This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Development Commands
This project uses pnpm as the package manager and Turbo for build orchestration:
-`pnpm install` - Install all dependencies
-`pnpm build` - Build all packages using Turbo
-`pnpm dev` - Start development mode for all packages
-`pnpm test` - Run all unit tests
-`pnpm e2e` - Run end-to-end tests
-`pnpm lint` - Run ESLint across all packages
-`pnpm type-check` - Run TypeScript type checking across workspace
-`pnpm format` - Check code formatting with Prettier
-`pnpm format:write` - Auto-fix formatting issues
-`pnpm circular-check` - Check for circular dependencies using madge
For individual package development:
-`turbo run build --filter="@llamaindex/core"` - Build specific package
-`turbo run test --filter="@llamaindex/core"` - Test specific package
- Navigate to specific package directory and run `pnpm test` for focused testing
-`pnpm clean` - Remove all build artifacts and node_modules across workspace
## Architecture Overview
LlamaIndex.TS is a TypeScript data framework for LLM applications organized as a pnpm monorepo with multiple runtime environment support (Node.js, Deno, Bun, Vercel Edge, Cloudflare Workers).
### Package Structure
**Core Packages:**
-`packages/core/` - Abstract base classes and interfaces for all runtime environments
-`packages/llamaindex/` - Main package that aggregates core functionality
-`packages/env/` - Environment-specific compatibility layers for different JS runtimes
**Provider Packages (`packages/providers/`):**
- LLM providers: `openai/`, `anthropic/`, `ollama/`, `google/`, `groq/`, etc.
- Vector stores: `storage/pinecone/`, `storage/chroma/`, `storage/qdrant/`, etc.
- Embeddings: Various embedding providers integrated within LLM packages
- Readers: `assemblyai/`, `discord/`, `notion/` for data ingestion
**Specialized Packages:**
-`packages/cloud/` - LlamaCloud integration for managed services
-`packages/tools/` - Function calling tools and utilities
-`packages/readers/` - File format readers (PDF, DOCX, etc.)
### Key Architectural Patterns
**Runtime Abstraction:** Core functionality is runtime-agnostic, with environment-specific implementations in separate entry points (`index.ts`, `index.edge.ts`, `index.workerd.ts`).
**Provider Pattern:** LLMs, embeddings, and vector stores implement common interfaces from `@llamaindex/core`, allowing easy swapping between providers.
**Modular Design:** Each provider is a separate package to minimize bundle size - users install only what they need.
- **Agents and Workflows:** Abstractions for building agentic workflows and agents in `packages/workflow`
- **Chat Engines:** Conversational interfaces in `core/chat-engine/`
- **Query Engines:** Document querying with retrieval in `core/query-engine/`
- **Indices:** VectorStoreIndex, SummaryIndex, KeywordTable in `llamaindex/indices/`
- **Node Parsers:** Text splitting and chunking in `core/node-parser/`
- **Ingestion Pipeline:** Document processing workflows in `llamaindex/ingestion/`
- **Storage:** Chat stores, document stores, index stores, and KV stores in `core/storage/`
### Deprecated Components
- **Agents:** ReAct and function calling agents in `core/agent/` and `llamaindex/agent/`
### Testing Structure
- Unit tests in each package's `tests/` directory
- E2E tests in `e2e/` directory with runtime-specific examples
- Tests depend on build artifacts, so always run `pnpm build` before testing
### Multi-Runtime Support
The codebase supports multiple JavaScript runtimes through conditional exports and separate entry points. When making changes, consider compatibility across Node.js, Deno, Bun, and edge runtimes.
### Development Notes
- The project uses Husky for git hooks with lint-staged for pre-commit formatting and linting
- All packages use bunchee for building with dual CJS/ESM support
- Core package exports are organized as sub-modules (e.g., `@llamaindex/core/llms`, `@llamaindex/core/embeddings`)
- Always run `pnpm build` before running tests, as tests depend on build artifacts
Right now, for first-time contributors, these three packages are of the highest importance:
We recommend you to understand the basics of Node.js, TypeScript, pnpm, and of course, LLM before contributing.
-`packages/llamaindex` which is the main NPM library `llamaindex`
-`examples` is where the demo code lives
-`apps/docs` is where the code for the documentation of https://ts.llamaindex.ai/ is located
There are some important folders in the repository:
### Turborepo docs
You can checkout how Turborepo works using the default [README-turborepo.md](/README-turborepo.md)
-`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...
-`providers/*`: The providers package of LlamaIndex.TS, which contains the providers for LLM and other services.
-`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.
## Getting Started
Install NodeJS. Preferably v18 using nvm or n.
Inside the LlamaIndexTS directory:
Make sure you have Node.js LTS (Long-term Support) installed. You can check your Node.js version by running:
```shell
node -v
# v22.x.x
```
npm i -g pnpm ts-node
### Use pnpm
```shell
npm install -g pnpm
```
### Install dependencies
```shell
pnpm install
pnpm install -g tsx
```
Note: we use pnpm in this repo, which has a lot of the same functionality and CLI options as npm but it does do some things better in a monorepo, like centralizing dependencies and caching.
### Build the packages
PNPM's has documentation on its [workspace feature](https://pnpm.io/workspaces) and Turborepo had some [useful documentation also](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks).
To build all packages, run:
### Running Typescript
When we publish to NPM we will have a tsc compiled version of the library in JS. For now, the easiest thing to do is use ts-node.
### Test cases
To run them, run
```
pnpm run test
```shell
pnpm build
```
To write new test cases write them in [packages/llamaindex/tests](/packages/llamaindex/tests)
### Start Developing
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
You can launch the package in dev-mode by running:
### 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]
```shell
pnpm dev
```
To install packages for every package or application run
This will use turbo to run all packages in watch-mode. This means you can make changes and have them automatically built.
If you want to customize what packages are built/watched, you can run turbo directly and adjust the filter:
```shell
pnpm turbo run dev --filter="./packages/core" --concurrency=100
```
pnpm add -w [NPM Package]
In another terminal, you can write and run any script needed to quickly test your changes. For example:
"The user is a software engineer who loves TypeScript and LlamaIndex.",
messageRole:"system",
}),
],
});
asyncfunctionmain() {
constresult=awaitmemory.getLLM();
console.log(result);
}
voidmain().catch(console.error);
```
And run it with:
```shell
pnpm exec tsx my_script.ts
```
This flow allows you to easily test your changes without having to build the entire project.
Once you are happy with your changes, be sure to add tests (and confirm existing tests are passing!).
### Run tests
#### Unit tests
After build, to run all unit tests, call:
```shell
pnpm test
```
Unit tests are located in the `tests` folder of each package. They are using their own package (e.g. `@llamaindex/core-tests` for `@llamaindex/core`). The tests are importing the package under test and the test package is not published.
#### E2E tests
To run all E2E tests, call:
```shell
pnpm e2e
```
All E2E tests are in the `e2e` folder.
### Docs
To contribute to the docs, go to the docs website folder and run the Docusaurus instance.
See the [docs](./apps/next/README.md) for more information.
```bash
cd apps/docs
pnpm install
pnpm start
```
## Adding a new package
That should start a webserver which will serve the docs on https://localhost:3000
Please follow these steps to add a new package:
Any changes you make should be reflected in the browser. If you need to regenerate the API docs and find that your TSDoc isn't getting the updates, feel free to remove apps/docs/api. It will automatically regenerate itself when you run pnpm start again.
1. Only add new packages to the `packages/providers` folder.
2. Use the `package.json` and `tsconfig.json` of an existing packages as template.
3. Reference your new package in the root `tsconfig.json` file
4. Add your package to the `examples/package.json` file if you add a new example.
## Changeset
## Before sending a PR
We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new changeset, run in the root folder:
Before sending a PR, make sure of the following:
```
1. Tests are all running and you added meaningful tests for your change.
2. If you have a new feature, document it in the `apps/next` docs folder.
3. If you have a new feature, add a new example in the `examples` folder.
4. You have a descriptive changeset for each PR:
### Bumping the versions of packages you've modified
We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
changeset, run in the root folder:
```shell
pnpm changeset
```
Please send a descriptive changeset for each PR.
You will be prompted to choose what packages need their versions bumped, and what kind of bump (major, minor or patch) is needed. Once you carry out this operation, the bumping will be automatic after the PR is merged.
## Publishing (maintainers only)
@@ -95,6 +160,6 @@ 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.
LlamaIndex is a data framework for your LLM application.
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in JS runtime environments with TypeScript support.
Documentation: https://ts.llamaindex.ai/
@@ -19,17 +24,36 @@ Try examples online:
LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.
For now, browser support is limited due to the lack of support for [AsyncLocalStorage-like APIs](https://github.com/tc39/proposal-async-context)
### Supported LLMs:
- OpenAI LLms
- Anthropic LLms
- Groq LLMs
- Llama2, Llama3, Llama3.1 LLMs
- MistralAI LLMs
- Fireworks LLMs
- DeepSeek LLMs
- ReplicateAI LLMs
- TogetherAI LLMs
- HuggingFace LLms
- DeepInfra LLMs
- Gemini LLMs
## Getting started
```shell
@@ -38,172 +62,20 @@ pnpm install llamaindex
yarn add llamaindex
```
### Setup TypeScript
### Setup in Node.js, Deno, Bun, TypeScript...?
```json5
{
compilerOptions: {
// ⬇️ add this line to your tsconfig.json
moduleResolution: "bundler", // or "node16"
},
}
```
See our official document: https://ts.llamaindex.ai/docs/llamaindex/getting_started
<details>
<summary>Why?</summary>
We are shipping both ESM and CJS module, and compatible with Vercel Edge, Cloudflare Workers, and other serverless platforms.
### Adding provider packages
So we are using [conditional exports](https://nodejs.org/api/packages.html#conditional-exports) to support all environments.
In most cases, you'll also need to install provider packages to use LlamaIndexTS. These are for adding AI models, file readers for ingestion or storing documents, e.g. in vector databases.
This is a kind of modern way of shipping packages, but might cause TypeScript type check to fail because of legacy module resolution.
For example, to use the OpenAI LLM, you would install the following package:
Imaging you put output file into `/dist/openai.js` but you are importing `llamaindex/openai` in your code, and set `package.json` like this:
```json
{
"exports":{
"./openai":"./dist/openai.js"
}
}
```
In old module resolution, TypeScript will not be able to find the module because it is not follow the file structure, even you run `node index.js` successfully. (on Node.js >=16)
See more about [moduleResolution](https://www.typescriptlang.org/docs/handbook/modules/theory.html#module-resolution) or
We have some wasm dependencies for better performance. You can use `vite-plugin-wasm` to load them.
```ts
importwasmfrom"vite-plugin-wasm";
exportdefault{
plugins:[wasm()],
ssr:{
external:["tiktoken"],
},
};
```shell
npm install @llamaindex/openai
pnpm install @llamaindex/openai
yarn add @llamaindex/openai
```
## Playground
@@ -212,71 +84,13 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou
## Core concepts for getting started:
- [Document](/packages/llamaindex/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
- [Node](/packages/llamaindex/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
- [Embedding](/packages/llamaindex/src/embeddings/OpenAIEmbedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that question. Because the default service context is OpenAI, the default embedding is `OpenAIEmbedding`. If using different models, say through Ollama, use this [Embedding](/packages/llamaindex/src/embeddings/OllamaEmbedding.ts) (see all [here](/packages/llamaindex/src/embeddings)).
- [Indices](/packages/llamaindex/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
- [QueryEngine](/packages/llamaindex/src/engines/query/RetrieverQueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query. To build a query engine from your Index (recommended), use the [`asQueryEngine`](/packages/llamaindex/src/indices/BaseIndex.ts) method on your Index. See all query engines [here](/packages/llamaindex/src/engines/query).
- [ChatEngine](/packages/llamaindex/src/engines/chat/SimpleChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices. See all chat engines [here](/packages/llamaindex/src/engines/chat).
- [SimplePrompt](/packages/llamaindex/src/Prompt.ts): A simple standardized function call definition that takes in inputs and formats them in a template literal. SimplePrompts can be specialized using currying and combined using other SimplePrompt functions.
## Tips when using in non-Node.js environments
When you are importing `llamaindex` in a non-Node.js environment(such as React Server Components, Cloudflare Workers, etc.)
Some classes are not exported from top-level entry file.
The reason is that some classes are only compatible with Node.js runtime,(e.g. `PDFReader`) which uses Node.js specific APIs(like `fs`, `child_process`, `crypto`).
If you need any of those classes, you have to import them instead directly though their file path in the package.
Here's an example for importing the `PineconeVectorStore` class:
import CodeSource from "!raw-loader!../../../../examples/chatEngine";
# Chat Engine
Chat Engine is a class that allows you to create a chatbot from a retriever. It is a wrapper around a retriever that allows you to chat with it in a conversational manner.
import CodeSource from "!raw-loader!../../../../examples/mistral";
# Using other LLM APIs
By default LlamaIndex.TS uses OpenAI's LLMs and embedding models, but we support [lots of other LLMs](../modules/llms) including models from Mistral (Mistral, Mixtral), Anthropic (Claude) and Google (Gemini).
If you don't want to use an API at all you can [run a local model](../../examples/local_llm)
## Using another LLM
You can specify what LLM LlamaIndex.TS will use on the `Settings` object, like this:
```typescript
import { MistralAI, Settings } from "llamaindex";
Settings.llm = new MistralAI({
model: "mistral-tiny",
apiKey: "<YOUR_API_KEY>",
});
```
You can see examples of other APIs we support by checking out "Available LLMs" in the sidebar of our [LLMs section](../modules/llms).
## Using another embedding model
A frequent gotcha when trying to use a different API as your LLM is that LlamaIndex will also by default index and embed your data using OpenAI's embeddings. To completely switch away from OpenAI you will need to set your embedding model as well, for example:
```typescript
import { MistralAIEmbedding, Settings } from "llamaindex";
Settings.embedModel = new MistralAIEmbedding();
```
We support [many different embeddings](../modules/embeddings).
## Full example
This example uses Mistral's `mistral-tiny` model as the LLM and Mistral for embeddings as well.
We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
## NextJS
If you're using NextJS you'll need to add `withLlamaIndex` to your `next.config.js` file. This will add the necessary configuration for included 3rd-party libraries to your build:
```js
// next.config.js
constwithLlamaIndex=require("llamaindex/next");
module.exports=withLlamaIndex({
// your next.js config
});
```
For details, check the latest [withLlamaIndex](https://github.com/run-llama/LlamaIndexTS/blob/main/packages/llamaindex/src/next.ts) implementation.
We support Node.JS versions 18, 20 and 22, with experimental support for Deno, Bun and Vercel Edge functions.
## Installation from NPM
```bash npm2yarn
npm install llamaindex
```
### Environment variables
Our examples use OpenAI by default. You can use [other LLMs](../examples/other_llms) via their APIs; if you would prefer to use local models check out our [local LLM example](../examples/local_llm).
To use OpenAI, you'll need to [get an OpenAI API key](https://platform.openai.com/account/api-keys) and then make it available as an environment variable this way:
```bash
export OPENAI_API_KEY="sk-......" # Replace with your key
```
If you want to have it automatically loaded every time, add it to your `.zshrc/.bashrc`.
**WARNING:** do not check in your OpenAI key into version control. GitHub automatically invalidates OpenAI keys checked in by accident.
## What next?
- The easiest way to started is to [build a full-stack chat app with `create-llama`](starter_tutorial/chatbot).
- Try our other [getting started tutorials](starter_tutorial/retrieval_augmented_generation)
- Learn more about the [high level concepts](concepts) behind how LlamaIndex works
- Check out our [many examples](../examples/more_examples) of LlamaIndex.TS in action
import CodeSource from "!raw-loader!../../../../../examples/agent/openai";
# Agent tutorial
We have a comprehensive, step-by-step [guide to building agents in LlamaIndex.TS](../../guides/agents/setup) that we recommend to learn what agents are and how to build them for production. But building a basic agent is simple:
## Set up
In a new folder:
```bash npm2yarn
npm init
npm install -D typescript @types/node
```
## Run agent
Create the file `example.ts`. This code will:
- Create two tools for use by the agent:
- A `sumNumbers` tool that adds two numbers
- A `divideNumbers` tool that divides numbers
-
- Give an example of the data structure we wish to generate
- Prompt the LLM with instructions and the example, plus a sample transcript
<CodeBlock language="ts">{CodeSource}</CodeBlock>
To run the code:
```bash
npx tsx example.ts
```
You should expect output something like:
```
{
content: 'The sum of 5 + 5 is 10. When you divide 10 by 2, you get 5.',
import CodeSource from "!raw-loader!../../../../../examples/jsonExtract";
# Structured data extraction tutorial
Make sure you have installed LlamaIndex.TS and have an OpenAI key. If you haven't, check out the [installation](../installation) guide.
You can use [other LLMs](../../examples/other_llms) via their APIs; if you would prefer to use local models check out our [local LLM example](../../examples/local_llm).
## Set up
In a new folder:
```bash npm2yarn
npm init
npm install -D typescript @types/node
```
## Extract data
Create the file `example.ts`. This code will:
- Set up an LLM connection to GPT-4
- Give an example of the data structure we wish to generate
- Prompt the LLM with instructions and the example, plus a sample transcript
<CodeBlock language="ts">{CodeSource}</CodeBlock>
To run the code:
```bash
npx tsx example.ts
```
You should expect output something like:
```json
{
"summary": "Sarah from XYZ Company called John to introduce the XYZ Widget, a tool designed to automate tasks and improve productivity. John expressed interest and requested case studies and a product demo. Sarah agreed to send the information and follow up to schedule the demo.",
"products": ["XYZ Widget"],
"rep_name": "Sarah",
"prospect_name": "John",
"action_items": [
"Send case studies and additional product information to John",
We want to use `await` so we're going to wrap all of our code in a `main` function, like this:
```typescript
// Your imports go here
async function main() {
// the rest of your code goes here
}
main().catch(console.error);
```
For the rest of this guide we'll assume your code is wrapped like this so we can use `await`. You can run the code this way:
```bash
npx tsx example.ts
```
### Load your dependencies
First we'll need to pull in our dependencies. These are:
- The OpenAI class to use the OpenAI LLM
- FunctionTool to provide tools to our agent
- OpenAIAgent to create the agent itself
- Settings to define some global settings for the library
- Dotenv to load our API key from the .env file
```javascript
import { OpenAI, FunctionTool, OpenAIAgent, Settings } from "llamaindex";
import "dotenv/config";
```
### Initialize your LLM
We need to tell our OpenAI class where its API key is, and which of OpenAI's models to use. We'll be using `gpt-4o`, which is capable while still being pretty cheap. This is a global setting, so anywhere an LLM is needed will use the same model.
```javascript
Settings.llm = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
model: "gpt-4o",
});
```
### Turn on logging
We want to see what our agent is up to, so we're going to hook into some events that the library generates and print them out. There are several events possible, but we'll specifically tune in to `llm-tool-call` (when a tool is called) and `llm-tool-result` (when it responds).
We're going to create a very simple function that adds two numbers together. This will be the tool we ask our agent to use.
```javascript
const sumNumbers = ({ a, b }) => {
return `${a + b}`;
};
```
Note that we're passing in an object with two named parameters, `a` and `b`. This is a little unusual, but important for defining a tool that an LLM can use.
### Turn the function into a tool for the agent
This is the most complicated part of creating an agent. We need to define a `FunctionTool`. We have to pass in:
- The function itself (`sumNumbers`)
- A name for the function, which the LLM will use to call it
- A description of the function. The LLM will read this description to figure out what the tool does, and if it needs to call it
- A schema for function. We tell the LLM that the parameter is an `object`, and we tell it about the two named parameters we gave it, `a` and `b`. We describe each parameter as a `number`, and we say that both are required.
- You can see [more examples of function schemas](https://cookbook.openai.com/examples/how_to_call_functions_with_chat_models).
```javascript
const tool = FunctionTool.from(sumNumbers, {
name: "sumNumbers",
description: "Use this function to sum two numbers",
parameters: {
type: "object",
properties: {
a: {
type: "number",
description: "First number to sum",
},
b: {
type: "number",
description: "Second number to sum",
},
},
required: ["a", "b"],
},
});
```
We then wrap up the tools into an array. We could provide lots of tools this way, but for this example we're just using the one.
```javascript
const tools = [tool];
```
### Create the agent
With your LLM already set up and your tools defined, creating an agent is simple:
```javascript
const agent = new OpenAIAgent({ tools });
```
### Ask the agent a question
We can use the `chat` interface to ask our agent a question, and it will use the tools we've defined to find an answer.
```javascript
let response = await agent.chat({
message: "Add 101 and 303",
});
console.log(response);
```
Let's see what running this looks like using `npx tsx agent.ts`
We're seeing two pieces of output here. The first is our callback firing when the tool is called. You can see in `toolResult` that the LLM has correctly passed `101` and `303` to our `sumNumbers` function, which adds them up and returns `404`.
The second piece of output is the response from the LLM itself, where the `message.content` key is giving us the answer.
Great! We've built an agent with tool use! Next you can:
- [See the full code](https://github.com/run-llama/ts-agents/blob/main/1_agent/agent.ts)
- [Switch to a local LLM](local_model)
- Move on to [add Retrieval-Augmented Generation to your agent](agentic_rag)
If you're happy using OpenAI, you can skip this section, but many people are interested in using models they run themselves. The easiest way to do this is via the great work of our friends at [Ollama](https://ollama.com/), who provide a simple to use client that will download, install and run a [growing range of models](https://ollama.com/library) for you.
### Install Ollama
They provide a one-click installer for Mac, Linux and Windows on their [home page](https://ollama.com/).
### Pick and run a model
Since we're going to be doing agentic work, we'll need a very capable model, but the largest models are hard to run on a laptop. We think `mixtral 8x7b` is a good balance between power and resources, but `llama3` is another great option. You can run it simply by running
```bash
ollama run mixtral:8x7b
```
The first time you run it will also automatically download and install the model for you.
### Switch the LLM in your code
There are two changes you need to make to the code we already wrote in `1_agent` to get Mixtral 8x7b to work. First, you need to switch to that model. Replace the call to `Settings.llm` with this:
```javascript
Settings.llm = new Ollama({
model: "mixtral:8x7b",
});
```
### Swap to a ReActAgent
In our original code we used a specific OpenAIAgent, so we'll need to switch to a more generic agent pattern, the ReAct pattern. This is simple: change the `const agent` line in your code to read
```javascript
const agent = new ReActAgent({ tools });
```
(You will also need to bring in `Ollama` and `ReActAgent` in your imports)
### Run your totally local agent
Because your embeddings were already local, your agent can now run entirely locally without making any API calls.
```bash
node agent.mjs
```
Note that your model will probably run a lot slower than OpenAI, so be prepared to wait a while!
**_Output_**
```javascript
{
response: {
message: {
role: 'assistant',
content: ' Thought: I need to use a tool to add the numbers 101 and 303.\n' +
'Action: sumNumbers\n' +
'Action Input: {"a": 101, "b": 303}\n' +
'\n' +
'Observation: 404\n' +
'\n' +
'Thought: I can answer without using any more tools.\n' +
'Answer: The sum of 101 and 303 is 404.'
},
raw: {
model: 'mixtral:8x7b',
created_at: '2024-05-09T00:24:30.339473Z',
message: [Object],
done: true,
total_duration: 64678371209,
load_duration: 57394551334,
prompt_eval_count: 475,
prompt_eval_duration: 4163981000,
eval_count: 94,
eval_duration: 3116692000
}
},
sources: [Getter]
}
```
Tada! You can see all of this in the folder `1a_mixtral`.
### Extending to other examples
You can use a ReActAgent instead of an OpenAIAgent in any of the further examples below, but keep in mind that GPT-4 is a lot more capable than Mixtral 8x7b, so you may see more errors or failures in reasoning if you are using an entirely local setup.
### Next steps
Now you've got a local agent, you can [add Retrieval-Augmented Generation to your agent](agentic_rag).
While an agent that can perform math is nifty (LLMs are usually not very good at math), LLM-based applications are always more interesting when they work with large amounts of data. In this case, we're going to use a 200-page PDF of the proposed budget of the city of San Francisco for fiscal years 2024-2024 and 2024-2025. It's a great example because it's extremely wordy and full of tables of figures, which present a challenge for humans and LLMs alike.
To learn more about RAG, we recommend this [introduction](https://docs.llamaindex.ai/en/stable/getting_started/concepts/) from our Python docs. We'll assume you know the basics:
- You need to parse your source data into chunks of text
- You need to encode that text as numbers, called embeddings
- You need to search your embeddings for the most relevant chunks of text
- You feed your relevant chunks and a query to an LLM to answer a question
We're going to start with the same agent we [built in step 1](https://github.com/run-llama/ts-agents/blob/main/1_agent/agent.ts), but make a few changes. You can find the finished version [in the repository](https://github.com/run-llama/ts-agents/blob/main/2_agentic_rag/agent.ts).
### New dependencies
We'll be bringing in `SimpleDirectoryReader`, `HuggingFaceEmbedding`, `VectorStoreIndex`, and `QueryEngineTool` from LlamaIndex.TS, as well as the dependencies we previously used.
```javascript
import {
OpenAI,
FunctionTool,
OpenAIAgent,
Settings,
SimpleDirectoryReader,
HuggingFaceEmbedding,
VectorStoreIndex,
QueryEngineTool,
} from "llamaindex";
```
### Add an embedding model
To encode our text into embeddings, we'll need an embedding model. We could use OpenAI for this but to save on API calls we're going to use a local embedding model from HuggingFace.
```javascript
Settings.embedModel = new HuggingFaceEmbedding({
modelType: "BAAI/bge-small-en-v1.5",
quantized: false,
});
```
### Load data using SimpleDirectoryReader
SimpleDirectoryReader is a flexible tool that can read a variety of file formats. We're going to point it at our data directory, which contains just the single PDF file, and get it to return a set of documents.
Now we turn our text into embeddings. The `VectorStoreIndex` class takes care of this for us when we use the `fromDocuments` method (it uses the embedding model we defined in `Settings` earlier).
```javascript
const index = await VectorStoreIndex.fromDocuments(documents);
```
### Configure a retriever
Before LlamaIndex can send a query to the LLM, it needs to find the most relevant chunks to send. That's the purpose of a `Retriever`. We're going to get `VectorStoreIndex` to act as a retriever for us
```javascript
const retriever = await index.asRetriever();
```
### Configure how many documents to retrieve
By default LlamaIndex will retrieve just the 2 most relevant chunks of text. This document is complex though, so we'll ask for more context.
```javascript
retriever.similarityTopK = 10;
```
### Create a query engine
And our final step in creating a RAG pipeline is to create a query engine that will use the retriever to find the most relevant chunks of text, and then use the LLM to answer the question.
```javascript
const queryEngine = await index.asQueryEngine({
retriever,
});
```
### Define the query engine as a tool
Just as before we created a `FunctionTool`, we're going to create a `QueryEngineTool` that uses our `queryEngine`.
```javascript
const tools = [
new QueryEngineTool({
queryEngine: queryEngine,
metadata: {
name: "san_francisco_budget_tool",
description: `This tool can answer detailed questions about the individual components of the budget of San Francisco in 2023-2024.`,
},
}),
];
```
As before, we've created an array of tools with just one tool in it. The metadata is slightly different: we don't need to define our parameters, we just give the tool a name and a natural-language description.
### Create the agent as before
Creating the agent and asking a question is exactly the same as before, but we'll ask a different question.
```javascript
// create the agent
const agent = new OpenAIAgent({ tools });
let response = await agent.chat({
message: "What's the budget of San Francisco in 2023-2024?",
});
console.log(response);
```
Once again we'll run `npx tsx agent.ts` and see what we get:
**_Output_**
```javascript
{
toolCall: {
id: 'call_iNo6rTK4pOpOBbO8FanfWLI9',
name: 'san_francisco_budget_tool',
input: { query: 'total budget' }
},
toolResult: {
tool: QueryEngineTool {
queryEngine: [RetrieverQueryEngine],
metadata: [Object]
},
input: { query: 'total budget' },
output: 'The total budget for the City and County of San Francisco for Fiscal Year (FY) 2023-24 is $14.6 billion, which represents a $611.8 million, or 4.4 percent, increase over the FY 2022-23 budget. For FY 2024-25, the total budget is also projected to be $14.6 billion, reflecting a $40.5 million, or 0.3 percent, decrease from the FY 2023-24 proposed budget. This budget includes various expenditures across different departments and services, with significant allocations to public works, transportation, commerce, public protection, and health services.',
isError: false
}
}
```
```javascript
{
response: {
raw: {
id: 'chatcmpl-9KxUkwizVCYCmxwFQcZFSHrInzNFU',
object: 'chat.completion',
created: 1714782286,
model: 'gpt-4-turbo-2024-04-09',
choices: [Array],
usage: [Object],
system_fingerprint: 'fp_ea6eb70039'
},
message: {
content: "The total budget for the City and County of San Francisco for the fiscal year 2023-2024 is $14.6 billion. This represents a $611.8 million, or 4.4 percent, increase over the previous fiscal year's budget. The budget covers various expenditures across different departments and services, including significant allocations to public works, transportation, commerce, public protection, and health services.",
role: 'assistant',
options: {}
}
},
sources: [Getter]
}
```
Once again we see a `toolResult`. You can see the query the LLM decided to send to the query engine ("total budget"), and the output the engine returned. In `response.message` you see that the LLM has returned the output from the tool almost verbatim, although it trimmed out the bit about 2024-2025 since we didn't ask about that year.
So now we have an agent that can index complicated documents and answer questions about them. Let's [combine our math agent and our RAG agent](rag_and_tools)!
LlamaIndex is a framework for building LLM-powered applications. LlamaIndex helps you ingest, structure, and access private or domain-specific data. It's available [as a Python package](https://docs.llamaindex.ai/en/stable/) and in TypeScript (this package). LlamaIndex.TS offers the core features of LlamaIndex for popular runtimes like Node.js (official support), Vercel Edge Functions (experimental), and Deno (experimental).
## 🚀 Why LlamaIndex.TS?
LLMs offer a natural language interface between humans and inferred data. Widely available models come pre-trained on huge amounts of publicly available data, from Wikipedia and mailing lists to textbooks and source code.
Applications built on top of LLMs often require augmenting these models with private or domain-specific data. That data is often distributed across siloed applications and data stores. It's behind APIs, in SQL databases, or trapped in PDFs and slide decks.
LlamaIndex.TS helps you unlock that data and then build powerful applications with it.
## 🦙 What is LlamaIndex for?
LlamaIndex.TS handles several major use cases:
- **Structured Data Extraction**: turning complex, unstructured and semi-structured data into uniform, programmatically accessible formats.
- **Retrieval-Augmented Generation (RAG)**: answering queries across your internal data by providing LLMs with up-to-date, semantically relevant context including Question and Answer systems and chat bots.
- **Autonomous Agents**: building software that is capable of intelligently selecting and using tools to accomplish tasks in an interactive, unsupervised manner.
## 👨👩👧👦 Who is LlamaIndex for?
LlamaIndex targets the "AI Engineer": developers building software in any domain that can be enhanced by LLM-powered functionality, without needing to be an expert in machine learning or natural language processing.
Our high-level API allows beginner users to use LlamaIndex.TS to ingest, index, and query their data in just a few lines of code.
For more complex applications, our lower-level APIs allow advanced users to customize and extend any module—data connectors, indices, retrievers, and query engines, to fit their needs.
## Getting Started
`npm install llamaindex`
Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter_tutorial/retrieval_augmented_generation.mdx) to build your first application.
Once you're up and running, [High-Level Concepts](./getting_started/concepts.md) has an overview of LlamaIndex's modular architecture. For more hands-on practical examples, look through our Examples section on the sidebar.
import CodeSource from "!raw-loader!../../../../../examples/readers/src/simple-directory-reader";
import CodeSource2 from "!raw-loader!../../../../../examples/readers/src/custom-simple-directory-reader";
# Loader
Before you can start indexing your documents, you need to load them into memory.
All "basic" data loaders can be seen below, mapped to their respective filetypes in `SimpleDirectoryReader`. More loaders are shown in the sidebar on the left.
Additionally the following loaders exist without separate documentation:
- `AssemblyAIReader` transcribes audio using [AssemblyAI](https://www.assemblyai.com/).
- [AudioTranscriptReader](../../api/classes/AudioTranscriptReader.md): loads entire transcript as a single document.
- [AudioTranscriptParagraphsReader](../../api/classes/AudioTranscriptParagraphsReader.md): creates a document per paragraph.
- [AudioTranscriptSentencesReader](../../api/classes/AudioTranscriptSentencesReader.md): creates a document per sentence.
- [AudioSubtitlesReader](../../api/classes/AudioTranscriptParagraphsReader.md): creates a document containing the subtitles of a transcript.
- [SimpleMongoReader](../../api/classes/SimpleMongoReader) loads data from a [MongoDB](https://www.mongodb.com/).
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
## SimpleDirectoryReader
[](https://stackblitz.com/github/run-llama/LlamaIndexTS/tree/main/examples/readers?file=src/simple-directory-reader.ts&title=Simple%20Directory%20Reader)
LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class.
It is a simple reader that reads all files from a directory and its subdirectories.
<CodeBlock language="ts">{CodeSource}</CodeBlock>
Currently, the following readers are mapped to specific file types:
- `overrideReader` overrides the reader for all file types, including unsupported ones.
- `fileExtToReader` maps a reader to a specific file type. Can override reader for existing file types or add support for new file types.
- `defaultReader` sets a fallback reader for files with unsupported extensions. By default it is `TextFileReader`.
SimpleDirectoryReader supports up to 9 concurrent requests. Use the `numWorkers` option to set the number of concurrent requests. By default it runs in sequential mode, i.e. set to 1.
Document stores contain ingested document chunks, i.e. [Node](../../documents_and_nodes/index.md)s.
## Available Document Stores
- [SimpleDocumentStore](../../../api/classes/SimpleDocumentStore.md): A simple in-memory document store with support for [persisting](../index.md#local-storage) data to disk.
- [PostgresDocumentStore](../../../api/classes/PostgresDocumentStore.md): A PostgreSQL document store, see [PostgreSQL Storage](../index.md#postgresql-storage).
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
Index stores are underlying storage components that contain metadata(i.e. information created when indexing) about the [index](../../data_index.md) itself.
## Available Index Stores
- [SimpleIndexStore](../../../api/classes/SimpleIndexStore.md): A simple in-memory index store with support for [persisting](../index.md#local-storage) data to disk.
- [PostgresIndexStore](../../../api/classes/PostgresIndexStore.md): A PostgreSQL index store, , see [PostgreSQL Storage](../index.md#postgresql-storage).
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
Key-Value Stores represent underlying storage components used in [Document Stores](../doc_stores/index.md) and [Index Stores](../index_stores/index.md)
## Available Key-Value Stores
- [SimpleKVStore](../../../api/classes/SimpleKVStore.md): A simple Key-Value store with support of [persisting](../index.md#local-storage) data to disk.
- [PostgresKVStore](../../../api/classes/PostgresKVStore.md): A PostgreSQL Key-Value store, see [PostgreSQL Storage](../index.md#postgresql-storage).
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
Vector stores save embedding vectors of your ingested document chunks.
## Available Vector Stores
Available Vector Stores are shown on the sidebar to the left. Additionally the following integrations exist without separate documentation:
- [SimpleVectorStore](../../../api/classes/SimpleVectorStore.md): A simple in-memory vector store with optional [persistance](../index.md#local-storage) to disk.
- [AstraDBVectorStore](../../../api/classes/AstraDBVectorStore.md): A cloud-native, scalable Database-as-a-Service built on Apache Cassandra, see [datastax.com](https://www.datastax.com/products/datastax-astra)
- [ChromaVectorStore](../../../api/classes/ChromaVectorStore.md): An open-source vector database, focused on ease of use and performance, see [trychroma.com](https://www.trychroma.com/)
- [MilvusVectorStore](../../../api/classes/MilvusVectorStore.md): An open-source, high-performance, highly scalable vector database, see [milvus.io](https://milvus.io/)
- [MongoDBAtlasVectorSearch](../../../api/classes/MongoDBAtlasVectorSearch.md): A cloud-based vector search solution for MongoDB, see [mongodb.com](https://www.mongodb.com/products/platform/atlas-vector-search)
- [PGVectorStore](../../../api/classes/PGVectorStore.md): An open-source vector store built on PostgreSQL, see [pgvector Github](https://github.com/pgvector/pgvector)
- [PineconeVectorStore](../../../api/classes/PineconeVectorStore.md): A managed, cloud-native vector database, see [pinecone.io](https://www.pinecone.io/)
- [WeaviateVectorStore](../../../api/classes/WeaviateVectorStore.md): An open-source, ai-native vector database, see [weaviate.io](https://weaviate.io/)
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
`Document`s and `Node`s are the basic building blocks of any index. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.
The embedding model in LlamaIndex is responsible for creating numerical representations of text. By default, LlamaIndex will use the `text-embedding-ada-002` model from OpenAI.
This can be explicitly updated through `Settings`
```typescript
import{OpenAIEmbedding,Settings}from"llamaindex";
Settings.embedModel=newOpenAIEmbedding({
model:"text-embedding-ada-002",
});
```
## Local Embedding
For local embeddings, you can use the [HuggingFace](./available_embeddings/huggingface.md) embedding model.
## Available Embeddings
Most available embeddings are listed in the sidebar on the left.
Additionally the following integrations exist without separate documentation:
- [ClipEmbedding](../../api/classes/ClipEmbedding.md) using `@xenova/transformers`
- [FireworksEmbedding](../../api/classes/FireworksEmbedding.md) see [fireworks.ai](https://fireworks.ai/)
Check the [LlamaIndexTS Github](https://github.com/run-llama/LlamaIndexTS) for the most up to date overview of integrations.
import CodeSource from "!raw-loader!../../../../examples/cloud/chat.ts";
# LlamaCloud
LlamaCloud is a new generation of managed parsing, ingestion, and retrieval services, designed to bring production-grade context-augmentation to your LLM and RAG applications.
Currently, LlamaCloud supports
- Managed Ingestion API, handling parsing and document management
- Managed Retrieval API, configuring optimal retrieval for your RAG system
## Access
We are opening up a private beta to a limited set of enterprise partners for the managed ingestion and retrieval API. If you’re interested in centralizing your data pipelines and spending more time working on your actual RAG use cases, come [talk to us.](https://www.llamaindex.ai/contact)
If you have access to LlamaCloud, you can visit [LlamaCloud](https://cloud.llamaindex.ai) to sign in and get an API key.
## Create a Managed Index
Currently, you can't create a managed index on LlamaCloud using LlamaIndexTS, but you can use an existing managed index for retrieval that was created by the Python version of LlamaIndex. See [the LlamaCloudIndex documentation](https://docs.llamaindex.ai/en/stable/module_guides/indexing/llama_cloud_index.html#usage) for more information on how to create a managed index.
## Use a Managed Index
Here's an example of how to use a managed index together with a chat engine:
To use Azure OpenAI, you only need to set a few environment variables together with the `OpenAI` class.
For example:
## Environment Variables
```
export AZURE_OPENAI_KEY="<YOUR KEY HERE>"
export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=rest-api>"
export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
To authenticate for production you'll have to use a [service account](https://cloud.google.com/docs/authentication/). `googleAuthOptions` has `credentials` which might be useful for you.
## Load and index documents
For this example, we will use a single document. In a real-world scenario, you would have multiple documents to index.
The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `Settings` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
The `MarkdownNodeParser` is a more advanced `NodeParser` that can handle markdown documents. It will split the markdown into nodes and then parse the nodes into a `Document` object.
A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string.
- [VectorIndexRetriever](../api/classes/VectorIndexRetriever.md) will fetch the top-k most similar nodes. Ideal for dense retrieval to find most relevant nodes.
- [SummaryIndexRetriever](../api/classes/SummaryIndexRetriever.md) will fetch all nodes no matter the query. Ideal when complete context is necessary, e.g. analyzing large datasets.
- [SummaryIndexLLMRetriever](../api/classes/SummaryIndexLLMRetriever.md) utilizes an LLM to score and filter nodes based on relevancy to the query.
- [KeywordTableLLMRetriever](../api/classes/KeywordTableLLMRetriever.md) uses an LLM to extract keywords from the query and retrieve relevant nodes based on keyword matches.
- [KeywordTableSimpleRetriever](../api/classes/KeywordTableSimpleRetriever.md) uses a basic frequency-based approach to extract keywords and retrieve nodes.
- [KeywordTableRAKERetriever](../api/classes/KeywordTableRAKERetriever.md) uses the RAKE (Rapid Automatic Keyword Extraction) algorithm to extract keywords from the query, focusing on co-occurrence and context for keyword-based retrieval.
import CodeSource from "!raw-loader!../../../../examples/workflow/joke.ts";
# Workflows
A `Workflow` in LlamaIndexTS is an event-driven abstraction used to chain together several events. Workflows are made up of `steps`, with each step responsible for handling certain event types and emitting new events.
Workflows in LlamaIndexTS work by defining step functions that handle specific event types and emit new events.
When a step function is added to a workflow, you need to specify the input and optionally the output event types (used for validation). The specification of the input events ensures each step only runs when an accepted event is ready.
You can create a `Workflow` to do anything! Build an agent, a RAG flow, an extraction flow, or anything else you want.
## Getting Started
As an illustrative example, let's consider a naive workflow where a joke is generated and then critiqued.
<CodeBlock language="ts">{CodeSource}</CodeBlock>
There's a few moving pieces here, so let's go through this piece by piece.
### Defining Workflow Events
```typescript
export class JokeEvent extends WorkflowEvent<{ joke: string }> {}
```
Events are user-defined classes that extend `WorkflowEvent` and contain arbitrary data provided as template argument. In this case, our workflow relies on a single user-defined event, the `JokeEvent` with a `joke` attribute of type `string`.
### Setting up the Workflow Class
```typescript
const llm = new OpenAI();
...
const jokeFlow = new Workflow({ verbose: true });
```
Our workflow is implemented by initiating the `Workflow` class. For simplicity, we created a `OpenAI` llm instance.
const prompt = `Write your best joke about ${ev.data.input}.`;
const response = await llm.complete({ prompt });
return new JokeEvent({ joke: response.text });
};
```
Here, we come to the entry-point of our workflow. While events are user-defined, there are two special-case events, the `StartEvent` and the `StopEvent`. Here, the `StartEvent` signifies where to send the initial workflow input.
The `StartEvent` is a bit of a special object since it can hold arbitrary attributes. Here, we accessed the topic with `ev.data.input`.
At this point, you may have noticed that we haven't explicitly told the workflow what events are handled by which steps.
To do so, we use the `addStep` method which adds a step to the workflow. The first argument is the event type that the step will handle, and the second argument is the previously defined step function:
const prompt = `Give a thorough critique of the following joke: ${ev.data.joke}`;
const response = await llm.complete({ prompt });
return new StopEvent({ result: response.text });
};
```
Here, we have our second, and last step, in the workflow. We know its the last step because the special `StopEvent` is returned. When the workflow encounters a returned `StopEvent`, it immediately stops the workflow and returns whatever the result was.
In this case, the result is a string, but it could be a map, array, or any other object.
Don't forget to add the step to the workflow:
```typescript
jokeFlow.addStep(JokeEvent, critiqueJoke);
```
### Running the Workflow
```typescript
const result = await jokeFlow.run("pirates");
console.log(result.data.result);
```
Lastly, we run the workflow. The `.run()` method is async, so we use await here to wait for the result.
### Validating Workflows
To tell the workflow what events are produced by each step, you can optionally provide a third argument to `addStep` to specify the output event type:
To validate a workflow, you need to call the `validate` method:
```typescript
jokeFlow.validate();
```
To automatically validate a workflow when you run it, you can set the `validate` flag to `true` at initialization:
```typescript
const jokeFlow = new Workflow({ verbose: true, validate: true });
```
## Working with Global Context/State
Optionally, you can choose to use global context between steps. For example, maybe multiple steps access the original `query` input from the user. You can store this in global context so that every step has access.
```typescript
import { Context } from "@llamaindex/core/workflow";
return `Answer this query using the context provided: ${event.data.query}`;
} else if (event instanceof RetrieveEvent) {
return `Context: ${event.data.context}`;
}
return "";
})
.join("\n");
const response = await llm.complete({ prompt });
return new StopEvent({ result: response.text });
};
```
Using `ctx.collectEvents()` we can buffer and wait for ALL expected events to arrive. This function will only return events (in the requested order) once all events have arrived.
## Manually Triggering Events
Normally, events are triggered by returning another event during a step. However, events can also be manually dispatched using the `ctx.sendEvent(event)` method within a workflow.
## Examples
You can find many useful examples of using workflows in the [examples folder](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/workflow).
LlamaIndex provides **one-click observability** 🔭 to allow you to build principled LLM applications in a production setting.
A key requirement for principled development of LLM applications over your data (RAG systems, agents) is being able to observe, debug, and evaluate
your system - both as a whole and for each component.
This feature allows you to seamlessly integrate the LlamaIndex library with powerful observability/evaluation tools offered by our partners.
Configure a variable once, and you'll be able to do things like the following:
- View LLM/prompt inputs/outputs
- Ensure that the outputs of any component (LLMs, embeddings) are performing as expected
- View call traces for both indexing and querying
Each provider has similarities and differences. Take a look below for the full set of guides for each one!
- [OpenLLMetry](#openllmetry)
- [Langtrace](#langtrace)
## OpenLLMetry
[OpenLLMetry](https://github.com/traceloop/openllmetry-js) is an open-source project based on OpenTelemetry for tracing and monitoring
LLM applications. It connects to [all major observability platforms](https://www.traceloop.com/docs/openllmetry/integrations/introduction) and installs in minutes.
Enhance your observability with Langtrace, a robust open-source tool supports OpenTelemetry and is designed to trace, evaluate, and manage LLM applications seamlessly. Langtrace integrates directly with LlamaIndex, offering detailed, real-time insights into performance metrics such as accuracy, evaluations, and latency.
#### Install
- Self-host or sign-up and generate an API key using [Langtrace](https://www.langtrace.ai) Cloud
Some files were not shown because too many files have changed in this diff
Show More
Reference in New Issue
Block a user
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.