Hide navigation sidebar

Hide table of contents sidebar

Toggle site navigation sidebar

LlamaIndex 🦙 0.9.48

Toggle table of contents sidebar

LlamaIndex 🦙 0.9.48

Getting Started

Installation and Setup
How to read these docs
Starter Tutorial
High-Level Concepts
Customization Tutorial
Discover LlamaIndex Video Series

Use Cases

Q&A
Toggle child pages in navigation
- RAG CLI
Chatbots
Agents
Toggle child pages in navigation
- Agents (Putting your RAG Pipeline Together)
  Toggle child pages in navigation
- Agentic Strategies (Optimizing your RAG Pipeline)
  Toggle child pages in navigation
  - Routers
    Toggle child pages in navigation
  - Query Transformations
    Toggle child pages in navigation
    - HyDE Query Transform
    - Multi-Step Query Engine
  - Sub Question Query Engine (Intro)
  - Build your own OpenAI Agent
  - OpenAI Agent with Query Engine Tools
  - Retrieval-Augmented OpenAI Agent
  - OpenAI Agent + Query Engine Experimental Cookbook
  - OpenAI Agent Query Planning
  - Context-Augmented OpenAI Agent
- Agents
  Toggle child pages in navigation
- Tools
  Toggle child pages in navigation
  - Usage Pattern
  - LlamaHub Tools Guide
Structured Data Extraction
Toggle child pages in navigation
- Structured Outputs
  Toggle child pages in navigation
  - Pydantic Program
    Toggle child pages in navigation
  - Query Engines + Pydantic Outputs
    Toggle child pages in navigation
  - Output Parsing Modules
    Toggle child pages in navigation
- Output Parsing Modules
  Toggle child pages in navigation
- Extracting names and locations from descriptions of people
- Extracting album data from music reviews
- Extracting information from emails
Multi-modal
Toggle child pages in navigation

Understanding

Building an LLM application
Using LLMs
Toggle child pages in navigation
- Privacy and Security
Loading Data (Ingestion)
Toggle child pages in navigation
- LlamaHub
- Documents / Nodes
  Toggle child pages in navigation
  - Defining and Customizing Documents
    Toggle child pages in navigation
    - Metadata Extraction Usage Pattern
      Toggle child pages in navigation
  - Defining and Customizing Nodes
  - Transformations
- Node Parser Usage Pattern
  Toggle child pages in navigation
  - Node Parser Modules
- Ingestion Pipeline
  Toggle child pages in navigation
Indexing
Storing
Querying
Putting It All Together
Toggle child pages in navigation
- Q&A patterns
  Toggle child pages in navigation
- Full-Stack Web Application
  Toggle child pages in navigation
  - A Guide to Building a Full-Stack Web App with LLamaIndex
  - A Guide to Building a Full-Stack LlamaIndex Web App with Delphic
- How to Build a Chatbot
- Agents
  Toggle child pages in navigation
- Full-Stack Projects
  Toggle child pages in navigation
Tracing and Debugging
Evaluating
Toggle child pages in navigation
- Cost Analysis
  Toggle child pages in navigation
  - Usage Pattern

Optimizing

Basic Strategies
Toggle child pages in navigation
Advanced Retrieval Strategies
Toggle child pages in navigation
- Query Transform Cookbook
- Query Transformations
  Toggle child pages in navigation
  - HyDE Query Transform
  - Multi-Step Query Engine
- Composable Objects
- DeepMemory (Activeloop)
- Weaviate Vector Store - Hybrid Search
- Pinecone Vector Store - Hybrid Search
Agentic strategies
Toggle child pages in navigation
- Routers
  Toggle child pages in navigation
- Query Transformations
  Toggle child pages in navigation
  - HyDE Query Transform
  - Multi-Step Query Engine
- Sub Question Query Engine (Intro)
- Build your own OpenAI Agent
- OpenAI Agent with Query Engine Tools
- Retrieval-Augmented OpenAI Agent
- OpenAI Agent + Query Engine Experimental Cookbook
- OpenAI Agent Query Planning
- Context-Augmented OpenAI Agent
Evaluation
Toggle child pages in navigation
- End-to-End Evaluation
  Toggle child pages in navigation
- Component Wise Evaluation
  Toggle child pages in navigation
  - BEIR Out of Domain Benchmark
  - HotpotQADistractor Demo
- Evaluating
  Toggle child pages in navigation
  - Usage Pattern (Response Evaluation)
  - Usage Pattern (Retrieval)
  - Modules
    Toggle child pages in navigation
  - Evaluating With LabelledRagDataset’s
    Toggle child pages in navigation
    - Benchmarking RAG Pipelines With A LabelledRagDatatset
    - Downloading a LlamaDataset from LlamaHub
  - Contributing A LabelledRagDataset
    Toggle child pages in navigation
    - LlamaDataset Submission Template Notebook
- Component Wise Evaluation
  Toggle child pages in navigation
  - BEIR Out of Domain Benchmark
  - HotpotQADistractor Demo
- End-to-End Evaluation
  Toggle child pages in navigation
Fine-tuning
Toggle child pages in navigation
Building Performant RAG Applications for Production
Toggle child pages in navigation
Writing Custom Modules
Building RAG from Scratch (Lower-Level)
Toggle child pages in navigation

Module Guides

Models
Toggle child pages in navigation
Prompts
Toggle child pages in navigation
Loading Data
Toggle child pages in navigation
- Data Connectors (LlamaHub)
  Toggle child pages in navigation
  - Usage Pattern
  - Module Guides
    Toggle child pages in navigation
- Documents / Nodes
  Toggle child pages in navigation
  - Defining and Customizing Documents
    Toggle child pages in navigation
    - Metadata Extraction Usage Pattern
      Toggle child pages in navigation
  - Defining and Customizing Nodes
  - Transformations
- Node Parser Usage Pattern
  Toggle child pages in navigation
  - Node Parser Modules
- Ingestion Pipeline
  Toggle child pages in navigation
Indexing
Toggle child pages in navigation
- Using VectorStoreIndex
  Toggle child pages in navigation
- How Each Index Works
- Module Guides
  Toggle child pages in navigation
- Composability
  Toggle child pages in navigation
Storing
Toggle child pages in navigation
Querying
Toggle child pages in navigation
- Query Pipeline
  Toggle child pages in navigation
  - Usage Pattern
  - Module Usage
  - Module Guides
    Toggle child pages in navigation
- Query Engine
  Toggle child pages in navigation
  - Usage Pattern
    Toggle child pages in navigation
    - Response Modes
    - Streaming
  - Module Guides
    Toggle child pages in navigation
  - Supporting Modules
    Toggle child pages in navigation
    - Query Transformations
      Toggle child pages in navigation
      - HyDE Query Transform
      - Multi-Step Query Engine
- Chat Engine
  Toggle child pages in navigation
  - Usage Pattern
  - Module Guides
    Toggle child pages in navigation
- Agents
  Toggle child pages in navigation
- Retriever
  Toggle child pages in navigation
  - Retriever Modes
  - Retriever Modules
    Toggle child pages in navigation
- Response Synthesizer
  Toggle child pages in navigation
  - Response Synthesis Modules
    Toggle child pages in navigation
- Routers
  Toggle child pages in navigation
- Node Postprocessor
  Toggle child pages in navigation
  - Node Postprocessor Modules
    Toggle child pages in navigation
- Structured Outputs
  Toggle child pages in navigation
  - Pydantic Program
    Toggle child pages in navigation
  - Query Engines + Pydantic Outputs
    Toggle child pages in navigation
  - Output Parsing Modules
    Toggle child pages in navigation
Agents
Toggle child pages in navigation
Observability
Toggle child pages in navigation
Evaluating
Toggle child pages in navigation
- Usage Pattern (Response Evaluation)
- Usage Pattern (Retrieval)
- Modules
  Toggle child pages in navigation
- Evaluating With LabelledRagDataset’s
  Toggle child pages in navigation
  - Benchmarking RAG Pipelines With A LabelledRagDatatset
  - Downloading a LlamaDataset from LlamaHub
- Contributing A LabelledRagDataset
  Toggle child pages in navigation
  - LlamaDataset Submission Template Notebook
Supporting Modules
Toggle child pages in navigation
- ServiceContext

API Reference

API Reference
Toggle child pages in navigation
- Agents
- Callbacks
- Composability
- Evaluation
- Example Notebooks
- Finetuning
- Indices
  Toggle child pages in navigation
- LLM Predictors
- LLMs
  Toggle child pages in navigation
- Memory
- Multi-Modal LLMs, Vector Stores, Embeddings, Retriever, and Query Engine
  Toggle child pages in navigation
  - OpenAI
  - Replicate
- Node Postprocessor
- Node
  Toggle child pages in navigation
- Playground
- Prompt Templates
- Querying an Index
  Toggle child pages in navigation
  - Retrievers
    Toggle child pages in navigation
  - Response Synthesizer
  - Query Engines
    Toggle child pages in navigation
  - Chat Engines
    Toggle child pages in navigation
  - Query Bundle
  - Query Transform
- Data Connectors
  Toggle child pages in navigation
- Response
- Service Context
  Toggle child pages in navigation
  - Embeddings
  - OpenAIEmbedding
  - HuggingFaceEmbedding
  - OptimumEmbedding
  - InstructorEmbedding
  - LangchainEmbedding
  - GoogleUnivSentEncoderEmbedding
  - Node Parser
    Toggle child pages in navigation
  - PromptHelper
  - LLMs
    Toggle child pages in navigation
- Embeddings
- OpenAIEmbedding
- HuggingFaceEmbedding
- OptimumEmbedding
- InstructorEmbedding
- LangchainEmbedding
- GoogleUnivSentEncoderEmbedding
- Storage Context
  Toggle child pages in navigation
- Structured Index Configuration

Community

Integrations
Toggle child pages in navigation
Frequently Asked Questions (FAQ)
Toggle child pages in navigation
Full-Stack Projects
Toggle child pages in navigation

Contributing

Contributing to LlamaIndex
Documentation Guide

Changes

ChangeLog
Deprecated Terms

Toggle table of contents sidebar

Predibase#

Copyright © 2023, Jerry Liu

Made with Sphinx and @pradyunsg's Furo