||
"next-env.d.ts",
|
||||
"src/content/docs/cloud/api/**"
|
||||
]
|
||||
},
|
||||
"dev": {
|
||||
"dependsOn": ["^build"]
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,3 +0,0 @@
|
||||
import { OpenAI } from "./openai.js";
|
||||
|
||||
export class Ollama extends OpenAI {}
|
||||
@@ -1,35 +0,0 @@
|
||||
import { Ollama } from "@llamaindex/ollama";
|
||||
import assert from "node:assert";
|
||||
import { test } from "node:test";
|
||||
import { getWeatherTool } from "./fixtures/tools.js";
|
||||
import { mockLLMEvent } from "./utils.js";
|
||||
|
||||
await test("ollama", async (t) => {
|
||||
await mockLLMEvent(t, "ollama");
|
||||
await t.test("ollama function call", async (t) => {
|
||||
const llm = new Ollama({
|
||||
model: "llama3.2",
|
||||
});
|
||||
const chatResponse = await llm.chat({
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: "What is the weather in Paris?",
|
||||
},
|
||||
],
|
||||
tools: [getWeatherTool],
|
||||
});
|
||||
if (
|
||||
chatResponse.message.options &&
|
||||
"toolCall" in chatResponse.message.options
|
||||
) {
|
||||
assert.equal(chatResponse.message.options.toolCall.length, 1);
|
||||
assert.equal(
|
||||
chatResponse.message.options.toolCall[0]!.name,
|
||||
getWeatherTool.metadata.name,
|
||||
);
|
||||
} else {
|
||||
throw new Error("Expected tool calls in response");
|
||||
}
|
||||
});
|
||||
});
|
||||
@@ -1,393 +0,0 @@
|
||||
{
|
||||
"llmEventStart": [
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "calculate 2 + 2"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "calculate 2 + 2"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": {
|
||||
"a": 2,
|
||||
"b": 2
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "4",
|
||||
"options": {
|
||||
"toolResult": {
|
||||
"result": "4",
|
||||
"isError": false,
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"llmEventEnd": [
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"response": {
|
||||
"raw": null,
|
||||
"message": {
|
||||
"content": "",
|
||||
"role": "assistant",
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": {
|
||||
"a": 2,
|
||||
"b": 2
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"response": {
|
||||
"raw": null,
|
||||
"message": {
|
||||
"content": "The result of \\(2 + 2\\) is \\(4\\).",
|
||||
"role": "assistant",
|
||||
"options": {}
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"llmEventStream": [
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": "{\"a\":2,\"b\":2}"
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "sumNumbers",
|
||||
"id": "call_S2x0FUa475GVpNQJ796Rc9fd",
|
||||
"input": {
|
||||
"a": 2,
|
||||
"b": 2
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"delta": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "The"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " result"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " of"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " \\("
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "2"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " +"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " "
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "2"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "\\"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": ")"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " is"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": " \\("
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "4"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": "\\"
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": ")."
|
||||
}
|
||||
},
|
||||
{
|
||||
"id": "PRESERVE_1",
|
||||
"chunk": {
|
||||
"raw": null,
|
||||
"options": {},
|
||||
"delta": ""
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,37 +0,0 @@
|
||||
{
|
||||
"llmEventStart": [
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the weather in Paris?"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"llmEventEnd": [
|
||||
{
|
||||
"id": "PRESERVE_0",
|
||||
"response": {
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"options": {
|
||||
"toolCall": [
|
||||
{
|
||||
"name": "getWeather",
|
||||
"input": {
|
||||
"city": "Paris"
|
||||
},
|
||||
"id": "5d198775-5268-4552-993b-9ecb4425385b"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"raw": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"llmEventStream": []
|
||||
}
|
||||
@@ -1,28 +1,5 @@
|
||||
# examples
|
||||
|
||||
## 0.0.14
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- Updated dependencies [d89ebe0]
|
||||
- Updated dependencies [fd8c882]
|
||||
- Updated dependencies [fd8c882]
|
||||
- llamaindex@0.8.10
|
||||
- @llamaindex/core@0.4.7
|
||||
- @llamaindex/workflow@0.0.4
|
||||
- @llamaindex/readers@1.0.8
|
||||
|
||||
## 0.0.13
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- @llamaindex/core@0.4.5
|
||||
- llamaindex@0.8.8
|
||||
- @llamaindex/workflow@0.0.3
|
||||
- @llamaindex/readers@1.0.6
|
||||
|
||||
## 0.0.12
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -1,71 +0,0 @@
|
||||
import "dotenv/config";
|
||||
|
||||
import {
|
||||
DefaultAzureCredential,
|
||||
getBearerTokenProvider,
|
||||
} from "@azure/identity";
|
||||
import {
|
||||
AzureCosmosDBNoSqlVectorStore,
|
||||
AzureCosmosNoSqlDocumentStore,
|
||||
AzureCosmosNoSqlIndexStore,
|
||||
Document,
|
||||
OpenAI,
|
||||
OpenAIEmbedding,
|
||||
Settings,
|
||||
storageContextFromDefaults,
|
||||
VectorStoreIndex,
|
||||
} from "llamaindex";
|
||||
/**
|
||||
* This example demonstrates how to use Azure CosmosDB with LlamaIndex.
|
||||
* It uses Azure CosmosDB as IndexStore, DocumentStore, and VectorStore.
|
||||
*
|
||||
* To run this example, create an .env file under /examples and set the following environment variables:
|
||||
*
|
||||
* AZURE_OPENAI_ENDPOINT="https://AOAI-ACCOUNT.openai.azure.com" // Sample Azure OpenAI endpoint.
|
||||
* AZURE_DEPLOYMENT_NAME="gpt-4o" // Sample Azure OpenAI deployment name.
|
||||
* EMBEDDING_MODEL="text-embedding-3-large" // Sample Azure OpenAI embedding model.
|
||||
* AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT = "https://DB-ACCOUNT.documents.azure.com:443/" // Sample CosmosDB account endpoint.
|
||||
*
|
||||
* This example uses managed identity to authenticate with Azure CosmosDB and Azure OpenAI. Make sure to assign the required roles to the managed identity.
|
||||
* You can also use connectionString for Azure CosmosDB and Keys with Azure OpenAI for authentication.
|
||||
*/
|
||||
(async () => {
|
||||
const credential = new DefaultAzureCredential();
|
||||
const azureADTokenProvider = getBearerTokenProvider(
|
||||
credential,
|
||||
"https://cognitiveservices.azure.com/.default",
|
||||
);
|
||||
|
||||
const azure = {
|
||||
azureADTokenProvider,
|
||||
deployment: process.env.AZURE_DEPLOYMENT_NAME,
|
||||
};
|
||||
Settings.llm = new OpenAI({ azure });
|
||||
Settings.embedModel = new OpenAIEmbedding({
|
||||
model: process.env.EMBEDDING_MODEL,
|
||||
azure: {
|
||||
...azure,
|
||||
deployment: process.env.EMBEDDING_MODEL,
|
||||
},
|
||||
});
|
||||
const docStore = AzureCosmosNoSqlDocumentStore.fromAadToken();
|
||||
console.log({ docStore });
|
||||
const indexStore = AzureCosmosNoSqlIndexStore.fromAadToken();
|
||||
console.log({ indexStore });
|
||||
const vectorStore = AzureCosmosDBNoSqlVectorStore.fromUriAndManagedIdentity();
|
||||
console.log({ vectorStore });
|
||||
const storageContext = await storageContextFromDefaults({
|
||||
docStore,
|
||||
indexStore,
|
||||
vectorStore,
|
||||
});
|
||||
console.log({ storageContext });
|
||||
|
||||
const document = new Document({ text: "Test Text" });
|
||||
const index = await VectorStoreIndex.fromDocuments([document], {
|
||||
storageContext,
|
||||
logProgress: true,
|
||||
});
|
||||
|
||||
console.log({ index });
|
||||
})();
|
||||
@@ -6,21 +6,17 @@ import {
|
||||
} from "@llamaindex/readers/cosmosdb";
|
||||
import * as dotenv from "dotenv";
|
||||
import {
|
||||
AzureCosmosDBNoSQLConfig,
|
||||
AzureCosmosDBNoSqlVectorStore,
|
||||
OpenAI,
|
||||
OpenAIEmbedding,
|
||||
Settings,
|
||||
storageContextFromDefaults,
|
||||
VectorStoreIndex,
|
||||
} from "llamaindex";
|
||||
import {
|
||||
createStoresFromConnectionString,
|
||||
createStoresFromManagedIdentity,
|
||||
} from "./utils";
|
||||
// Load environment variables from local .env file
|
||||
dotenv.config();
|
||||
|
||||
const cosmosEndpoint = process.env.AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT!;
|
||||
const cosmosEndpoint = process.env.AZURE_COSMOSDB_NOSQL_ENDPOINT!;
|
||||
const cosmosConnectionString =
|
||||
process.env.AZURE_COSMOSDB_NOSQL_CONNECTION_STRING!;
|
||||
const databaseName =
|
||||
@@ -30,7 +26,7 @@ const collectionName =
|
||||
const vectorCollectionName =
|
||||
process.env.AZURE_COSMOSDB_VECTOR_CONTAINER_NAME || "vectorContainer";
|
||||
|
||||
// This example uses Azure OpenAI llm and embedding models
|
||||
// This exampple uses Azure OpenAI llm and embedding models
|
||||
const llmInit = {
|
||||
azure: {
|
||||
apiVersion: process.env.AZURE_OPENAI_LLM_API_VERSION,
|
||||
@@ -50,48 +46,24 @@ const embedModelInit = {
|
||||
Settings.llm = new OpenAI(llmInit);
|
||||
Settings.embedModel = new OpenAIEmbedding(embedModelInit);
|
||||
|
||||
// Initialize the CosmosDB client
|
||||
async function initializeCosmosClient() {
|
||||
if (cosmosConnectionString) {
|
||||
return new CosmosClient(cosmosConnectionString);
|
||||
} else {
|
||||
const credential = new DefaultAzureCredential();
|
||||
return new CosmosClient({
|
||||
endpoint: cosmosEndpoint,
|
||||
aadCredentials: credential,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Initialize CosmosDB to be used as a vectorStore, docStore, and indexStore
|
||||
async function initializeStores() {
|
||||
// Create a configuration object for the Azure CosmosDB NoSQL Vector Store
|
||||
const dbConfig: AzureCosmosDBNoSQLConfig = {
|
||||
databaseName,
|
||||
containerName: vectorCollectionName,
|
||||
flatMetadata: false,
|
||||
};
|
||||
|
||||
if (cosmosConnectionString) {
|
||||
return createStoresFromConnectionString(cosmosConnectionString, dbConfig);
|
||||
} else {
|
||||
// Use managed identity to authenticate with Azure CosmosDB
|
||||
const credential = new DefaultAzureCredential();
|
||||
return createStoresFromManagedIdentity(
|
||||
cosmosEndpoint,
|
||||
credential,
|
||||
dbConfig,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
async function loadVectorData() {
|
||||
if (!cosmosConnectionString && !cosmosEndpoint) {
|
||||
throw new Error(
|
||||
"Azure CosmosDB connection string or endpoint must be set.",
|
||||
);
|
||||
}
|
||||
const cosmosClient = await initializeCosmosClient();
|
||||
|
||||
let cosmosClient: CosmosClient;
|
||||
// initialize the cosmos client
|
||||
if (cosmosConnectionString) {
|
||||
cosmosClient = new CosmosClient(cosmosConnectionString);
|
||||
} else {
|
||||
cosmosClient = new CosmosClient({
|
||||
endpoint: cosmosEndpoint,
|
||||
aadCredentials: new DefaultAzureCredential(),
|
||||
});
|
||||
}
|
||||
|
||||
const reader = new SimpleCosmosDBReader(cosmosClient);
|
||||
// create a configuration object for the reader
|
||||
const simpleCosmosReaderConfig: SimpleCosmosDBReaderLoaderConfig = {
|
||||
@@ -104,15 +76,16 @@ async function loadVectorData() {
|
||||
|
||||
// load objects from cosmos and convert them into LlamaIndex Document objects
|
||||
const documents = await reader.loadData(simpleCosmosReaderConfig);
|
||||
|
||||
// use Azure CosmosDB as a vectorStore, docStore, and indexStore
|
||||
const { vectorStore, docStore, indexStore } = await initializeStores();
|
||||
// Store the embeddings in the CosmosDB container
|
||||
const storageContext = await storageContextFromDefaults({
|
||||
vectorStore,
|
||||
docStore,
|
||||
indexStore,
|
||||
// create Azure CosmosDB as a vector store
|
||||
const vectorStore = new AzureCosmosDBNoSqlVectorStore({
|
||||
client: cosmosClient,
|
||||
databaseName,
|
||||
containerName: vectorCollectionName,
|
||||
flatMetadata: false,
|
||||
});
|
||||
|
||||
// Store the embeddings in the CosmosDB container
|
||||
const storageContext = await storageContextFromDefaults({ vectorStore });
|
||||
await VectorStoreIndex.fromDocuments(documents, { storageContext });
|
||||
console.log(
|
||||
`Successfully created embeddings in the CosmosDB container ${vectorCollectionName}.`,
|
||||
|
||||
@@ -3,21 +3,17 @@ import { DefaultAzureCredential } from "@azure/identity";
|
||||
import * as dotenv from "dotenv";
|
||||
import {
|
||||
AzureCosmosDBNoSQLConfig,
|
||||
AzureCosmosDBNoSqlVectorStore,
|
||||
OpenAI,
|
||||
OpenAIEmbedding,
|
||||
Settings,
|
||||
storageContextFromDefaults,
|
||||
VectorStoreIndex,
|
||||
} from "llamaindex";
|
||||
import {
|
||||
createStoresFromConnectionString,
|
||||
createStoresFromManagedIdentity,
|
||||
} from "./utils";
|
||||
|
||||
// Load environment variables from local .env file
|
||||
dotenv.config();
|
||||
|
||||
const cosmosEndpoint = process.env.AZURE_COSMOSDB_NOSQL_ACCOUNT_ENDPOINT!;
|
||||
const cosmosEndpoint = process.env.AZURE_COSMOSDB_NOSQL_ENDPOINT!;
|
||||
const cosmosConnectionString =
|
||||
process.env.AZURE_COSMOSDB_NOSQL_CONNECTION_STRING!;
|
||||
const databaseName =
|
||||
@@ -44,27 +40,6 @@ const embedModelInit = {
|
||||
Settings.llm = new OpenAI(llmInit);
|
||||
Settings.embedModel = new OpenAIEmbedding(embedModelInit);
|
||||
|
||||
async function initializeStores() {
|
||||
// Create a configuration object for the Azure CosmosDB NoSQL Vector Store
|
||||
const dbConfig: AzureCosmosDBNoSQLConfig = {
|
||||
databaseName,
|
||||
containerName,
|
||||
flatMetadata: false,
|
||||
};
|
||||
|
||||
if (cosmosConnectionString) {
|
||||
return createStoresFromConnectionString(cosmosConnectionString, dbConfig);
|
||||
} else {
|
||||
// Use managed identity to authenticate with Azure CosmosDB
|
||||
const credential = new DefaultAzureCredential();
|
||||
return createStoresFromManagedIdentity(
|
||||
cosmosEndpoint,
|
||||
credential,
|
||||
dbConfig,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
async function query() {
|
||||
if (!cosmosConnectionString && !cosmosEndpoint) {
|
||||
throw new Error(
|
||||
@@ -90,19 +65,10 @@ async function query() {
|
||||
containerName,
|
||||
flatMetadata: false,
|
||||
};
|
||||
|
||||
// use Azure CosmosDB as a vectorStore, docStore, and indexStore
|
||||
const { vectorStore, docStore, indexStore } = await initializeStores();
|
||||
|
||||
// Store the embeddings in the CosmosDB container
|
||||
const storageContext = await storageContextFromDefaults({
|
||||
vectorStore,
|
||||
docStore,
|
||||
indexStore,
|
||||
});
|
||||
const store = new AzureCosmosDBNoSqlVectorStore(dbConfig);
|
||||
|
||||
// create an index from the Azure CosmosDB NoSQL Vector Store
|
||||
const index = await VectorStoreIndex.init({ storageContext });
|
||||
const index = await VectorStoreIndex.fromVectorStore(store);
|
||||
|
||||
// create a retriever and a query engine from the index
|
||||
const retriever = index.asRetriever({ similarityTopK: 20 });
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
import { TokenCredential } from "@azure/identity";
|
||||
import {
|
||||
AzureCosmosDBNoSQLConfig,
|
||||
AzureCosmosDBNoSqlVectorStore,
|
||||
AzureCosmosNoSqlDocumentStore,
|
||||
AzureCosmosNoSqlIndexStore,
|
||||
} from "llamaindex";
|
||||
|
||||
/**
|
||||
* Util function to create AzureCosmosDB vectorStore, docStore, indexStore from connection string.
|
||||
*/
|
||||
export const createStoresFromConnectionString = (
|
||||
connectionString: string,
|
||||
dbConfig: AzureCosmosDBNoSQLConfig,
|
||||
) => {
|
||||
const vectorStore = AzureCosmosDBNoSqlVectorStore.fromConnectionString({
|
||||
connectionString,
|
||||
...dbConfig,
|
||||
});
|
||||
const docStore = AzureCosmosNoSqlDocumentStore.fromConnectionString({
|
||||
connectionString,
|
||||
});
|
||||
const indexStore = AzureCosmosNoSqlIndexStore.fromConnectionString({
|
||||
connectionString,
|
||||
});
|
||||
return { vectorStore, docStore, indexStore };
|
||||
};
|
||||
|
||||
/**
|
||||
* Util function to create AzureCosmosDB vectorStore, docStore, indexStore from connection string.
|
||||
*/
|
||||
export const createStoresFromManagedIdentity = (
|
||||
endpoint: string,
|
||||
credential: TokenCredential,
|
||||
dbConfig: AzureCosmosDBNoSQLConfig,
|
||||
) => {
|
||||
const vectorStore = AzureCosmosDBNoSqlVectorStore.fromUriAndManagedIdentity({
|
||||
endpoint,
|
||||
credential,
|
||||
...dbConfig,
|
||||
});
|
||||
const docStore = AzureCosmosNoSqlDocumentStore.fromAadToken({
|
||||
endpoint,
|
||||
credential,
|
||||
});
|
||||
const indexStore = AzureCosmosNoSqlIndexStore.fromAadToken({
|
||||
endpoint,
|
||||
credential,
|
||||
});
|
||||
return { vectorStore, docStore, indexStore };
|
||||
};
|
||||
@@ -1,15 +1,15 @@
|
||||
{
|
||||
"name": "@llamaindex/examples",
|
||||
"private": true,
|
||||
"version": "0.0.14",
|
||||
"version": "0.0.12",
|
||||
"dependencies": {
|
||||
"@aws-crypto/sha256-js": "^5.2.0",
|
||||
"@azure/cosmos": "^4.1.1",
|
||||
"@azure/identity": "^4.4.1",
|
||||
"@datastax/astra-db-ts": "^1.4.1",
|
||||
"@llamaindex/core": "^0.4.7",
|
||||
"@llamaindex/readers": "^1.0.8",
|
||||
"@llamaindex/workflow": "^0.0.4",
|
||||
"@llamaindex/core": "^0.4.0",
|
||||
"@llamaindex/readers": "^1.0.0",
|
||||
"@llamaindex/workflow": "^0.0.2",
|
||||
"@notionhq/client": "^2.2.15",
|
||||
"@pinecone-database/pinecone": "^3.0.2",
|
||||
"@vercel/postgres": "^0.10.0",
|
||||
@@ -18,15 +18,15 @@
|
||||
"commander": "^12.1.0",
|
||||
"dotenv": "^16.4.5",
|
||||
"js-tiktoken": "^1.0.14",
|
||||
"llamaindex": "^0.8.10",
|
||||
"llamaindex": "^0.8.0",
|
||||
"mongodb": "^6.7.0",
|
||||
"pathe": "^1.1.2",
|
||||
"postgres": "^3.4.4"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"tsx": "^4.19.0",
|
||||
"typescript": "^5.6.3"
|
||||
"typescript": "^5.6.2"
|
||||
},
|
||||
"scripts": {
|
||||
"lint": "eslint ."
|
||||
|
||||
@@ -22,8 +22,8 @@
|
||||
"llamaindex": "*"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"tsx": "^4.19.0",
|
||||
"typescript": "^5.6.3"
|
||||
"typescript": "^5.6.2"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -14,6 +14,7 @@ Settings.llm = new Ollama({
|
||||
|
||||
Settings.embedModel = new HuggingFaceEmbedding({
|
||||
modelType: "BAAI/bge-small-en-v1.5",
|
||||
quantized: false,
|
||||
});
|
||||
|
||||
async function main() {
|
||||
|
||||
@@ -1,16 +0,0 @@
|
||||
import { VLLM } from "llamaindex";
|
||||
|
||||
const llm = new VLLM({
|
||||
model: "NousResearch/Meta-Llama-3-8B-Instruct",
|
||||
});
|
||||
|
||||
const response = await llm.chat({
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: "Hello?",
|
||||
},
|
||||
],
|
||||
});
|
||||
|
||||
console.log(response.message.content);
|
||||
@@ -1,19 +1,14 @@
|
||||
import {
|
||||
HandlerContext,
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
WorkflowEvent,
|
||||
} from "@llamaindex/workflow";
|
||||
} from "@llamaindex/core/workflow";
|
||||
import { OpenAI } from "llamaindex";
|
||||
|
||||
const MAX_REVIEWS = 3;
|
||||
|
||||
type Context = {
|
||||
specification: string;
|
||||
numberReviews: number;
|
||||
};
|
||||
|
||||
// Using the o1-preview model (see https://platform.openai.com/docs/guides/reasoning?reasoning-prompt-examples=coding-planning)
|
||||
const llm = new OpenAI({ model: "o1-preview", temperature: 1 });
|
||||
|
||||
@@ -25,9 +20,7 @@ stores the question/answer pair in the database.`;
|
||||
|
||||
// Create custom event types
|
||||
export class MessageEvent extends WorkflowEvent<{ msg: string }> {}
|
||||
|
||||
export class CodeEvent extends WorkflowEvent<{ code: string }> {}
|
||||
|
||||
export class ReviewEvent extends WorkflowEvent<{
|
||||
review: string;
|
||||
code: string;
|
||||
@@ -41,13 +34,12 @@ const truncate = (str: string) => {
|
||||
};
|
||||
|
||||
// the architect is responsible for writing the structure and the initial code based on the specification
|
||||
const architect = async (
|
||||
context: HandlerContext<Context>,
|
||||
_: StartEvent<string>,
|
||||
) => {
|
||||
const spec = context.data.specification;
|
||||
const architect = async (context: Context, ev: StartEvent) => {
|
||||
// get the specification from the start event and save it to context
|
||||
context.set("specification", ev.data.input);
|
||||
const spec = context.get("specification");
|
||||
// write a message to send an update to the user
|
||||
context.sendEvent(
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({
|
||||
msg: `Writing app using this specification: ${truncate(spec)}`,
|
||||
}),
|
||||
@@ -58,13 +50,13 @@ const architect = async (
|
||||
};
|
||||
|
||||
// the coder is responsible for updating the code based on the review
|
||||
const coder = async (context: HandlerContext<Context>, ev: ReviewEvent) => {
|
||||
const coder = async (context: Context, ev: ReviewEvent) => {
|
||||
// get the specification from the context
|
||||
const spec = context.data.specification;
|
||||
const spec = context.get("specification");
|
||||
// get the latest review and code
|
||||
const { review, code } = ev.data;
|
||||
// write a message to send an update to the user
|
||||
context.sendEvent(
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({
|
||||
msg: `Update code based on review: ${truncate(review)}`,
|
||||
}),
|
||||
@@ -75,35 +67,32 @@ const coder = async (context: HandlerContext<Context>, ev: ReviewEvent) => {
|
||||
};
|
||||
|
||||
// the reviewer is responsible for reviewing the code and providing feedback
|
||||
const reviewer = async (context: HandlerContext<Context>, ev: CodeEvent) => {
|
||||
const reviewer = async (context: Context, ev: CodeEvent) => {
|
||||
// get the specification from the context
|
||||
const spec = context.data.specification;
|
||||
const spec = context.get("specification");
|
||||
// get latest code from the event
|
||||
const { code } = ev.data;
|
||||
// update and check the number of reviews
|
||||
context.data.numberReviews++;
|
||||
if (context.data.numberReviews > MAX_REVIEWS) {
|
||||
const numberReviews = context.get("numberReviews", 0) + 1;
|
||||
context.set("numberReviews", numberReviews);
|
||||
if (numberReviews > MAX_REVIEWS) {
|
||||
// the we've done this too many times - return the code
|
||||
context.sendEvent(
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({
|
||||
msg: `Already reviewed ${
|
||||
context.data.numberReviews - 1
|
||||
} times, stopping!`,
|
||||
msg: `Already reviewed ${numberReviews - 1} times, stopping!`,
|
||||
}),
|
||||
);
|
||||
return new StopEvent({ result: code });
|
||||
}
|
||||
// write a message to send an update to the user
|
||||
context.sendEvent(
|
||||
new MessageEvent({
|
||||
msg: `Review #${context.data.numberReviews}: ${truncate(code)}`,
|
||||
}),
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({ msg: `Review #${numberReviews}: ${truncate(code)}` }),
|
||||
);
|
||||
const prompt = `Review this code: <code>${code}</code>. Check if the code quality and whether it correctly implements this specification: <spec>${spec}</spec>. If you're satisfied, just return 'Looks great', nothing else. If not, return a review with a list of changes you'd like to see.`;
|
||||
const review = (await llm.complete({ prompt })).text;
|
||||
if (review.includes("Looks great")) {
|
||||
// the reviewer is satisfied with the code, let's return the review
|
||||
context.sendEvent(
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({
|
||||
msg: `Reviewer says: ${review}`,
|
||||
}),
|
||||
@@ -114,44 +103,20 @@ const reviewer = async (context: HandlerContext<Context>, ev: CodeEvent) => {
|
||||
return new ReviewEvent({ review, code });
|
||||
};
|
||||
|
||||
const codeAgent = new Workflow<Context, string, string>();
|
||||
codeAgent.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [CodeEvent],
|
||||
},
|
||||
architect,
|
||||
);
|
||||
codeAgent.addStep(
|
||||
{
|
||||
inputs: [ReviewEvent],
|
||||
outputs: [CodeEvent],
|
||||
},
|
||||
coder,
|
||||
);
|
||||
codeAgent.addStep(
|
||||
{
|
||||
inputs: [CodeEvent],
|
||||
outputs: [ReviewEvent, StopEvent],
|
||||
},
|
||||
reviewer,
|
||||
);
|
||||
const codeAgent = new Workflow({ validate: true });
|
||||
codeAgent.addStep(StartEvent, architect, { outputs: CodeEvent });
|
||||
codeAgent.addStep(ReviewEvent, coder, { outputs: CodeEvent });
|
||||
codeAgent.addStep(CodeEvent, reviewer, { outputs: ReviewEvent });
|
||||
|
||||
// Usage
|
||||
async function main() {
|
||||
const run = codeAgent.run(specification).with({
|
||||
specification,
|
||||
numberReviews: 0,
|
||||
});
|
||||
for await (const event of run) {
|
||||
if (event instanceof MessageEvent) {
|
||||
const msg = (event as MessageEvent).data.msg;
|
||||
console.log(`${msg}\n`);
|
||||
} else if (event instanceof StopEvent) {
|
||||
const result = (event as StopEvent<string>).data;
|
||||
console.log("Final code:\n", result);
|
||||
}
|
||||
const run = codeAgent.run(specification);
|
||||
for await (const event of codeAgent.streamEvents()) {
|
||||
const msg = (event as MessageEvent).data.msg;
|
||||
console.log(`${msg}\n`);
|
||||
}
|
||||
const result = await run;
|
||||
console.log("Final code:\n", result.data.result);
|
||||
}
|
||||
|
||||
main().catch(console.error);
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
import {
|
||||
HandlerContext,
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
WorkflowEvent,
|
||||
} from "@llamaindex/workflow";
|
||||
} from "@llamaindex/core/workflow";
|
||||
import { OpenAI } from "llamaindex";
|
||||
|
||||
// Create LLM instance
|
||||
@@ -12,77 +12,59 @@ const llm = new OpenAI();
|
||||
|
||||
// Create custom event types
|
||||
export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
|
||||
|
||||
export class CritiqueEvent extends WorkflowEvent<{ critique: string }> {}
|
||||
|
||||
export class AnalysisEvent extends WorkflowEvent<{ analysis: string }> {}
|
||||
|
||||
const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
|
||||
const prompt = `Write your best joke about ${ev.data}.`;
|
||||
const generateJoke = async (_context: Context, ev: StartEvent) => {
|
||||
const prompt = `Write your best joke about ${ev.data.input}.`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new JokeEvent({ joke: response.text });
|
||||
};
|
||||
|
||||
const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
|
||||
const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
|
||||
const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new CritiqueEvent({ critique: response.text });
|
||||
};
|
||||
|
||||
const analyzeJoke = async (_: unknown, ev: JokeEvent) => {
|
||||
const analyzeJoke = async (_context: Context, ev: JokeEvent) => {
|
||||
const prompt = `Give a thorough analysis of the following joke: ${ev.data.joke}`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new AnalysisEvent({ analysis: response.text });
|
||||
};
|
||||
|
||||
const reportJoke = async (
|
||||
context: HandlerContext,
|
||||
ev1: AnalysisEvent,
|
||||
ev2: CritiqueEvent,
|
||||
context: Context,
|
||||
ev: AnalysisEvent | CritiqueEvent,
|
||||
) => {
|
||||
const subPrompts = [ev1.data.analysis, ev2.data.critique];
|
||||
const events = context.collectEvents(ev, [AnalysisEvent, CritiqueEvent]);
|
||||
if (!events) {
|
||||
return;
|
||||
}
|
||||
const subPrompts = events.map((event) => {
|
||||
if (event instanceof AnalysisEvent) {
|
||||
return `Analysis: ${event.data.analysis}`;
|
||||
} else if (event instanceof CritiqueEvent) {
|
||||
return `Critique: ${event.data.critique}`;
|
||||
}
|
||||
return "";
|
||||
});
|
||||
|
||||
const prompt = `Based on the following information about a joke:\n${subPrompts.join(
|
||||
"\n",
|
||||
)}\nProvide a comprehensive report on the joke's quality and impact.`;
|
||||
const prompt = `Based on the following information about a joke:\n${subPrompts.join("\n")}\nProvide a comprehensive report on the joke's quality and impact.`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new StopEvent(response.text);
|
||||
return new StopEvent({ result: response.text });
|
||||
};
|
||||
|
||||
const jokeFlow = new Workflow<unknown, string, string>();
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [JokeEvent],
|
||||
},
|
||||
generateJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [CritiqueEvent],
|
||||
},
|
||||
critiqueJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [AnalysisEvent],
|
||||
},
|
||||
analyzeJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [AnalysisEvent, CritiqueEvent],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
reportJoke,
|
||||
);
|
||||
const jokeFlow = new Workflow();
|
||||
jokeFlow.addStep(StartEvent, generateJoke);
|
||||
jokeFlow.addStep(JokeEvent, critiqueJoke);
|
||||
jokeFlow.addStep(JokeEvent, analyzeJoke);
|
||||
jokeFlow.addStep([AnalysisEvent, CritiqueEvent], reportJoke);
|
||||
|
||||
// Usage
|
||||
async function main() {
|
||||
const result = await jokeFlow.run("pirates");
|
||||
console.log(result.data);
|
||||
console.log(result.data.result);
|
||||
}
|
||||
|
||||
main().catch(console.error);
|
||||
+10
-21
@@ -1,9 +1,10 @@
|
||||
import {
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
WorkflowEvent,
|
||||
} from "@llamaindex/workflow";
|
||||
} from "@llamaindex/core/workflow";
|
||||
import { OpenAI } from "llamaindex";
|
||||
|
||||
// Create LLM instance
|
||||
@@ -12,38 +13,26 @@ const llm = new OpenAI();
|
||||
// Create a custom event type
|
||||
export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
|
||||
|
||||
const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
|
||||
const prompt = `Write your best joke about ${ev.data}.`;
|
||||
const generateJoke = async (_context: Context, ev: StartEvent) => {
|
||||
const prompt = `Write your best joke about ${ev.data.input}.`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new JokeEvent({ joke: response.text });
|
||||
};
|
||||
|
||||
const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
|
||||
const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
|
||||
const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new StopEvent(response.text);
|
||||
return new StopEvent({ result: response.text });
|
||||
};
|
||||
|
||||
const jokeFlow = new Workflow<unknown, string, string>();
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [JokeEvent],
|
||||
},
|
||||
generateJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
critiqueJoke,
|
||||
);
|
||||
const jokeFlow = new Workflow({ verbose: true });
|
||||
jokeFlow.addStep(StartEvent, generateJoke);
|
||||
jokeFlow.addStep(JokeEvent, critiqueJoke);
|
||||
|
||||
// Usage
|
||||
async function main() {
|
||||
const result = await jokeFlow.run("pirates");
|
||||
console.log(result.data);
|
||||
console.log(result.data.result);
|
||||
}
|
||||
|
||||
main().catch(console.error);
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
import {
|
||||
HandlerContext,
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
WorkflowEvent,
|
||||
} from "@llamaindex/workflow";
|
||||
} from "@llamaindex/core/workflow";
|
||||
import { OpenAI } from "llamaindex";
|
||||
|
||||
// Create LLM instance
|
||||
@@ -12,55 +12,38 @@ const llm = new OpenAI();
|
||||
|
||||
// Create custom event types
|
||||
export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
|
||||
|
||||
export class MessageEvent extends WorkflowEvent<{ msg: string }> {}
|
||||
|
||||
const generateJoke = async (context: HandlerContext, ev: StartEvent) => {
|
||||
context.sendEvent(
|
||||
new MessageEvent({ msg: `Generating a joke about: ${ev.data}` }),
|
||||
const generateJoke = async (context: Context, ev: StartEvent) => {
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({ msg: `Generating a joke about: ${ev.data.input}` }),
|
||||
);
|
||||
const prompt = `Write your best joke about ${ev.data}.`;
|
||||
const prompt = `Write your best joke about ${ev.data.input}.`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new JokeEvent({ joke: response.text });
|
||||
};
|
||||
|
||||
const critiqueJoke = async (context: HandlerContext, ev: JokeEvent) => {
|
||||
context.sendEvent(
|
||||
const critiqueJoke = async (context: Context, ev: JokeEvent) => {
|
||||
context.writeEventToStream(
|
||||
new MessageEvent({ msg: `Write a critique of this joke: ${ev.data.joke}` }),
|
||||
);
|
||||
const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new StopEvent(response.text);
|
||||
return new StopEvent({ result: response.text });
|
||||
};
|
||||
|
||||
const jokeFlow = new Workflow();
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [JokeEvent],
|
||||
},
|
||||
generateJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
critiqueJoke,
|
||||
);
|
||||
jokeFlow.addStep(StartEvent, generateJoke);
|
||||
jokeFlow.addStep(JokeEvent, critiqueJoke);
|
||||
|
||||
// Usage
|
||||
async function main() {
|
||||
const run = jokeFlow.run("pirates");
|
||||
for await (const event of run) {
|
||||
if (event instanceof MessageEvent) {
|
||||
console.log("Message:");
|
||||
console.log((event as MessageEvent).data.msg);
|
||||
} else if (event instanceof StopEvent) {
|
||||
console.log("Result:");
|
||||
console.log((event as StopEvent<string>).data);
|
||||
}
|
||||
for await (const event of jokeFlow.streamEvents()) {
|
||||
console.log((event as MessageEvent).data.msg);
|
||||
}
|
||||
const result = await run;
|
||||
console.log(result.data.result);
|
||||
}
|
||||
|
||||
main().catch(console.error);
|
||||
|
||||
@@ -1,21 +1,19 @@
|
||||
import { StartEvent, StopEvent, Workflow } from "@llamaindex/workflow";
|
||||
import {
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
} from "@llamaindex/core/workflow";
|
||||
|
||||
const longRunning = async (_: unknown, ev: StartEvent<string>) => {
|
||||
const longRunning = async (_context: Context, ev: StartEvent) => {
|
||||
await new Promise((resolve) => setTimeout(resolve, 2000)); // Wait for 2 seconds
|
||||
return new StopEvent("We waited 2 seconds");
|
||||
return new StopEvent({ result: "We waited 2 seconds" });
|
||||
};
|
||||
|
||||
async function timeout() {
|
||||
const workflow = new Workflow<unknown, string, string>({
|
||||
timeout: 1,
|
||||
});
|
||||
workflow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
longRunning,
|
||||
);
|
||||
const workflow = new Workflow({ verbose: true, timeout: 1 });
|
||||
workflow.addStep(StartEvent, longRunning);
|
||||
// This will timeout
|
||||
try {
|
||||
await workflow.run("Let's start");
|
||||
} catch (error) {
|
||||
@@ -25,23 +23,14 @@ async function timeout() {
|
||||
|
||||
async function notimeout() {
|
||||
// Increase timeout to 3 seconds - no timeout
|
||||
const workflow = new Workflow<unknown, string, string>({
|
||||
timeout: 3,
|
||||
});
|
||||
workflow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
longRunning,
|
||||
);
|
||||
const workflow = new Workflow({ verbose: true, timeout: 3 });
|
||||
workflow.addStep(StartEvent, longRunning);
|
||||
const result = await workflow.run("Let's start");
|
||||
console.log(result.data);
|
||||
console.log(result.data.result);
|
||||
}
|
||||
|
||||
async function main() {
|
||||
await timeout();
|
||||
console.log("---");
|
||||
await notimeout();
|
||||
}
|
||||
|
||||
|
||||
@@ -1,9 +1,10 @@
|
||||
import {
|
||||
Context,
|
||||
StartEvent,
|
||||
StopEvent,
|
||||
Workflow,
|
||||
WorkflowEvent,
|
||||
} from "@llamaindex/workflow";
|
||||
} from "@llamaindex/core/workflow";
|
||||
import { OpenAI } from "llamaindex";
|
||||
|
||||
// Create LLM instance
|
||||
@@ -12,66 +13,40 @@ const llm = new OpenAI();
|
||||
// Create a custom event type
|
||||
export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
|
||||
|
||||
const generateJoke = async (_: unknown, ev: StartEvent<string>) => {
|
||||
const prompt = `Write your best joke about ${ev.data}.`;
|
||||
const generateJoke = async (_context: Context, ev: StartEvent) => {
|
||||
const prompt = `Write your best joke about ${ev.data.input}.`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new JokeEvent({ joke: response.text });
|
||||
};
|
||||
|
||||
const critiqueJoke = async (_: unknown, ev: JokeEvent) => {
|
||||
const critiqueJoke = async (_context: Context, ev: JokeEvent) => {
|
||||
const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
|
||||
const response = await llm.complete({ prompt });
|
||||
return new StopEvent(response.text);
|
||||
return new StopEvent({ result: response.text });
|
||||
};
|
||||
|
||||
async function validateFails() {
|
||||
try {
|
||||
const jokeFlow = new Workflow();
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
// @ts-expect-error outputs should be JokeEvent
|
||||
generateJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [StopEvent],
|
||||
},
|
||||
critiqueJoke,
|
||||
);
|
||||
await jokeFlow.run("pirates").strict();
|
||||
const jokeFlow = new Workflow({ verbose: true, validate: true });
|
||||
jokeFlow.addStep(StartEvent, generateJoke, { outputs: StopEvent });
|
||||
jokeFlow.addStep(JokeEvent, critiqueJoke, { outputs: StopEvent });
|
||||
await jokeFlow.run("pirates");
|
||||
} catch (e) {
|
||||
console.error("Validation failed:", e);
|
||||
}
|
||||
}
|
||||
|
||||
async function validate() {
|
||||
const jokeFlow = new Workflow();
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [StartEvent<string>],
|
||||
outputs: [JokeEvent],
|
||||
},
|
||||
generateJoke,
|
||||
);
|
||||
jokeFlow.addStep(
|
||||
{
|
||||
inputs: [JokeEvent],
|
||||
outputs: [StopEvent<string>],
|
||||
},
|
||||
critiqueJoke,
|
||||
);
|
||||
const result = await jokeFlow.run("pirates").strict();
|
||||
console.log(result.data);
|
||||
const jokeFlow = new Workflow({ verbose: true, validate: true });
|
||||
jokeFlow.addStep(StartEvent, generateJoke, { outputs: JokeEvent });
|
||||
jokeFlow.addStep(JokeEvent, critiqueJoke, { outputs: StopEvent });
|
||||
const result = await jokeFlow.run("pirates");
|
||||
console.log(result.data.result);
|
||||
}
|
||||
|
||||
// Usage
|
||||
async function main() {
|
||||
await validateFails();
|
||||
console.log("---");
|
||||
await validate();
|
||||
}
|
||||
|
||||
|
||||
+11
-5
@@ -19,22 +19,28 @@
|
||||
},
|
||||
"devDependencies": {
|
||||
"@changesets/cli": "^2.27.5",
|
||||
"eslint": "9.14.0",
|
||||
"eslint": "9.13.0",
|
||||
"eslint-config-next": "^15.0.2",
|
||||
"eslint-config-prettier": "^9.1.0",
|
||||
"eslint-config-turbo": "^2.2.3",
|
||||
"eslint-plugin-react": "7.37.2",
|
||||
"globals": "^15.12.0",
|
||||
"globals": "^15.11.0",
|
||||
"husky": "^9.1.6",
|
||||
"lint-staged": "^15.2.10",
|
||||
"madge": "^8.0.0",
|
||||
"prettier": "^3.3.3",
|
||||
"prettier-plugin-organize-imports": "^4.1.0",
|
||||
"turbo": "^2.2.3",
|
||||
"typescript": "^5.6.3",
|
||||
"typescript-eslint": "^8.13.0"
|
||||
"typescript": "^5.6.2",
|
||||
"typescript-eslint": "^8.12.2"
|
||||
},
|
||||
"packageManager": "pnpm@9.5.0",
|
||||
"pnpm": {
|
||||
"overrides": {
|
||||
"trim": "1.0.1",
|
||||
"protobufjs": "7.2.6"
|
||||
}
|
||||
},
|
||||
"packageManager": "pnpm@9.12.3",
|
||||
"lint-staged": {
|
||||
"(!apps/docs/i18n/**/docusaurus-plugin-content-docs/current/api/*).{js,jsx,ts,tsx,md}": "prettier --write"
|
||||
}
|
||||
|
||||
@@ -1,61 +1,5 @@
|
||||
# @llamaindex/autotool
|
||||
|
||||
## 5.0.12
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.12
|
||||
|
||||
## 5.0.11
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.11
|
||||
|
||||
## 5.0.10
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- llamaindex@0.8.10
|
||||
|
||||
## 5.0.9
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- Updated dependencies [4d4cd8a]
|
||||
- llamaindex@0.8.9
|
||||
|
||||
## 5.0.8
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- llamaindex@0.8.8
|
||||
|
||||
## 5.0.7
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.7
|
||||
|
||||
## 5.0.6
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- llamaindex@0.8.6
|
||||
|
||||
## 5.0.5
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- Updated dependencies [a6db5dd]
|
||||
- Updated dependencies [396b1e1]
|
||||
- llamaindex@0.8.5
|
||||
|
||||
## 5.0.4
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -1,69 +1,5 @@
|
||||
# @llamaindex/autotool-01-node-example
|
||||
|
||||
## 0.0.55
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.12
|
||||
- @llamaindex/autotool@5.0.12
|
||||
|
||||
## 0.0.54
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.11
|
||||
- @llamaindex/autotool@5.0.11
|
||||
|
||||
## 0.0.53
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- llamaindex@0.8.10
|
||||
- @llamaindex/autotool@5.0.10
|
||||
|
||||
## 0.0.52
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- Updated dependencies [4d4cd8a]
|
||||
- llamaindex@0.8.9
|
||||
- @llamaindex/autotool@5.0.9
|
||||
|
||||
## 0.0.51
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- llamaindex@0.8.8
|
||||
- @llamaindex/autotool@5.0.8
|
||||
|
||||
## 0.0.50
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.7
|
||||
- @llamaindex/autotool@5.0.7
|
||||
|
||||
## 0.0.49
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- llamaindex@0.8.6
|
||||
- @llamaindex/autotool@5.0.6
|
||||
|
||||
## 0.0.48
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- Updated dependencies [a6db5dd]
|
||||
- Updated dependencies [396b1e1]
|
||||
- llamaindex@0.8.5
|
||||
- @llamaindex/autotool@5.0.5
|
||||
|
||||
## 0.0.47
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -13,5 +13,5 @@
|
||||
"scripts": {
|
||||
"start": "node --import tsx --import @llamaindex/autotool/node ./src/index.ts"
|
||||
},
|
||||
"version": "0.0.55"
|
||||
"version": "0.0.47"
|
||||
}
|
||||
|
||||
@@ -1,69 +1,5 @@
|
||||
# @llamaindex/autotool-02-next-example
|
||||
|
||||
## 0.1.99
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.12
|
||||
- @llamaindex/autotool@5.0.12
|
||||
|
||||
## 0.1.98
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.11
|
||||
- @llamaindex/autotool@5.0.11
|
||||
|
||||
## 0.1.97
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f066e50]
|
||||
- llamaindex@0.8.10
|
||||
- @llamaindex/autotool@5.0.10
|
||||
|
||||
## 0.1.96
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- Updated dependencies [4d4cd8a]
|
||||
- llamaindex@0.8.9
|
||||
- @llamaindex/autotool@5.0.9
|
||||
|
||||
## 0.1.95
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- llamaindex@0.8.8
|
||||
- @llamaindex/autotool@5.0.8
|
||||
|
||||
## 0.1.94
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- llamaindex@0.8.7
|
||||
- @llamaindex/autotool@5.0.7
|
||||
|
||||
## 0.1.93
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- llamaindex@0.8.6
|
||||
- @llamaindex/autotool@5.0.6
|
||||
|
||||
## 0.1.92
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- Updated dependencies [a6db5dd]
|
||||
- Updated dependencies [396b1e1]
|
||||
- llamaindex@0.8.5
|
||||
- @llamaindex/autotool@5.0.5
|
||||
|
||||
## 0.1.91
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@llamaindex/autotool-02-next-example",
|
||||
"private": true,
|
||||
"version": "0.1.99",
|
||||
"version": "0.1.91",
|
||||
"scripts": {
|
||||
"dev": "next dev",
|
||||
"build": "next build",
|
||||
@@ -15,7 +15,7 @@
|
||||
"dotenv": "^16.3.1",
|
||||
"llamaindex": "workspace:*",
|
||||
"lucide-react": "^0.436.0",
|
||||
"next": "15.0.2",
|
||||
"next": "14.3.0-canary.51",
|
||||
"react": "^18.3.1",
|
||||
"react-dom": "^18.3.1",
|
||||
"react-markdown": "^9.0.1",
|
||||
@@ -24,7 +24,7 @@
|
||||
"tailwind-merge": "^2.5.2"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"@types/react": "^18.3.12",
|
||||
"@types/react-dom": "^18.3.1",
|
||||
"@types/react-syntax-highlighter": "^15.5.11",
|
||||
@@ -32,6 +32,6 @@
|
||||
"cross-env": "^7.0.3",
|
||||
"postcss": "^8.4.41",
|
||||
"tailwindcss": "^3.4.10",
|
||||
"typescript": "^5.6.3"
|
||||
"typescript": "^5.6.2"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@llamaindex/autotool",
|
||||
"type": "module",
|
||||
"version": "5.0.12",
|
||||
"version": "5.0.4",
|
||||
"description": "auto transpile your JS function to LLM Agent compatible",
|
||||
"files": [
|
||||
"dist",
|
||||
@@ -47,7 +47,7 @@
|
||||
"dependencies": {
|
||||
"@swc/core": "^1.7.22",
|
||||
"jotai": "2.8.4",
|
||||
"typedoc": "^0.26.11",
|
||||
"typedoc": "^0.26.6",
|
||||
"unplugin": "^1.12.2"
|
||||
},
|
||||
"peerDependencies": {
|
||||
@@ -69,14 +69,14 @@
|
||||
"devDependencies": {
|
||||
"@swc/types": "^0.1.12",
|
||||
"@types/json-schema": "^7.0.15",
|
||||
"@types/node": "^22.9.0",
|
||||
"bunchee": "5.6.1",
|
||||
"@types/node": "^22.8.4",
|
||||
"bunchee": "5.5.1",
|
||||
"llamaindex": "workspace:*",
|
||||
"next": "15.0.2",
|
||||
"rollup": "^4.24.4",
|
||||
"next": "14.2.11",
|
||||
"rollup": "^4.21.2",
|
||||
"tsx": "^4.19.0",
|
||||
"typescript": "^5.6.3",
|
||||
"vitest": "^2.1.4",
|
||||
"typescript": "^5.6.2",
|
||||
"vitest": "^2.0.5",
|
||||
"webpack": "^5.94.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,66 +1,5 @@
|
||||
# @llamaindex/cloud
|
||||
|
||||
## 2.0.9
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [7ae6eaa]
|
||||
- @llamaindex/core@0.4.9
|
||||
|
||||
## 2.0.8
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f865c98]
|
||||
- @llamaindex/core@0.4.8
|
||||
|
||||
## 2.0.7
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [d89ebe0]
|
||||
- Updated dependencies [fd8c882]
|
||||
- @llamaindex/core@0.4.7
|
||||
|
||||
## 2.0.6
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- @llamaindex/env@0.1.20
|
||||
- @llamaindex/core@0.4.6
|
||||
|
||||
## 2.0.5
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- @llamaindex/core@0.4.5
|
||||
- @llamaindex/env@0.1.19
|
||||
|
||||
## 2.0.4
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [a8d3fa6]
|
||||
- @llamaindex/env@0.1.18
|
||||
- @llamaindex/core@0.4.4
|
||||
|
||||
## 2.0.3
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [95a5cc6]
|
||||
- @llamaindex/core@0.4.3
|
||||
|
||||
## 2.0.2
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- @llamaindex/env@0.1.17
|
||||
- @llamaindex/core@0.4.2
|
||||
|
||||
## 2.0.1
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -10,6 +10,9 @@ export default defineConfig({
|
||||
format: "prettier",
|
||||
lint: "eslint",
|
||||
},
|
||||
services: {
|
||||
asClass: true,
|
||||
},
|
||||
types: {
|
||||
enums: "javascript",
|
||||
},
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
{
|
||||
"name": "@llamaindex/cloud",
|
||||
"version": "2.0.9",
|
||||
"version": "2.0.1",
|
||||
"type": "module",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"generate": "./node_modules/.bin/openapi-ts",
|
||||
"generate": "pnpx @hey-api/openapi-ts@0.53.11",
|
||||
"build": "pnpm run generate && bunchee",
|
||||
"dev": "bunchee --watch"
|
||||
},
|
||||
@@ -51,10 +51,10 @@
|
||||
},
|
||||
"devDependencies": {
|
||||
"@hey-api/client-fetch": "^0.4.2",
|
||||
"@hey-api/openapi-ts": "^0.54.3",
|
||||
"@hey-api/openapi-ts": "^0.53.11",
|
||||
"@llamaindex/core": "workspace:*",
|
||||
"@llamaindex/env": "workspace:*",
|
||||
"bunchee": "5.6.1"
|
||||
"bunchee": "5.5.1"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@llamaindex/core": "workspace:*",
|
||||
|
||||
@@ -4,12 +4,7 @@ import { fs, getEnv, path } from "@llamaindex/env";
|
||||
import {
|
||||
type Body_upload_file_api_v1_parsing_upload_post,
|
||||
type ParserLanguages,
|
||||
getJobApiV1ParsingJobJobIdGet,
|
||||
getJobImageResultApiV1ParsingJobJobIdResultImageNameGet,
|
||||
getJobJsonResultApiV1ParsingJobJobIdResultJsonGet,
|
||||
getJobResultApiV1ParsingJobJobIdResultMarkdownGet,
|
||||
getJobTextResultApiV1ParsingJobJobIdResultTextGet,
|
||||
uploadFileApiV1ParsingUploadPost,
|
||||
ParsingService,
|
||||
} from "./api";
|
||||
import { sleep } from "./utils";
|
||||
|
||||
@@ -206,7 +201,7 @@ export class LlamaParseReader extends FileReader {
|
||||
| undefined;
|
||||
} as unknown as Body_upload_file_api_v1_parsing_upload_post;
|
||||
|
||||
const response = await uploadFileApiV1ParsingUploadPost({
|
||||
const response = await ParsingService.uploadFileApiV1ParsingUploadPost({
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
signal: AbortSignal.timeout(this.maxTimeout * 1000),
|
||||
@@ -228,7 +223,7 @@ export class LlamaParseReader extends FileReader {
|
||||
await sleep(this.checkInterval * 1000);
|
||||
|
||||
// Check the job status. If unsuccessful response, checks if maximum timeout has been reached. If reached, throws an error
|
||||
const result = await getJobApiV1ParsingJobJobIdGet({
|
||||
const result = await ParsingService.getJobApiV1ParsingJobJobIdGet({
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
@@ -244,36 +239,45 @@ export class LlamaParseReader extends FileReader {
|
||||
let result;
|
||||
switch (resultType) {
|
||||
case "json": {
|
||||
result = await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
});
|
||||
result =
|
||||
await ParsingService.getJobJsonResultApiV1ParsingJobJobIdResultJsonGet(
|
||||
{
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
},
|
||||
);
|
||||
break;
|
||||
}
|
||||
case "markdown": {
|
||||
result = await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
});
|
||||
result =
|
||||
await ParsingService.getJobResultApiV1ParsingJobJobIdResultMarkdownGet(
|
||||
{
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
},
|
||||
);
|
||||
break;
|
||||
}
|
||||
case "text": {
|
||||
result = await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
});
|
||||
result =
|
||||
await ParsingService.getJobTextResultApiV1ParsingJobJobIdResultTextGet(
|
||||
{
|
||||
client: this.#client,
|
||||
throwOnError: true,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
},
|
||||
signal,
|
||||
},
|
||||
);
|
||||
break;
|
||||
}
|
||||
}
|
||||
@@ -455,13 +459,15 @@ export class LlamaParseReader extends FileReader {
|
||||
jobId: string,
|
||||
): Promise<void> {
|
||||
const response =
|
||||
await getJobImageResultApiV1ParsingJobJobIdResultImageNameGet({
|
||||
client: this.#client,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
name: imageName,
|
||||
await ParsingService.getJobImageResultApiV1ParsingJobJobIdResultImageNameGet(
|
||||
{
|
||||
client: this.#client,
|
||||
path: {
|
||||
job_id: jobId,
|
||||
name: imageName,
|
||||
},
|
||||
},
|
||||
});
|
||||
);
|
||||
if (response.error) {
|
||||
throw new Error(`Failed to download image: ${response.error.detail}`);
|
||||
}
|
||||
|
||||
@@ -8,6 +8,7 @@
|
||||
"moduleResolution": "Bundler",
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"lib": ["DOM", "ESNext"],
|
||||
"types": []
|
||||
},
|
||||
"include": ["./src"],
|
||||
|
||||
@@ -1,73 +1,5 @@
|
||||
# @llamaindex/community
|
||||
|
||||
## 0.0.67
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [7ae6eaa]
|
||||
- @llamaindex/core@0.4.9
|
||||
|
||||
## 0.0.66
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [f865c98]
|
||||
- @llamaindex/core@0.4.8
|
||||
|
||||
## 0.0.65
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [d89ebe0]
|
||||
- Updated dependencies [fd8c882]
|
||||
- @llamaindex/core@0.4.7
|
||||
|
||||
## 0.0.64
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- @llamaindex/env@0.1.20
|
||||
- @llamaindex/core@0.4.6
|
||||
|
||||
## 0.0.63
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [ad85bd0]
|
||||
- @llamaindex/core@0.4.5
|
||||
- @llamaindex/env@0.1.19
|
||||
|
||||
## 0.0.62
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [a8d3fa6]
|
||||
- @llamaindex/env@0.1.18
|
||||
- @llamaindex/core@0.4.4
|
||||
|
||||
## 0.0.61
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 487782c: Add missing inference endpoints for Haiku 3.5
|
||||
- Updated dependencies [95a5cc6]
|
||||
- @llamaindex/core@0.4.3
|
||||
|
||||
## 0.0.60
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- @llamaindex/env@0.1.17
|
||||
- @llamaindex/core@0.4.2
|
||||
|
||||
## 0.0.59
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 47a7c3e: feat: added support for Haiku 3.5 via Bedrock
|
||||
|
||||
## 0.0.58
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -4,7 +4,7 @@
|
||||
|
||||
## Current Features:
|
||||
|
||||
- Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock) including the latest Sonnet 3.5 v2 and Haiku 3.5
|
||||
- Bedrock support for the Anthropic Claude Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock) including the latest Sonnet 3.5 v2
|
||||
- Bedrock support for the Meta LLama 2, 3, 3.1 and 3.2 Models [usage](https://ts.llamaindex.ai/modules/llms/available_llms/bedrock)
|
||||
- Meta LLama3.1 405b and Llama3.2 tool call support
|
||||
- Meta 3.2 11B and 90B vision support
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@llamaindex/community",
|
||||
"description": "Community package for LlamaIndexTS",
|
||||
"version": "0.0.67",
|
||||
"version": "0.0.58",
|
||||
"type": "module",
|
||||
"types": "dist/type/index.d.ts",
|
||||
"main": "dist/cjs/index.js",
|
||||
@@ -42,8 +42,8 @@
|
||||
"dev": "bunchee --watch"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.9.0",
|
||||
"bunchee": "5.6.1"
|
||||
"@types/node": "^22.8.4",
|
||||
"bunchee": "5.5.1"
|
||||
},
|
||||
"dependencies": {
|
||||
"@aws-sdk/client-bedrock-agent-runtime": "^3.642.0",
|
||||
|
||||
@@ -66,7 +66,6 @@ export const BEDROCK_MODELS = {
|
||||
ANTHROPIC_CLAUDE_3_OPUS: "anthropic.claude-3-opus-20240229-v1:0",
|
||||
ANTHROPIC_CLAUDE_3_5_SONNET: "anthropic.claude-3-5-sonnet-20240620-v1:0",
|
||||
ANTHROPIC_CLAUDE_3_5_SONNET_V2: "anthropic.claude-3-5-sonnet-20241022-v2:0",
|
||||
ANTHROPIC_CLAUDE_3_5_HAIKU: "anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
META_LLAMA2_13B_CHAT: "meta.llama2-13b-chat-v1",
|
||||
META_LLAMA2_70B_CHAT: "meta.llama2-70b-chat-v1",
|
||||
META_LLAMA3_8B_INSTRUCT: "meta.llama3-8b-instruct-v1:0",
|
||||
@@ -87,7 +86,6 @@ export type BEDROCK_MODELS =
|
||||
|
||||
export const INFERENCE_BEDROCK_MODELS = {
|
||||
US_ANTHROPIC_CLAUDE_3_HAIKU: "us.anthropic.claude-3-haiku-20240307-v1:0",
|
||||
US_ANTHROPIC_CLAUDE_3_5_HAIKU: "us.anthropic.claude-3-5-haiku-20241022-v1:0",
|
||||
US_ANTHROPIC_CLAUDE_3_OPUS: "us.anthropic.claude-3-opus-20240229-v1:0",
|
||||
US_ANTHROPIC_CLAUDE_3_SONNET: "us.anthropic.claude-3-sonnet-20240229-v1:0",
|
||||
US_ANTHROPIC_CLAUDE_3_5_SONNET:
|
||||
@@ -100,7 +98,6 @@ export const INFERENCE_BEDROCK_MODELS = {
|
||||
US_META_LLAMA_3_2_90B_INSTRUCT: "us.meta.llama3-2-90b-instruct-v1:0",
|
||||
|
||||
EU_ANTHROPIC_CLAUDE_3_HAIKU: "eu.anthropic.claude-3-haiku-20240307-v1:0",
|
||||
EU_ANTHROPIC_CLAUDE_3_5_HAIKU: "eu.anthropic.claude-3-5-haiku-20240307-v1:0",
|
||||
EU_ANTHROPIC_CLAUDE_3_SONNET: "eu.anthropic.claude-3-sonnet-20240229-v1:0",
|
||||
EU_ANTHROPIC_CLAUDE_3_5_SONNET:
|
||||
"eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
|
||||
@@ -125,8 +122,6 @@ export const INFERENCE_TO_BEDROCK_MAP: Record<
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
|
||||
[INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_SONNET_V2]:
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
|
||||
[INFERENCE_BEDROCK_MODELS.US_ANTHROPIC_CLAUDE_3_5_HAIKU]:
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
|
||||
[INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_1B_INSTRUCT]:
|
||||
BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
|
||||
[INFERENCE_BEDROCK_MODELS.US_META_LLAMA_3_2_3B_INSTRUCT]:
|
||||
@@ -174,7 +169,6 @@ const CHAT_ONLY_MODELS = {
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 200000,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 200000,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 200000,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 200000,
|
||||
[BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
|
||||
[BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 4096,
|
||||
[BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 8192,
|
||||
@@ -210,7 +204,6 @@ export const STREAMING_MODELS = new Set([
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
|
||||
BEDROCK_MODELS.META_LLAMA2_13B_CHAT,
|
||||
BEDROCK_MODELS.META_LLAMA2_70B_CHAT,
|
||||
BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT,
|
||||
@@ -233,7 +226,6 @@ export const TOOL_CALL_MODELS: BEDROCK_MODELS[] = [
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2,
|
||||
BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU,
|
||||
BEDROCK_MODELS.META_LLAMA3_1_405B_INSTRUCT,
|
||||
BEDROCK_MODELS.META_LLAMA3_2_1B_INSTRUCT,
|
||||
BEDROCK_MODELS.META_LLAMA3_2_3B_INSTRUCT,
|
||||
@@ -267,8 +259,7 @@ export const BEDROCK_MODEL_MAX_TOKENS: Partial<Record<BEDROCK_MODELS, number>> =
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_HAIKU]: 4096,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_OPUS]: 4096,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET]: 4096,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 8192,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_HAIKU]: 8192,
|
||||
[BEDROCK_MODELS.ANTHROPIC_CLAUDE_3_5_SONNET_V2]: 4096,
|
||||
[BEDROCK_MODELS.META_LLAMA2_13B_CHAT]: 2048,
|
||||
[BEDROCK_MODELS.META_LLAMA2_70B_CHAT]: 2048,
|
||||
[BEDROCK_MODELS.META_LLAMA3_8B_INSTRUCT]: 2048,
|
||||
|
||||
@@ -1,60 +1,5 @@
|
||||
# @llamaindex/core
|
||||
|
||||
## 0.4.9
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 7ae6eaa: feat: allow pass `additionalChatOptions` to agent
|
||||
|
||||
## 0.4.8
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- f865c98: feat: async get message on chat store
|
||||
|
||||
## 0.4.7
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- d89ebe0: feat: better support for zod schema
|
||||
- fd8c882: chore: add warning on legacy workflow API
|
||||
|
||||
## 0.4.6
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [4fc001c]
|
||||
- @llamaindex/env@0.1.20
|
||||
|
||||
## 0.4.5
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- ad85bd0: - fix agent chat message not saved into the task context when streaming
|
||||
- fix async local storage might use `node:async_hook` in edge-light/workerd condition
|
||||
- Updated dependencies [ad85bd0]
|
||||
- @llamaindex/env@0.1.19
|
||||
|
||||
## 0.4.4
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [a8d3fa6]
|
||||
- @llamaindex/env@0.1.18
|
||||
|
||||
## 0.4.3
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 95a5cc6: refactor: move storage into core
|
||||
|
||||
## 0.4.2
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- Updated dependencies [14cc9eb]
|
||||
- @llamaindex/env@0.1.17
|
||||
|
||||
## 0.4.1
|
||||
|
||||
### Patch Changes
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@llamaindex/core",
|
||||
"type": "module",
|
||||
"version": "0.4.9",
|
||||
"version": "0.4.1",
|
||||
"description": "LlamaIndex Core Module",
|
||||
"exports": {
|
||||
"./agent": {
|
||||
@@ -214,48 +214,6 @@
|
||||
"default": "./storage/chat-store/dist/index.js"
|
||||
}
|
||||
},
|
||||
"./storage/doc-store": {
|
||||
"require": {
|
||||
"types": "./storage/doc-store/dist/index.d.cts",
|
||||
"default": "./storage/doc-store/dist/index.cjs"
|
||||
},
|
||||
"import": {
|
||||
"types": "./storage/doc-store/dist/index.d.ts",
|
||||
"default": "./storage/doc-store/dist/index.js"
|
||||
},
|
||||
"default": {
|
||||
"types": "./storage/doc-store/dist/index.d.ts",
|
||||
"default": "./storage/doc-store/dist/index.js"
|
||||
}
|
||||
},
|
||||
"./storage/index-store": {
|
||||
"require": {
|
||||
"types": "./storage/index-store/dist/index.d.cts",
|
||||
"default": "./storage/index-store/dist/index.cjs"
|
||||
},
|
||||
"import": {
|
||||
"types": "./storage/index-store/dist/index.d.ts",
|
||||
"default": "./storage/index-store/dist/index.js"
|
||||
},
|
||||
"default": {
|
||||
"types": "./storage/index-store/dist/index.d.ts",
|
||||
"default": "./storage/index-store/dist/index.js"
|
||||
}
|
||||
},
|
||||
"./storage/kv-store": {
|
||||
"require": {
|
||||
"types": "./storage/kv-store/dist/index.d.cts",
|
||||
"default": "./storage/kv-store/dist/index.cjs"
|
||||
},
|
||||
"import": {
|
||||
"types": "./storage/kv-store/dist/index.d.ts",
|
||||
"default": "./storage/kv-store/dist/index.js"
|
||||
},
|
||||
"default": {
|
||||
"types": "./storage/kv-store/dist/index.d.ts",
|
||||
"default": "./storage/kv-store/dist/index.js"
|
||||
}
|
||||
},
|
||||
"./response-synthesizers": {
|
||||
"require": {
|
||||
"types": "./response-synthesizers/dist/index.d.cts",
|
||||
@@ -391,13 +349,13 @@
|
||||
"devDependencies": {
|
||||
"@edge-runtime/vm": "^4.0.3",
|
||||
"ajv": "^8.17.1",
|
||||
"bunchee": "5.6.1",
|
||||
"happy-dom": "^15.11.0",
|
||||
"bunchee": "5.5.1",
|
||||
"happy-dom": "^15.7.4",
|
||||
"natural": "^8.0.1"
|
||||
},
|
||||
"dependencies": {
|
||||
"@llamaindex/env": "workspace:*",
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"magic-bytes.js": "^1.10.0",
|
||||
"zod": "^3.23.8",
|
||||
"zod-to-json-schema": "^3.23.3"
|
||||
|
||||
+19
-103
@@ -3,7 +3,7 @@ import {
|
||||
BaseChatEngine,
|
||||
type NonStreamingChatEngineParams,
|
||||
type StreamingChatEngineParams,
|
||||
} from "../chat-engine";
|
||||
} from "../chat-engine/base";
|
||||
import { wrapEventCaller } from "../decorator";
|
||||
import { Settings } from "../global";
|
||||
import type {
|
||||
@@ -106,17 +106,11 @@ export type AgentRunnerParams<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = {
|
||||
llm: AI;
|
||||
chatHistory: ChatMessage<AdditionalMessageOptions>[];
|
||||
systemPrompt: MessageContent | null;
|
||||
runner: AgentWorker<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
|
||||
tools:
|
||||
| BaseToolWithCall[]
|
||||
| ((query: MessageContent) => Promise<BaseToolWithCall[]>);
|
||||
@@ -131,7 +125,6 @@ export type AgentParamsBase<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> =
|
||||
| {
|
||||
llm?: AI;
|
||||
@@ -139,7 +132,6 @@ export type AgentParamsBase<
|
||||
systemPrompt?: MessageContent;
|
||||
verbose?: boolean;
|
||||
tools: BaseToolWithCall[];
|
||||
additionalChatOptions?: AdditionalChatOptions;
|
||||
}
|
||||
| {
|
||||
llm?: AI;
|
||||
@@ -147,7 +139,6 @@ export type AgentParamsBase<
|
||||
systemPrompt?: MessageContent;
|
||||
verbose?: boolean;
|
||||
toolRetriever: ObjectRetriever<BaseToolWithCall>;
|
||||
additionalChatOptions?: AdditionalChatOptions;
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -162,75 +153,37 @@ export abstract class AgentWorker<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> {
|
||||
#taskSet = new Set<
|
||||
TaskStep<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
|
||||
>();
|
||||
abstract taskHandler: TaskHandler<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
#taskSet = new Set<TaskStep<AI, Store, AdditionalMessageOptions>>();
|
||||
abstract taskHandler: TaskHandler<AI, Store, AdditionalMessageOptions>;
|
||||
|
||||
public createTask(
|
||||
query: MessageContent,
|
||||
context: AgentTaskContext<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
): ReadableStream<
|
||||
TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
|
||||
> {
|
||||
context: AgentTaskContext<AI, Store, AdditionalMessageOptions>,
|
||||
): ReadableStream<TaskStepOutput<AI, Store, AdditionalMessageOptions>> {
|
||||
context.store.messages.push({
|
||||
role: "user",
|
||||
content: query,
|
||||
});
|
||||
const taskOutputStream = createTaskOutputStream(this.taskHandler, context);
|
||||
return new ReadableStream<
|
||||
TaskStepOutput<AI, Store, AdditionalMessageOptions, AdditionalChatOptions>
|
||||
TaskStepOutput<AI, Store, AdditionalMessageOptions>
|
||||
>({
|
||||
start: async (controller) => {
|
||||
for await (const stepOutput of taskOutputStream) {
|
||||
this.#taskSet.add(stepOutput.taskStep);
|
||||
controller.enqueue(stepOutput);
|
||||
if (stepOutput.isLast) {
|
||||
let currentStep: TaskStep<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
AdditionalMessageOptions
|
||||
> | null = stepOutput.taskStep;
|
||||
while (currentStep) {
|
||||
this.#taskSet.delete(currentStep);
|
||||
currentStep = currentStep.prevStep;
|
||||
}
|
||||
const { output, taskStep } = stepOutput;
|
||||
if (output instanceof ReadableStream) {
|
||||
const [pipStream, finalStream] = output.tee();
|
||||
stepOutput.output = finalStream;
|
||||
const reader = pipStream.getReader();
|
||||
const { value } = await reader.read();
|
||||
reader.releaseLock();
|
||||
let content: string = value!.delta;
|
||||
for await (const chunk of pipStream) {
|
||||
content += chunk.delta;
|
||||
}
|
||||
taskStep.context.store.messages = [
|
||||
...taskStep.context.store.messages,
|
||||
{
|
||||
role: "assistant",
|
||||
content,
|
||||
options: value!.options,
|
||||
},
|
||||
];
|
||||
}
|
||||
controller.enqueue(stepOutput);
|
||||
controller.close();
|
||||
} else {
|
||||
controller.enqueue(stepOutput);
|
||||
}
|
||||
}
|
||||
},
|
||||
@@ -252,7 +205,6 @@ export abstract class AgentRunner<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> extends BaseChatEngine {
|
||||
readonly #llm: AI;
|
||||
readonly #tools:
|
||||
@@ -260,12 +212,7 @@ export abstract class AgentRunner<
|
||||
| ((query: MessageContent) => Promise<BaseToolWithCall[]>);
|
||||
readonly #systemPrompt: MessageContent | null = null;
|
||||
#chatHistory: ChatMessage<AdditionalMessageOptions>[];
|
||||
readonly #runner: AgentWorker<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
readonly #runner: AgentWorker<AI, Store, AdditionalMessageOptions>;
|
||||
readonly #verbose: boolean;
|
||||
|
||||
// create extra store
|
||||
@@ -276,7 +223,7 @@ export abstract class AgentRunner<
|
||||
}
|
||||
|
||||
static defaultTaskHandler: TaskHandler<LLM> = async (step, enqueueOutput) => {
|
||||
const { llm, getTools, stream, additionalChatOptions } = step.context;
|
||||
const { llm, getTools, stream } = step.context;
|
||||
const lastMessage = step.context.store.messages.at(-1)!.content;
|
||||
const tools = await getTools(lastMessage);
|
||||
if (!stream) {
|
||||
@@ -284,9 +231,8 @@ export abstract class AgentRunner<
|
||||
stream,
|
||||
tools,
|
||||
messages: [...step.context.store.messages],
|
||||
additionalChatOptions,
|
||||
});
|
||||
await stepTools({
|
||||
await stepTools<LLM>({
|
||||
response,
|
||||
tools,
|
||||
step,
|
||||
@@ -297,7 +243,6 @@ export abstract class AgentRunner<
|
||||
stream,
|
||||
tools,
|
||||
messages: [...step.context.store.messages],
|
||||
additionalChatOptions,
|
||||
});
|
||||
await stepToolsStreaming<LLM>({
|
||||
response,
|
||||
@@ -309,12 +254,7 @@ export abstract class AgentRunner<
|
||||
};
|
||||
|
||||
protected constructor(
|
||||
params: AgentRunnerParams<
|
||||
AI,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
params: AgentRunnerParams<AI, Store, AdditionalMessageOptions>,
|
||||
) {
|
||||
super();
|
||||
const { llm, chatHistory, systemPrompt, runner, tools, verbose } = params;
|
||||
@@ -368,7 +308,6 @@ export abstract class AgentRunner<
|
||||
stream: boolean = false,
|
||||
verbose: boolean | undefined = undefined,
|
||||
chatHistory?: ChatMessage<AdditionalMessageOptions>[],
|
||||
additionalChatOptions?: AdditionalChatOptions,
|
||||
) {
|
||||
const initialMessages = [...(chatHistory ?? this.#chatHistory)];
|
||||
if (this.#systemPrompt !== null) {
|
||||
@@ -387,7 +326,6 @@ export abstract class AgentRunner<
|
||||
stream,
|
||||
toolCallCount: 0,
|
||||
llm: this.#llm,
|
||||
additionalChatOptions: additionalChatOptions ?? {},
|
||||
getTools: (message) => this.getTools(message),
|
||||
store: {
|
||||
...this.createStore(),
|
||||
@@ -405,29 +343,13 @@ export abstract class AgentRunner<
|
||||
});
|
||||
}
|
||||
|
||||
async chat(params: NonStreamingChatEngineParams): Promise<EngineResponse>;
|
||||
async chat(
|
||||
params: NonStreamingChatEngineParams<
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
): Promise<EngineResponse>;
|
||||
async chat(
|
||||
params: StreamingChatEngineParams<
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
params: StreamingChatEngineParams,
|
||||
): Promise<ReadableStream<EngineResponse>>;
|
||||
@wrapEventCaller
|
||||
async chat(
|
||||
params:
|
||||
| NonStreamingChatEngineParams<
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>
|
||||
| StreamingChatEngineParams<
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
params: NonStreamingChatEngineParams | StreamingChatEngineParams,
|
||||
): Promise<EngineResponse | ReadableStream<EngineResponse>> {
|
||||
let chatHistory: ChatMessage<AdditionalMessageOptions>[] = [];
|
||||
|
||||
@@ -444,7 +366,6 @@ export abstract class AgentRunner<
|
||||
!!params.stream,
|
||||
false,
|
||||
chatHistory,
|
||||
params.chatOptions,
|
||||
);
|
||||
for await (const stepOutput of task) {
|
||||
// update chat history for each round
|
||||
@@ -452,15 +373,10 @@ export abstract class AgentRunner<
|
||||
if (stepOutput.isLast) {
|
||||
const { output } = stepOutput;
|
||||
if (output instanceof ReadableStream) {
|
||||
return output.pipeThrough(
|
||||
new TransformStream<EngineResponse>({
|
||||
return output.pipeThrough<EngineResponse>(
|
||||
new TransformStream({
|
||||
transform(chunk, controller) {
|
||||
controller.enqueue(
|
||||
EngineResponse.fromChatResponseChunk(
|
||||
chunk,
|
||||
chunk.sourceNodes,
|
||||
),
|
||||
);
|
||||
controller.enqueue(EngineResponse.fromChatResponseChunk(chunk));
|
||||
},
|
||||
}),
|
||||
);
|
||||
|
||||
@@ -4,66 +4,24 @@ import { ObjectRetriever } from "../objects";
|
||||
import { AgentRunner, AgentWorker, type AgentParamsBase } from "./base.js";
|
||||
import { validateAgentParams } from "./utils.js";
|
||||
|
||||
type LLMParamsBase<
|
||||
AI extends LLM,
|
||||
AdditionalMessageOptions extends object = AI extends LLM<
|
||||
object,
|
||||
infer AdditionalMessageOptions
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = AgentParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions>;
|
||||
type LLMParamsBase = AgentParamsBase<LLM>;
|
||||
|
||||
type LLMParamsWithTools<
|
||||
AI extends LLM,
|
||||
AdditionalMessageOptions extends object = AI extends LLM<
|
||||
object,
|
||||
infer AdditionalMessageOptions
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
|
||||
type LLMParamsWithTools = LLMParamsBase & {
|
||||
tools: BaseToolWithCall[];
|
||||
};
|
||||
|
||||
type LLMParamsWithToolRetriever<
|
||||
AI extends LLM,
|
||||
AdditionalMessageOptions extends object = AI extends LLM<
|
||||
object,
|
||||
infer AdditionalMessageOptions
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = LLMParamsBase<AI, AdditionalMessageOptions, AdditionalChatOptions> & {
|
||||
type LLMParamsWithToolRetriever = LLMParamsBase & {
|
||||
toolRetriever: ObjectRetriever<BaseToolWithCall>;
|
||||
};
|
||||
|
||||
export type LLMAgentParams<
|
||||
AI extends LLM,
|
||||
AdditionalMessageOptions extends object = AI extends LLM<
|
||||
object,
|
||||
infer AdditionalMessageOptions
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> =
|
||||
| LLMParamsWithTools<AI, AdditionalMessageOptions, AdditionalChatOptions>
|
||||
| LLMParamsWithToolRetriever<
|
||||
AI,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
export type LLMAgentParams = LLMParamsWithTools | LLMParamsWithToolRetriever;
|
||||
|
||||
export class LLMAgentWorker extends AgentWorker<LLM> {
|
||||
taskHandler = AgentRunner.defaultTaskHandler;
|
||||
}
|
||||
|
||||
export class LLMAgent extends AgentRunner<LLM> {
|
||||
constructor(params: LLMAgentParams<LLM>) {
|
||||
constructor(params: LLMAgentParams) {
|
||||
validateAgentParams(params);
|
||||
const llm = params.llm ?? (Settings.llm ? (Settings.llm as LLM) : null);
|
||||
if (!llm)
|
||||
|
||||
@@ -19,7 +19,6 @@ export type AgentTaskContext<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = {
|
||||
readonly stream: boolean;
|
||||
readonly toolCallCount: number;
|
||||
@@ -27,7 +26,6 @@ export type AgentTaskContext<
|
||||
readonly getTools: (
|
||||
input: MessageContent,
|
||||
) => BaseToolWithCall[] | Promise<BaseToolWithCall[]>;
|
||||
readonly additionalChatOptions: Partial<AdditionalChatOptions>;
|
||||
shouldContinue: (
|
||||
taskStep: Readonly<TaskStep<Model, Store, AdditionalMessageOptions>>,
|
||||
) => boolean;
|
||||
@@ -47,26 +45,13 @@ export type TaskStep<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = {
|
||||
id: UUID;
|
||||
context: AgentTaskContext<
|
||||
Model,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
context: AgentTaskContext<Model, Store, AdditionalMessageOptions>;
|
||||
|
||||
// linked list
|
||||
prevStep: TaskStep<
|
||||
Model,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
> | null;
|
||||
nextSteps: Set<
|
||||
TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>
|
||||
>;
|
||||
prevStep: TaskStep<Model, Store, AdditionalMessageOptions> | null;
|
||||
nextSteps: Set<TaskStep<Model, Store, AdditionalMessageOptions>>;
|
||||
};
|
||||
|
||||
export type TaskStepOutput<
|
||||
@@ -78,14 +63,8 @@ export type TaskStepOutput<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = {
|
||||
taskStep: TaskStep<
|
||||
Model,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>;
|
||||
taskStep: TaskStep<Model, Store, AdditionalMessageOptions>;
|
||||
// output shows the response to the user
|
||||
output:
|
||||
| ChatResponse<AdditionalMessageOptions>
|
||||
@@ -102,16 +81,10 @@ export type TaskHandler<
|
||||
>
|
||||
? AdditionalMessageOptions
|
||||
: never,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> = (
|
||||
step: TaskStep<Model, Store, AdditionalMessageOptions, AdditionalChatOptions>,
|
||||
step: TaskStep<Model, Store, AdditionalMessageOptions>,
|
||||
enqueueOutput: (
|
||||
taskOutput: TaskStepOutput<
|
||||
Model,
|
||||
Store,
|
||||
AdditionalMessageOptions,
|
||||
AdditionalChatOptions
|
||||
>,
|
||||
taskOutput: TaskStepOutput<Model, Store, AdditionalMessageOptions>,
|
||||
) => void,
|
||||
) => Promise<void>;
|
||||
|
||||
|
||||
@@ -79,7 +79,7 @@ export async function stepToolsStreaming<Model extends LLM>({
|
||||
for await (const chunk of pipStream) {
|
||||
if (chunk.options && "toolCall" in chunk.options) {
|
||||
const toolCall = chunk.options.toolCall;
|
||||
toolCall.forEach((toolCall: ToolCall | PartialToolCall) => {
|
||||
toolCall.forEach((toolCall) => {
|
||||
toolCalls.set(toolCall.id, toolCall);
|
||||
});
|
||||
}
|
||||
|
||||
@@ -16,18 +16,14 @@ export interface BaseChatEngineParams<
|
||||
|
||||
export interface StreamingChatEngineParams<
|
||||
AdditionalMessageOptions extends object = object,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> extends BaseChatEngineParams<AdditionalMessageOptions> {
|
||||
stream: true;
|
||||
chatOptions?: AdditionalChatOptions;
|
||||
}
|
||||
|
||||
export interface NonStreamingChatEngineParams<
|
||||
AdditionalMessageOptions extends object = object,
|
||||
AdditionalChatOptions extends object = object,
|
||||
> extends BaseChatEngineParams<AdditionalMessageOptions> {
|
||||
stream?: false;
|
||||
chatOptions?: AdditionalChatOptions;
|
||||
}
|
||||
|
||||
export abstract class BaseChatEngine {
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
import { randomUUID } from "@llamaindex/env";
|
||||
import type { UUID } from "../global";
|
||||
import { BaseNode } from "../schema";
|
||||
import { IndexStructType } from "./struct-type";
|
||||
|
||||
export abstract class IndexStruct {
|
||||
@@ -66,48 +65,3 @@ export class KeywordTable extends IndexStruct {
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
export class IndexDict extends IndexStruct {
|
||||
nodesDict: Record<string, BaseNode> = {};
|
||||
type: IndexStructType = IndexStructType.SIMPLE_DICT;
|
||||
|
||||
addNode(node: BaseNode, textId?: string) {
|
||||
const vectorId = textId ?? node.id_;
|
||||
this.nodesDict[vectorId] = node;
|
||||
}
|
||||
|
||||
toJson(): Record<string, unknown> {
|
||||
const nodesDict: Record<string, unknown> = {};
|
||||
|
||||
for (const [key, node] of Object.entries(this.nodesDict)) {
|
||||
nodesDict[key] = node.toJSON();
|
||||
}
|
||||
|
||||
return {
|
||||
...super.toJson(),
|
||||
nodesDict,
|
||||
type: this.type,
|
||||
};
|
||||
}
|
||||
|
||||
delete(nodeId: string) {
|
||||
delete this.nodesDict[nodeId];
|
||||
}
|
||||
}
|
||||
|
||||
export class IndexList extends IndexStruct {
|
||||
nodes: string[] = [];
|
||||
type: IndexStructType = IndexStructType.LIST;
|
||||
|
||||
addNode(node: BaseNode) {
|
||||
this.nodes.push(node.id_);
|
||||
}
|
||||
|
||||
toJson(): Record<string, unknown> {
|
||||
return {
|
||||
...super.toJson(),
|
||||
nodes: this.nodes,
|
||||
type: this.type,
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,8 +1,2 @@
|
||||
export {
|
||||
IndexDict,
|
||||
IndexList,
|
||||
IndexStruct,
|
||||
KeywordTable,
|
||||
} from "./data-structs";
|
||||
export { jsonToIndexStruct } from "./json-to-index-struct";
|
||||
export { IndexStruct, KeywordTable } from "./data-structs";
|
||||
export { IndexStructType } from "./struct-type";
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
import type { BaseNode } from "../schema";
|
||||
import { jsonToNode } from "../schema";
|
||||
import { IndexDict, IndexList, IndexStruct } from "./data-structs";
|
||||
import { IndexStructType } from "./struct-type";
|
||||
|
||||
export function jsonToIndexStruct(
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
json: any,
|
||||
): IndexStruct {
|
||||
if (json.type === IndexStructType.LIST) {
|
||||
const indexList = new IndexList(json.indexId, json.summary);
|
||||
indexList.nodes = json.nodes;
|
||||
return indexList;
|
||||
} else if (json.type === IndexStructType.SIMPLE_DICT) {
|
||||
const indexDict = new IndexDict(json.indexId, json.summary);
|
||||
indexDict.nodesDict = Object.entries(json.nodesDict).reduce<
|
||||
Record<string, BaseNode>
|
||||
>((acc, [key, value]) => {
|
||||
acc[key] = jsonToNode(value);
|
||||
return acc;
|
||||
}, {});
|
||||
return indexDict;
|
||||
} else {
|
||||
throw new Error(`Unknown index struct type: ${json.type}`);
|
||||
}
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { Tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { type Tokenizers } from "@llamaindex/env";
|
||||
import type { MessageContentDetail } from "../llms";
|
||||
import { BaseNode, MetadataMode, TransformComponent } from "../schema";
|
||||
import { extractSingleText } from "../utils";
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { Tokenizers, tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { Tokenizers, tokenizers } from "@llamaindex/env";
|
||||
|
||||
export function truncateMaxTokens(
|
||||
tokenizer: Tokenizers,
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
import { getEnv } from "@llamaindex/env";
|
||||
import type { Tokenizer } from "@llamaindex/env/tokenizers";
|
||||
import { getEnv, type Tokenizer } from "@llamaindex/env";
|
||||
import type { LLM } from "../llms";
|
||||
import {
|
||||
type CallbackManager,
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
import { AsyncLocalStorage } from "@llamaindex/env";
|
||||
import { type Tokenizer, tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { AsyncLocalStorage, type Tokenizer, tokenizers } from "@llamaindex/env";
|
||||
|
||||
const chunkSizeAsyncLocalStorage = new AsyncLocalStorage<Tokenizer>();
|
||||
let globalTokenizer: Tokenizer = tokenizers.tokenizer();
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { Tokenizer } from "@llamaindex/env/tokenizers";
|
||||
import { type Tokenizer, tokenizers } from "@llamaindex/env";
|
||||
import {
|
||||
DEFAULT_CHUNK_OVERLAP_RATIO,
|
||||
DEFAULT_CONTEXT_WINDOW,
|
||||
@@ -64,7 +64,7 @@ export class PromptHelper {
|
||||
this.numOutput = numOutput;
|
||||
this.chunkOverlapRatio = chunkOverlapRatio;
|
||||
this.chunkSizeLimit = chunkSizeLimit;
|
||||
this.tokenizer = tokenizer ?? Settings.tokenizer;
|
||||
this.tokenizer = tokenizer ?? tokenizers.tokenizer();
|
||||
this.separator = separator;
|
||||
}
|
||||
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
import { extractText, streamConverter } from "../utils";
|
||||
import { streamConverter } from "../utils";
|
||||
import { extractText } from "../utils/llms";
|
||||
import type {
|
||||
ChatResponse,
|
||||
ChatResponseChunk,
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import type { Tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import type { Tokenizers } from "@llamaindex/env";
|
||||
import type { JSONSchemaType } from "ajv";
|
||||
import type { JSONObject, JSONValue } from "../global";
|
||||
import type { JSONObject, JSONValue } from "../global/type";
|
||||
|
||||
/**
|
||||
* @internal
|
||||
|
||||
@@ -65,9 +65,7 @@ export abstract class BaseChatStoreMemory<
|
||||
super();
|
||||
}
|
||||
|
||||
getAllMessages():
|
||||
| ChatMessage<AdditionalMessageOptions>[]
|
||||
| Promise<ChatMessage<AdditionalMessageOptions>[]> {
|
||||
getAllMessages(): ChatMessage<AdditionalMessageOptions>[] {
|
||||
return this.chatStore.getMessages(this.chatStoreKey);
|
||||
}
|
||||
|
||||
|
||||
@@ -33,11 +33,11 @@ export class ChatMemoryBuffer<
|
||||
}
|
||||
}
|
||||
|
||||
async getMessages(
|
||||
getMessages(
|
||||
transientMessages?: ChatMessage<AdditionalMessageOptions>[] | undefined,
|
||||
initialTokenCount: number = 0,
|
||||
) {
|
||||
const messages = await this.getAllMessages();
|
||||
const messages = this.getAllMessages();
|
||||
|
||||
if (initialTokenCount > this.tokenLimit) {
|
||||
throw new Error("Initial token count exceeds token limit");
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { type Tokenizer, tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { type Tokenizer, tokenizers } from "@llamaindex/env";
|
||||
import { Settings } from "../global";
|
||||
import type { ChatMessage, LLM, MessageType } from "../llms";
|
||||
import { defaultSummaryPrompt, type SummaryPrompt } from "../prompts";
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { Tokenizer } from "@llamaindex/env/tokenizers";
|
||||
import type { Tokenizer } from "@llamaindex/env";
|
||||
import { z } from "zod";
|
||||
import { Settings } from "../global";
|
||||
import { sentenceSplitterSchema } from "../schema";
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { Tokenizer } from "@llamaindex/env/tokenizers";
|
||||
import type { Tokenizer } from "@llamaindex/env";
|
||||
import { z } from "zod";
|
||||
import { DEFAULT_CHUNK_OVERLAP, DEFAULT_CHUNK_SIZE, Settings } from "../global";
|
||||
import { MetadataAwareTextSplitter } from "./base";
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import type { Tokenizer } from "@llamaindex/env/tokenizers";
|
||||
import type { Tokenizer } from "@llamaindex/env";
|
||||
|
||||
export type SplitterParams = {
|
||||
tokenizer?: Tokenizer;
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import type { MessageContent } from "../llms";
|
||||
import type { BaseNodePostprocessor } from "../postprocessor";
|
||||
import { BaseQueryEngine, type QueryType } from "../query-engine";
|
||||
import {
|
||||
type BaseSynthesizer,
|
||||
getResponseSynthesizer,
|
||||
@@ -7,7 +8,6 @@ import {
|
||||
import { BaseRetriever } from "../retriever";
|
||||
import type { NodeWithScore } from "../schema";
|
||||
import { extractText } from "../utils";
|
||||
import { BaseQueryEngine, type QueryType } from "./base";
|
||||
|
||||
export class RetrieverQueryEngine extends BaseQueryEngine {
|
||||
retriever: BaseRetriever;
|
||||
|
||||
@@ -1,10 +1,5 @@
|
||||
export * from "./node";
|
||||
export {
|
||||
FileReader,
|
||||
TransformComponent,
|
||||
type BaseReader,
|
||||
type StoredValue,
|
||||
} from "./type";
|
||||
export { FileReader, TransformComponent, type BaseReader } from "./type";
|
||||
export type { BaseOutputParser } from "./type/base-output-parser";
|
||||
export { EngineResponse } from "./type/engine–response";
|
||||
export * from "./zod";
|
||||
|
||||
@@ -1,10 +1,6 @@
|
||||
import { fs, path, randomUUID } from "@llamaindex/env";
|
||||
import type { BaseNode, Document } from "./node";
|
||||
|
||||
// fixme: remove any
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
export type StoredValue = Record<string, any> | null;
|
||||
|
||||
interface TransformComponentSignature<
|
||||
Result extends BaseNode[] | Promise<BaseNode[]>,
|
||||
> {
|
||||
|
||||
@@ -7,11 +7,7 @@ export abstract class BaseChatStore<
|
||||
key: string,
|
||||
messages: ChatMessage<AdditionalMessageOptions>[],
|
||||
): void;
|
||||
abstract getMessages(
|
||||
key: string,
|
||||
):
|
||||
| ChatMessage<AdditionalMessageOptions>[]
|
||||
| Promise<ChatMessage<AdditionalMessageOptions>[]>;
|
||||
abstract getMessages(key: string): ChatMessage<AdditionalMessageOptions>[];
|
||||
abstract addMessage(
|
||||
key: string,
|
||||
message: ChatMessage<AdditionalMessageOptions>,
|
||||
|
||||
@@ -1,167 +0,0 @@
|
||||
import { path } from "@llamaindex/env";
|
||||
import {
|
||||
DEFAULT_DOC_STORE_PERSIST_FILENAME,
|
||||
DEFAULT_PERSIST_DIR,
|
||||
} from "../../global";
|
||||
import type { StoredValue } from "../../schema";
|
||||
import { BaseNode, Document, ObjectType, TextNode } from "../../schema";
|
||||
|
||||
const TYPE_KEY = "__type__";
|
||||
const DATA_KEY = "__data__";
|
||||
|
||||
export interface Serializer<T> {
|
||||
toPersistence(data: Record<string, unknown>): T;
|
||||
|
||||
fromPersistence(data: T): Record<string, unknown>;
|
||||
}
|
||||
|
||||
export const jsonSerializer: Serializer<string> = {
|
||||
toPersistence(data) {
|
||||
return JSON.stringify(data);
|
||||
},
|
||||
fromPersistence(data) {
|
||||
return JSON.parse(data);
|
||||
},
|
||||
};
|
||||
|
||||
export const noneSerializer: Serializer<Record<string, unknown>> = {
|
||||
toPersistence(data) {
|
||||
return data;
|
||||
},
|
||||
fromPersistence(data) {
|
||||
return data;
|
||||
},
|
||||
};
|
||||
|
||||
type DocJson<Data> = {
|
||||
[TYPE_KEY]: ObjectType;
|
||||
[DATA_KEY]: Data;
|
||||
};
|
||||
|
||||
export function isValidDocJson(
|
||||
docJson: StoredValue | null | undefined,
|
||||
): docJson is DocJson<unknown> {
|
||||
return (
|
||||
typeof docJson === "object" &&
|
||||
docJson !== null &&
|
||||
docJson[TYPE_KEY] !== undefined &&
|
||||
docJson[DATA_KEY] !== undefined
|
||||
);
|
||||
}
|
||||
|
||||
export function docToJson(
|
||||
doc: BaseNode,
|
||||
serializer: Serializer<unknown>,
|
||||
): DocJson<unknown> {
|
||||
return {
|
||||
[DATA_KEY]: serializer.toPersistence(doc.toJSON()),
|
||||
[TYPE_KEY]: doc.type,
|
||||
};
|
||||
}
|
||||
|
||||
export function jsonToDoc<Data>(
|
||||
docDict: DocJson<Data>,
|
||||
serializer: Serializer<Data>,
|
||||
): BaseNode {
|
||||
const docType = docDict[TYPE_KEY];
|
||||
// fixme: zod type check this
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const dataDict: any = serializer.fromPersistence(docDict[DATA_KEY]);
|
||||
let doc: BaseNode;
|
||||
|
||||
if (docType === ObjectType.DOCUMENT) {
|
||||
doc = new Document({
|
||||
text: dataDict.text,
|
||||
id_: dataDict.id_,
|
||||
embedding: dataDict.embedding,
|
||||
hash: dataDict.hash,
|
||||
metadata: dataDict.metadata,
|
||||
});
|
||||
} else if (docType === ObjectType.TEXT) {
|
||||
doc = new TextNode({
|
||||
text: dataDict.text,
|
||||
id_: dataDict.id_,
|
||||
hash: dataDict.hash,
|
||||
metadata: dataDict.metadata,
|
||||
relationships: dataDict.relationships,
|
||||
});
|
||||
} else {
|
||||
throw new Error(`Unknown doc type: ${docType}`);
|
||||
}
|
||||
|
||||
return doc;
|
||||
}
|
||||
|
||||
const DEFAULT_PERSIST_PATH = path.join(
|
||||
DEFAULT_PERSIST_DIR,
|
||||
DEFAULT_DOC_STORE_PERSIST_FILENAME,
|
||||
);
|
||||
|
||||
export interface RefDocInfo {
|
||||
nodeIds: string[];
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
extraInfo: Record<string, any>;
|
||||
}
|
||||
|
||||
export abstract class BaseDocumentStore {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
serializer: Serializer<any> = jsonSerializer;
|
||||
|
||||
// Save/load
|
||||
persist(persistPath: string = DEFAULT_PERSIST_PATH): void {
|
||||
// Persist the docstore to a file.
|
||||
}
|
||||
|
||||
// Main interface
|
||||
abstract docs(): Promise<Record<string, BaseNode>>;
|
||||
|
||||
abstract addDocuments(docs: BaseNode[], allowUpdate: boolean): Promise<void>;
|
||||
|
||||
abstract getDocument(
|
||||
docId: string,
|
||||
raiseError: boolean,
|
||||
): Promise<BaseNode | undefined>;
|
||||
|
||||
abstract deleteDocument(docId: string, raiseError: boolean): Promise<void>;
|
||||
|
||||
abstract documentExists(docId: string): Promise<boolean>;
|
||||
|
||||
// Hash
|
||||
abstract setDocumentHash(docId: string, docHash: string): Promise<void>;
|
||||
|
||||
abstract getDocumentHash(docId: string): Promise<string | undefined>;
|
||||
|
||||
abstract getAllDocumentHashes(): Promise<Record<string, string>>;
|
||||
|
||||
// Ref Docs
|
||||
abstract getAllRefDocInfo(): Promise<Record<string, RefDocInfo> | undefined>;
|
||||
|
||||
abstract getRefDocInfo(refDocId: string): Promise<RefDocInfo | undefined>;
|
||||
|
||||
abstract deleteRefDoc(refDocId: string, raiseError: boolean): Promise<void>;
|
||||
|
||||
// Nodes
|
||||
getNodes(nodeIds: string[], raiseError: boolean = true): Promise<BaseNode[]> {
|
||||
return Promise.all(
|
||||
nodeIds.map((nodeId) => this.getNode(nodeId, raiseError)),
|
||||
);
|
||||
}
|
||||
|
||||
async getNode(nodeId: string, raiseError: boolean = true): Promise<BaseNode> {
|
||||
const doc = await this.getDocument(nodeId, raiseError);
|
||||
if (!(doc instanceof BaseNode)) {
|
||||
throw new Error(`Document ${nodeId} is not a Node.`);
|
||||
}
|
||||
return doc;
|
||||
}
|
||||
|
||||
async getNodeDict(nodeIdDict: {
|
||||
[index: number]: string;
|
||||
}): Promise<Record<number, BaseNode>> {
|
||||
const result: Record<number, BaseNode> = {};
|
||||
for (const index in nodeIdDict) {
|
||||
result[index] = await this.getNode(nodeIdDict[index]!);
|
||||
}
|
||||
return result;
|
||||
}
|
||||
}
|
||||
@@ -1,115 +0,0 @@
|
||||
import { path } from "@llamaindex/env";
|
||||
import { IndexStruct, jsonToIndexStruct } from "../../data-structs";
|
||||
import {
|
||||
DEFAULT_INDEX_STORE_PERSIST_FILENAME,
|
||||
DEFAULT_NAMESPACE,
|
||||
DEFAULT_PERSIST_DIR,
|
||||
} from "../../global";
|
||||
import {
|
||||
BaseInMemoryKVStore,
|
||||
BaseKVStore,
|
||||
type DataType,
|
||||
SimpleKVStore,
|
||||
} from "../kv-store";
|
||||
|
||||
export const DEFAULT_PERSIST_PATH = path.join(
|
||||
DEFAULT_PERSIST_DIR,
|
||||
DEFAULT_INDEX_STORE_PERSIST_FILENAME,
|
||||
);
|
||||
|
||||
export abstract class BaseIndexStore {
|
||||
abstract getIndexStructs(): Promise<IndexStruct[]>;
|
||||
|
||||
abstract addIndexStruct(indexStruct: IndexStruct): Promise<void>;
|
||||
|
||||
abstract deleteIndexStruct(key: string): Promise<void>;
|
||||
|
||||
abstract getIndexStruct(structId?: string): Promise<IndexStruct | undefined>;
|
||||
|
||||
async persist(persistPath: string = DEFAULT_PERSIST_PATH): Promise<void> {
|
||||
// Persist the index store to disk.
|
||||
}
|
||||
}
|
||||
|
||||
export class KVIndexStore extends BaseIndexStore {
|
||||
private _kvStore: BaseKVStore;
|
||||
private _collection: string;
|
||||
|
||||
constructor(kvStore: BaseKVStore, namespace: string = DEFAULT_NAMESPACE) {
|
||||
super();
|
||||
this._kvStore = kvStore;
|
||||
this._collection = `${namespace}/data`;
|
||||
}
|
||||
|
||||
async addIndexStruct(indexStruct: IndexStruct): Promise<void> {
|
||||
const key = indexStruct.indexId;
|
||||
const data = indexStruct.toJson();
|
||||
await this._kvStore.put(key, data, this._collection);
|
||||
}
|
||||
|
||||
async deleteIndexStruct(key: string): Promise<void> {
|
||||
await this._kvStore.delete(key, this._collection);
|
||||
}
|
||||
|
||||
async getIndexStruct(structId?: string): Promise<IndexStruct | undefined> {
|
||||
if (!structId) {
|
||||
const structs = await this.getIndexStructs();
|
||||
if (structs.length !== 1) {
|
||||
throw new Error("More than one index struct found");
|
||||
}
|
||||
return structs[0];
|
||||
} else {
|
||||
const json = await this._kvStore.get(structId, this._collection);
|
||||
if (json == null) {
|
||||
return;
|
||||
}
|
||||
return jsonToIndexStruct(json);
|
||||
}
|
||||
}
|
||||
|
||||
async getIndexStructs(): Promise<IndexStruct[]> {
|
||||
const jsons = await this._kvStore.getAll(this._collection);
|
||||
return Object.values(jsons).map((json) => jsonToIndexStruct(json));
|
||||
}
|
||||
}
|
||||
|
||||
export class SimpleIndexStore extends KVIndexStore {
|
||||
private kvStore: BaseInMemoryKVStore;
|
||||
|
||||
constructor(kvStore?: BaseInMemoryKVStore) {
|
||||
kvStore = kvStore || new SimpleKVStore();
|
||||
super(kvStore);
|
||||
this.kvStore = kvStore;
|
||||
}
|
||||
|
||||
static async fromPersistDir(
|
||||
persistDir: string = DEFAULT_PERSIST_DIR,
|
||||
): Promise<SimpleIndexStore> {
|
||||
const persistPath = path.join(
|
||||
persistDir,
|
||||
DEFAULT_INDEX_STORE_PERSIST_FILENAME,
|
||||
);
|
||||
return this.fromPersistPath(persistPath);
|
||||
}
|
||||
|
||||
static async fromPersistPath(persistPath: string): Promise<SimpleIndexStore> {
|
||||
const simpleKVStore = await SimpleKVStore.fromPersistPath(persistPath);
|
||||
return new SimpleIndexStore(simpleKVStore);
|
||||
}
|
||||
|
||||
async persist(persistPath: string = DEFAULT_PERSIST_DIR): Promise<void> {
|
||||
this.kvStore.persist(persistPath);
|
||||
}
|
||||
|
||||
static fromDict(saveDict: DataType): SimpleIndexStore {
|
||||
const simpleKVStore = SimpleKVStore.fromDict(saveDict);
|
||||
return new SimpleIndexStore(simpleKVStore);
|
||||
}
|
||||
|
||||
toDict(): Record<string, unknown> {
|
||||
if (!(this.kvStore instanceof SimpleKVStore)) {
|
||||
throw new Error("KVStore is not a SimpleKVStore");
|
||||
}
|
||||
return this.kvStore.toDict();
|
||||
}
|
||||
}
|
||||
@@ -4,12 +4,18 @@ import { zodToJsonSchema } from "zod-to-json-schema";
|
||||
import type { JSONValue } from "../global";
|
||||
import type { BaseTool, ToolMetadata } from "../llms";
|
||||
|
||||
const kOriginalFn = Symbol("originalFn");
|
||||
|
||||
export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
|
||||
implements BaseTool<T>
|
||||
{
|
||||
[kOriginalFn]?: (input: T) => R;
|
||||
|
||||
#fn: (input: T) => R;
|
||||
readonly #metadata: ToolMetadata<JSONSchemaType<T>>;
|
||||
readonly #zodType: z.ZodType<T> | null = null;
|
||||
#metadata: ToolMetadata<JSONSchemaType<T>>;
|
||||
// todo: for the future, we can use zod to validate the input parameters
|
||||
// eslint-disable-next-line no-unused-private-class-members
|
||||
#zodType: z.ZodType<T> | null = null;
|
||||
constructor(
|
||||
fn: (input: T) => R,
|
||||
metadata: ToolMetadata<JSONSchemaType<T>>,
|
||||
@@ -26,12 +32,6 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
|
||||
fn: (input: T) => JSONValue | Promise<JSONValue>,
|
||||
schema: ToolMetadata<JSONSchemaType<T>>,
|
||||
): FunctionTool<T, JSONValue | Promise<JSONValue>>;
|
||||
static from<R extends z.ZodType>(
|
||||
fn: (input: z.infer<R>) => JSONValue | Promise<JSONValue>,
|
||||
schema: Omit<ToolMetadata, "parameters"> & {
|
||||
parameters: R;
|
||||
},
|
||||
): FunctionTool<z.infer<R>, JSONValue | Promise<JSONValue>>;
|
||||
static from<T, R extends z.ZodType<T>>(
|
||||
fn: (input: T) => JSONValue | Promise<JSONValue>,
|
||||
schema: Omit<ToolMetadata, "parameters"> & {
|
||||
@@ -40,15 +40,15 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
|
||||
): FunctionTool<T, JSONValue>;
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
static from(fn: any, schema: any): any {
|
||||
if (schema.parameters instanceof z.ZodSchema) {
|
||||
const jsonSchema = zodToJsonSchema(schema.parameters);
|
||||
if (schema.parameter instanceof z.ZodSchema) {
|
||||
const jsonSchema = zodToJsonSchema(schema.parameter);
|
||||
return new FunctionTool(
|
||||
fn,
|
||||
{
|
||||
...schema,
|
||||
parameters: jsonSchema,
|
||||
},
|
||||
schema.parameters,
|
||||
schema.parameter,
|
||||
);
|
||||
}
|
||||
return new FunctionTool(fn, schema);
|
||||
@@ -58,15 +58,7 @@ export class FunctionTool<T, R extends JSONValue | Promise<JSONValue>>
|
||||
return this.#metadata as BaseTool<T>["metadata"];
|
||||
}
|
||||
|
||||
call = (input: T) => {
|
||||
if (this.#zodType) {
|
||||
const result = this.#zodType.safeParse(input);
|
||||
if (result.success) {
|
||||
return this.#fn.call(null, result.data);
|
||||
} else {
|
||||
console.warn(result.error.errors);
|
||||
}
|
||||
}
|
||||
call(input: T) {
|
||||
return this.#fn.call(null, input);
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,8 +13,6 @@ export type StepFunction<T extends WorkflowEvent = WorkflowEvent> = (
|
||||
|
||||
type EventTypeParam = EventTypes | EventTypes[];
|
||||
|
||||
let once = false;
|
||||
|
||||
export class Workflow {
|
||||
#steps: Map<
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
@@ -31,20 +29,8 @@ export class Workflow {
|
||||
verbose?: boolean;
|
||||
timeout?: number;
|
||||
validate?: boolean;
|
||||
ignoreDeprecatedWarning?: boolean;
|
||||
} = {},
|
||||
) {
|
||||
if (!once && !params.ignoreDeprecatedWarning) {
|
||||
console.warn(
|
||||
"@llamaindex/core/workflow is going to use the new workflow API in the next major version.",
|
||||
"Please update your imports to @llamaindex/workflow",
|
||||
);
|
||||
console.warn(
|
||||
"See https://ts.llamaindex.ai/docs/llamaindex/guide/workflow for more information",
|
||||
);
|
||||
once = true;
|
||||
}
|
||||
|
||||
this.#verbose = params.verbose ?? false;
|
||||
this.#timeout = params.timeout ?? null;
|
||||
this.#validate = params.validate ?? false;
|
||||
|
||||
@@ -1,8 +0,0 @@
|
||||
{
|
||||
"type": "module",
|
||||
"main": "./dist/index.cjs",
|
||||
"module": "./dist/index.js",
|
||||
"types": "./dist/index.d.ts",
|
||||
"exports": "./dist/index.js",
|
||||
"private": true
|
||||
}
|
||||
@@ -1,8 +0,0 @@
|
||||
{
|
||||
"type": "module",
|
||||
"main": "./dist/index.cjs",
|
||||
"module": "./dist/index.js",
|
||||
"types": "./dist/index.d.ts",
|
||||
"exports": "./dist/index.js",
|
||||
"private": true
|
||||
}
|
||||
@@ -1,8 +0,0 @@
|
||||
{
|
||||
"type": "module",
|
||||
"main": "./dist/index.cjs",
|
||||
"module": "./dist/index.js",
|
||||
"types": "./dist/index.d.ts",
|
||||
"exports": "./dist/index.js",
|
||||
"private": true
|
||||
}
|
||||
@@ -1,5 +1,5 @@
|
||||
import { truncateMaxTokens } from "@llamaindex/core/embeddings";
|
||||
import { Tokenizers, tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { Tokenizers, tokenizers } from "@llamaindex/env";
|
||||
import { describe, expect, test } from "vitest";
|
||||
|
||||
describe("truncateMaxTokens", () => {
|
||||
|
||||
@@ -19,7 +19,7 @@ describe("ChatMemoryBuffer", () => {
|
||||
expect(buffer.tokenLimit).toBe(500);
|
||||
});
|
||||
|
||||
test("getMessages returns all messages when under token limit", async () => {
|
||||
test("getMessages returns all messages when under token limit", () => {
|
||||
const messages: ChatMessage[] = [
|
||||
{ role: "user", content: "Hello" },
|
||||
{ role: "assistant", content: "Hi there!" },
|
||||
@@ -30,11 +30,11 @@ describe("ChatMemoryBuffer", () => {
|
||||
chatHistory: messages,
|
||||
});
|
||||
|
||||
const result = await buffer.getMessages();
|
||||
const result = buffer.getMessages();
|
||||
expect(result).toEqual(messages);
|
||||
});
|
||||
|
||||
test("getMessages truncates messages when over token limit", async () => {
|
||||
test("getMessages truncates messages when over token limit", () => {
|
||||
const messages: ChatMessage[] = [
|
||||
{ role: "user", content: "This is a long message" },
|
||||
{ role: "assistant", content: "This is also a long reply" },
|
||||
@@ -45,11 +45,11 @@ describe("ChatMemoryBuffer", () => {
|
||||
chatHistory: messages,
|
||||
});
|
||||
|
||||
const result = await buffer.getMessages();
|
||||
const result = buffer.getMessages();
|
||||
expect(result).toEqual([{ role: "user", content: "Short" }]);
|
||||
});
|
||||
|
||||
test("getMessages handles input messages", async () => {
|
||||
test("getMessages handles input messages", () => {
|
||||
const storedMessages: ChatMessage[] = [
|
||||
{ role: "user", content: "Hello" },
|
||||
{ role: "assistant", content: "Hi there!" },
|
||||
@@ -62,13 +62,13 @@ describe("ChatMemoryBuffer", () => {
|
||||
const inputMessages: ChatMessage[] = [
|
||||
{ role: "user", content: "New message" },
|
||||
];
|
||||
const result = await buffer.getMessages(inputMessages);
|
||||
const result = buffer.getMessages(inputMessages);
|
||||
expect(result).toEqual([...inputMessages, ...storedMessages]);
|
||||
});
|
||||
|
||||
test("getMessages throws error when initial token count exceeds limit", () => {
|
||||
const buffer = new ChatMemoryBuffer({ tokenLimit: 10 });
|
||||
expect(async () => buffer.getMessages(undefined, 20)).rejects.toThrow(
|
||||
expect(() => buffer.getMessages(undefined, 20)).toThrow(
|
||||
"Initial token count exceeds token limit",
|
||||
);
|
||||
});
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { SentenceSplitter } from "@llamaindex/core/node-parser";
|
||||
import { Document } from "@llamaindex/core/schema";
|
||||
import { tokenizers } from "@llamaindex/env/tokenizers";
|
||||
import { tokenizers } from "@llamaindex/env";
|
||||
import { beforeEach, describe, expect, test } from "vitest";
|
||||
|
||||
describe("SentenceSplitter", () => {
|
||||
|
||||
@@ -7,6 +7,6 @@
|
||||
},
|
||||
"devDependencies": {
|
||||
"@llamaindex/core": "workspace:*",
|
||||
"vitest": "^2.1.4"
|
||||
"vitest": "^2.0.5"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8,6 +8,7 @@
|
||||
"moduleResolution": "Bundler",
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"lib": ["ESNext", "DOM", "DOM.AsyncIterable"],
|
||||
"types": ["node"]
|
||||
},
|
||||
"include": ["./src"],
|
||||
|
||||
Vendored
-27
@@ -1,32 +1,5 @@
|
||||
# @llamaindex/env
|
||||
|
||||
## 0.1.20
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 4fc001c: chore: bump `@huggingface/transformers`
|
||||
|
||||
Upgrade to v3, please read https://github.com/huggingface/transformers.js/releases/tag/3.0.0 for more information.
|
||||
|
||||
## 0.1.19
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- ad85bd0: - fix agent chat message not saved into the task context when streaming
|
||||
- fix async local storage might use `node:async_hook` in edge-light/workerd condition
|
||||
|
||||
## 0.1.18
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- a8d3fa6: fix: exports in package.json
|
||||
|
||||
## 0.1.17
|
||||
|
||||
### Patch Changes
|
||||
|
||||
- 14cc9eb: chore: move multi-model into single sub module
|
||||
|
||||
## 0.1.16
|
||||
|
||||
### Patch Changes
|
||||
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"type": "module",
|
||||
"main": "./dist/index.cjs",
|
||||
"module": "./dist/index.js",
|
||||
"types": "./dist/index.d.ts",
|
||||
"exports": {
|
||||
"browser": "./dist/index.browser.js",
|
||||
"edge-light": "./dist/index.edge-light.js",
|
||||
"workerd": "./dist/index.workerd.js"
|
||||
},
|
||||
"private": true
|
||||
}
|
||||
Vendored
+9
-63
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"name": "@llamaindex/env",
|
||||
"description": "environment wrapper, supports all JS environment including node, deno, bun, edge runtime, and cloudflare worker",
|
||||
"version": "0.1.20",
|
||||
"version": "0.1.16",
|
||||
"type": "module",
|
||||
"types": "dist/index.d.ts",
|
||||
"module": "dist/index.js",
|
||||
@@ -28,7 +28,7 @@
|
||||
"types": "./dist/index.d.ts",
|
||||
"import": "./dist/index.js",
|
||||
"require": "./dist/index.cjs",
|
||||
"default": "./dist/index.js"
|
||||
"default": "./dist/index.cjs"
|
||||
},
|
||||
"workerd": {
|
||||
"types": "./dist/index.workerd.d.ts",
|
||||
@@ -50,63 +50,9 @@
|
||||
"types": "./dist/index.d.cts",
|
||||
"default": "./dist/index.cjs"
|
||||
}
|
||||
},
|
||||
"./tokenizers": {
|
||||
"workerd": {
|
||||
"types": "./tokenizers/dist/index.workerd.d.ts",
|
||||
"default": "./tokenizers/dist/index.workerd.js"
|
||||
},
|
||||
"edge-light": {
|
||||
"types": "./tokenizers/dist/index.edge-light.d.ts",
|
||||
"default": "./tokenizers/dist/index.edge-light.js"
|
||||
},
|
||||
"browser": {
|
||||
"types": "./tokenizers/dist/index.browser.d.ts",
|
||||
"default": "./tokenizers/dist/index.browser.js"
|
||||
},
|
||||
"import": {
|
||||
"types": "./tokenizers/dist/index.d.ts",
|
||||
"default": "./tokenizers/dist/index.js"
|
||||
},
|
||||
"require": {
|
||||
"types": "./tokenizers/dist/index.d.cts",
|
||||
"default": "./tokenizers/dist/index.cjs"
|
||||
},
|
||||
"default": {
|
||||
"types": "./tokenizers/dist/index.d.ts",
|
||||
"default": "./tokenizers/dist/index.js"
|
||||
}
|
||||
},
|
||||
"./multi-model": {
|
||||
"workerd": {
|
||||
"types": "./multi-model/dist/index.workerd.d.ts",
|
||||
"default": "./multi-model/dist/index.workerd.js"
|
||||
},
|
||||
"edge-light": {
|
||||
"types": "./multi-model/dist/index.edge-light.d.ts",
|
||||
"default": "./multi-model/dist/index.edge-light.js"
|
||||
},
|
||||
"browser": {
|
||||
"types": "./multi-model/dist/index.browser.d.ts",
|
||||
"default": "./multi-model/dist/index.browser.js"
|
||||
},
|
||||
"import": {
|
||||
"types": "./multi-model/dist/index.d.ts",
|
||||
"default": "./multi-model/dist/index.js"
|
||||
},
|
||||
"require": {
|
||||
"types": "./multi-model/dist/index.d.cts",
|
||||
"default": "./multi-model/dist/index.cjs"
|
||||
},
|
||||
"default": {
|
||||
"types": "./multi-model/dist/index.d.ts",
|
||||
"default": "./multi-model/dist/index.js"
|
||||
}
|
||||
}
|
||||
},
|
||||
"files": [
|
||||
"tokenizers",
|
||||
"multi-model",
|
||||
"dist",
|
||||
"CHANGELOG.md",
|
||||
"!**/*.tsbuildinfo"
|
||||
@@ -122,17 +68,17 @@
|
||||
"test": "vitest"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^22.9.0",
|
||||
"@types/node": "^22.8.4",
|
||||
"@types/readable-stream": "^4.0.15",
|
||||
"@huggingface/transformers": "^3.0.2",
|
||||
"bunchee": "5.6.1",
|
||||
"gpt-tokenizer": "^2.6.0",
|
||||
"@xenova/transformers": "^2.17.2",
|
||||
"bunchee": "5.5.1",
|
||||
"gpt-tokenizer": "^2.5.0",
|
||||
"pathe": "^1.1.2",
|
||||
"vitest": "^2.1.4"
|
||||
"vitest": "^2.0.5"
|
||||
},
|
||||
"peerDependencies": {
|
||||
"@aws-crypto/sha256-js": "^5.2.0",
|
||||
"@huggingface/transformers": "^3.0.2",
|
||||
"@xenova/transformers": "^2.17.2",
|
||||
"gpt-tokenizer": "^2.5.0",
|
||||
"js-tiktoken": "^1.0.12",
|
||||
"pathe": "^1.1.2"
|
||||
@@ -141,7 +87,7 @@
|
||||
"@aws-crypto/sha256-js": {
|
||||
"optional": true
|
||||
},
|
||||
"@huggingface/transformers": {
|
||||
"@xenova/transformers": {
|
||||
"optional": true
|
||||
},
|
||||
"pathe": {
|
||||
|
||||
Vendored
-1
@@ -1 +0,0 @@
|
||||
export { AsyncLocalStorage } from "node:async_hooks";
|
||||
-3
@@ -1,3 +0,0 @@
|
||||
// Async Local Storage is available cross different JS runtimes
|
||||
// @ts-expect-error AsyncLocalStorage is not defined in Non Node.js environment
|
||||
export const AsyncLocalStorage = globalThis.AsyncLocalStorage;
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user