Contents Menu Expand Light mode Dark mode Auto light/dark mode
LlamaIndex 🦙 0.8.36
LlamaIndex 🦙 0.8.36

Getting Started

  • Installation and Setup
  • Starter Tutorial
  • High-Level Concepts
  • Customization Tutorial

End-to-End Tutorials

  • Basic Usage Pattern
  • One-Click Observability
    • Wandb Callback Handler
    • LlamaIndex Tracing Tutorial
    • OpenInference Callback Handler
    • Evaluating and Improving a LlamaIndex Search and Retrieval Application
    • Evaluating and Tracking with TruLens
    • Quickstart Guide with LlamaIndex + TruLens
    • Colab
  • Principled Development Practices
    • The Development Pathway
    • Building Performant RAG Applications for Production
      • Recursive Retriever + Query Engine Demo
      • Document Summary Index
      • Metadata Replacement + Node Sentence Window
      • Auto-Retrieval from a Vector Database
      • Document Summary Index
      • Recursive Retriever + Document Agents
      • Comparing Methods for Structured Retrieval (Auto-Retrieval vs. Recursive Retrieval)
      • Query Engine
        • Usage Pattern
          • Response Modes
          • Streaming
        • Module Guides
          • Custom Query Engine
          • Retriever Query Engine
          • JSON Query Engine
          • Pandas Query Engine
          • Knowledge Graph Query Engine
          • Knowledge Graph RAG Query Engine
          • Router Query Engine
          • Retriever Router Query Engine
          • Joint QA Summary Query Engine
          • Sub Question Query Engine
          • Multi-Step Query Engine
          • SQL Router Query Engine
          • SQL Auto Vector Query Engine
          • SQL Join Query Engine
          • SQL Query Engine with LlamaIndex + DuckDB
          • Retry Query Engine
          • Retry Source Query Engine
          • Retry Guideline Query Engine
          • CitationQueryEngine
          • Recursive Retriever + Query Engine Demo
          • Recursive Retriever + Document Agents
          • Ensemble Query Engine Guide
          • FLARE Query Engine
        • Supporting Modules
          • Query Transformations
            • HyDE Query Transform
            • Multi-Step Query Engine
      • Routers
        • Usage Pattern
        • Modules
          • Router Query Engine
          • Retriever Router Query Engine
          • SQL Router Query Engine
          • Router Retriever
      • Data Agents
        • Usage Pattern
        • Module Guides
          • 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
          • Recursive Retriever + Document Agents
          • ReAct Agent with Query Engine Tools
      • Sub Question Query Engine
      • Joint QA Summary Query Engine
      • Recursive Retriever + Document Agents
      • Router Query Engine
      • OpenAI Agent + Query Engine Experimental Cookbook
      • OpenAI Agent Query Planning
      • Embedding Fine-tuning Guide
    • Observability
    • Evaluation
      • End-to-End Evaluation
        • QuestionGeneration
      • Component Wise Evaluation
        • BEIR Out of Domain Benchmark
        • HotpotQADistractor Demo
      • Evaluation
        • Usage Pattern (Response Evaluation)
        • Usage Pattern (Retrieval)
        • Modules
          • Faithfulness Evaluator
          • Relevancy Evaluator
          • Guideline Evaluator
          • Correctness Evaluator
          • Embedding Similarity Evaluator
          • LlamaIndex + DeepEval Integration
          • QuestionGeneration
          • BatchEvalRunner - Running Multiple Evaluations
          • Retrieval Evaluation
    • Monitoring
  • Discover LlamaIndex Video Series
  • Finetuning
    • Fine-tuning an Adapter
    • Embedding Fine-tuning Guide
    • Embedding Fine-tuning Repo
    • Embedding Fine-tuning Blog
    • GPT-3.5 Fine-tuning Notebook (Colab)
    • GPT-3.5 Fine-tuning Notebook (Notebook link)
    • Fine-tuning a gpt-3.5 ReAct Agent on Better Chain of Thought
    • GPT-3.5 Fine-tuning Notebook (Colab)
    • GPT-3.5 Fine-tuning Notebook (in Repo)
    • Fine-tuning to Memorize Knowledge
    • Llama 2 Text-to-SQL Fine-tuning (Repo)
    • Llama 2 Text-to-SQL Fine-tuning (Notebook)
  • Building RAG from Scratch (Lower-Level)
    • Building Data Ingestion from Scratch
    • Building Retrieval from Scratch
    • Building RAG from Scratch (Open-source only!)
    • Building a (Very Simple) Vector Store from Scratch
    • Building Response Synthesis from Scratch
    • Building a Router from Scratch
    • Building Evaluation from Scratch
  • Use Cases
    • Q&A over Documents
    • Chatbots
    • Agents
      • 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
    • Knowledge Graphs
      • LlamaIndex Workshop: Building RAG with Knowledge Graphs
      • REBEL + Knowledge Graph Index
    • Structured Data
    • Full-Stack Web Application
    • Private Setup
    • Finetuning Llama 2 for Text-to-SQL
    • Finetuning GPT-3.5 to Distill GPT-4

Index/Data Modules

  • Data Connectors (LlamaHub)
    • Usage Pattern
    • Module Guides
      • Simple Directory Reader
      • Psychic Reader
      • DeepLake Reader
      • Qdrant Reader
      • Discord Reader
      • MongoDB Reader
      • Chroma Reader
      • MyScale Reader
      • Faiss Reader
      • Obsidian Reader
      • Slack Reader
      • Web Page Reader
      • Pinecone Reader
      • Mbox Reader
      • MilvusReader
      • Notion Reader
      • Github Repo Reader
      • Google Docs Reader
      • Database Reader
      • Twitter Reader
      • Weaviate Reader
      • Make Reader
      • Deplot Reader Demo
  • Documents / Nodes
    • Defining and Customizing Documents
      • Extracting Metadata for Better Document Indexing and Understanding
    • Defining and Customizing Nodes
    • Automated Metadata Extraction for Nodes
      • Extracting Metadata for Better Document Indexing and Understanding
      • Automated Metadata Extraction for Better Retrieval + Synthesis
      • Entity Metadata Extraction
      • Metadata Extraction and Augmentation w/ Marvin
      • Pydantic Extractor
  • Node Parser
    • Usage Pattern
  • Storage
    • Customizing Storage
    • Persisting & Loading Data
    • Vector Stores
      • Elasticsearch Vector Store
      • Simple Vector Store
      • Rockset Vector Store
      • Qdrant Vector Store
      • Faiss Vector Store
      • DeepLake Vector Store
      • MyScale Vector Store
      • Metal Vector Store
      • Weaviate Vector Store
      • Opensearch Vector Store
      • Pinecone Vector Store
      • Chroma
      • LanceDB Vector Store
      • Milvus Vector Store
      • Redis Vector Store
      • Query the data
      • Working with Metadata
      • Weaviate Vector Store - Hybrid Search
      • Zep Vector Store
      • Create a Zep Vector Store and Index
      • Querying with Metadata filters
      • Pinecone Vector Store - Hybrid Search
      • Simple Vector Store - Async Index Creation
      • Tair Vector Store
      • Supabase Vector Store
      • DocArray Hnsw Vector Store
      • DocArray InMemory Vector Store
      • MongoDB Atlas
      • Cassandra Vector Store
      • Neo4j vector store
      • Azure Cognitive Search
      • Basic Example
      • Create Index (if it does not exist)
      • Use Existing Index
      • Adding a document to existing index
      • Filtering
      • Epsilla Vector Store
      • Timescale Vector Store (PostgreSQL)
    • Document Stores
    • Index Stores
    • Key-Value Stores
    • Using Graph Stores
      • Neo4j Graph Store
      • Nebula Graph Store
      • Knowledge Graph Query Engine
      • Kuzu Graph Store
      • FalkorDB Graph Store
  • Indexes
    • How Each Index Works
    • Usage Pattern
      • Metadata Extraction
      • Document Management
    • Module Guides
      • Vector Store Index
      • Summary Index
      • Tree Index
      • Keyword Table Index
      • Knowledge Graph Index
      • Custom Retriever combining KG Index and VectorStore Index
      • Knowledge Graph Query Engine
      • Knowledge Graph RAG Query Engine
      • REBEL + Knowledge Graph Index
      • SQL Index
      • SQL Query Engine with LlamaIndex + DuckDB
      • Document Summary Index
    • Composability
      • Composable Graph Basic
      • Composable Graph with Weaviate
      • Composable Graph

Query Modules

  • Query Engine
    • Usage Pattern
      • Response Modes
      • Streaming
    • Module Guides
      • Custom Query Engine
      • Retriever Query Engine
      • JSON Query Engine
      • Pandas Query Engine
      • Knowledge Graph Query Engine
      • Knowledge Graph RAG Query Engine
      • Router Query Engine
      • Retriever Router Query Engine
      • Joint QA Summary Query Engine
      • Sub Question Query Engine
      • Multi-Step Query Engine
      • SQL Router Query Engine
      • SQL Auto Vector Query Engine
      • SQL Join Query Engine
      • SQL Query Engine with LlamaIndex + DuckDB
      • Retry Query Engine
      • Retry Source Query Engine
      • Retry Guideline Query Engine
      • CitationQueryEngine
      • Recursive Retriever + Query Engine Demo
      • Recursive Retriever + Document Agents
      • Ensemble Query Engine Guide
      • FLARE Query Engine
    • Supporting Modules
      • Query Transformations
        • HyDE Query Transform
        • Multi-Step Query Engine
  • Chat Engine
    • Usage Pattern
    • Module Guides
      • ReAct Chat Engine
      • OpenAI Chat Engine
      • Context Chat Engine
      • Condense Question Chat Engine
      • Simple Chat Engine
  • Retriever
    • Usage Pattern
      • Retriever Modes
      • Define Custom Retriever
      • BM25 Hybrid Retriever
    • Module Guides
      • BM25 Retriever
      • Custom Retriever (KG Index and Vector Store Index)
      • Knowledge Graph RAG Retriever
      • Auto-Retrieval (with Chroma)
      • Auto-Retrieval (with BagelDB)
      • Recursive Retriever + Query Engine Demo
      • Router Retriever
      • Ensemble Query Engine Guide
      • Auto Merging Retriever
      • Recursive Retriever + Node References
      • Recursive Retriever + Node References + Braintrust
  • Routers
    • Usage Pattern
    • Modules
      • Router Query Engine
      • Retriever Router Query Engine
      • SQL Router Query Engine
      • Router Retriever
  • Node Postprocessor
    • Usage Pattern
    • Modules
      • Sentence Embedding Optimizer
      • Cohere Rerank
      • LLM Reranker Demonstration (2021 Lyft 10-k)
      • LLM Reranker Demonstration (Great Gatsby)
      • Recency Filtering
      • Time-Weighted Rerank
      • PII Masking
      • Forward/Backward Augmentation
      • Metadata Replacement + Node Sentence Window
      • LongContextReorder
  • Response Synthesizer
    • Usage Pattern
    • Module Guide
      • Refine
      • Refine with Structured Answer Filtering
      • Tree Summarize
  • Structured Outputs
    • Output Parsing
      • Guardrails Output Parsing
      • Langchain Output Parsing
      • Guidance Pydantic Program
      • Guidance for Sub-Question Query Engine
      • OpenAI Pydantic Program
    • Pydantic Program
      • OpenAI Pydantic Program
      • Guidance Pydantic Program
      • Guidance for Sub-Question Query Engine
      • DataFrame Structured Data Extraction
      • Evaporate Demo

Agent Modules

  • Data Agents
    • Usage Pattern
    • Module Guides
      • 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
      • Recursive Retriever + Document Agents
      • ReAct Agent with Query Engine Tools
  • Tools
    • Usage Pattern
    • LlamaHub Tools Guide

Model Modules

  • LLM
    • Using LLMs as standalone modules
    • Customizing LLMs within LlamaIndex Abstractions
    • Modules
      • OpenAI
      • Azure OpenAI
      • Anthropic
      • Gradient Base Model
      • Gradient Model Adapter
      • HuggingFace LLM - Camel-5b
      • HuggingFace LLM - StableLM
      • Local Llama2 + VectorStoreIndex
      • EverlyAI
      • LiteLLM
      • PaLM
      • Predibase
      • Replicate - Llama 2 13B
      • Replicate - Vicuna 13B
      • Llama2 + VectorStoreIndex
      • LangChain LLM
      • Llama API
      • LlamaCPP
      • Xorbits Inference
      • Set Monster API Key env variable
      • Basic Usage Pattern
      • RunGPT
      • Setup
      • Portkey
      • Anyscale
      • Ollama - Llama 2 7B
  • Embeddings
    • Usage Pattern
    • Modules
      • OpenAI Embeddings
      • Langchain Embeddings
      • Azure OpenAI
      • Custom Embeddings
      • Local Embeddings with HuggingFace
  • Prompts
    • Completion Prompts Customization
    • Chat Prompts Customization

Supporting Modules

  • ServiceContext
  • Callbacks
    • Token Counting Handler
    • Llama Debug Handler
    • Wandb Callback Handler
    • Aim Callback
    • OpenInference Callback Handler
    • Token Counting - Migration Guide
  • Evaluation
    • Usage Pattern (Response Evaluation)
    • Usage Pattern (Retrieval)
    • Modules
      • Faithfulness Evaluator
      • Relevancy Evaluator
      • Guideline Evaluator
      • Correctness Evaluator
      • Embedding Similarity Evaluator
      • LlamaIndex + DeepEval Integration
      • QuestionGeneration
      • BatchEvalRunner - Running Multiple Evaluations
      • Retrieval Evaluation
  • Cost Analysis
    • Usage Pattern
  • Playground
    • Playground

Development

  • Contributing to LlamaIndex
  • Documentation Guide
  • Privacy and Security
  • ChangeLog

Community

  • Integrations
    • One-Click Observability
      • Wandb Callback Handler
      • LlamaIndex Tracing Tutorial
      • OpenInference Callback Handler
      • Evaluating and Improving a LlamaIndex Search and Retrieval Application
      • Evaluating and Tracking with TruLens
      • Quickstart Guide with LlamaIndex + TruLens
      • Colab
    • Tracing with Graphsignal
    • Evaluating and Tracking with TruLens
    • Unit Testing LLMs With DeepEval
    • Guidance
    • Guardrails
    • OpenAI Function Calling
    • Using Vector Stores
      • Elasticsearch
      • Simple Vector Store
      • Simple Vector Stores - Maximum Marginal Relevance Retrieval
      • Redis Vector Store
      • Query the data
      • Working with Metadata
      • Qdrant Vector Store
      • Faiss Vector Store
      • DeepLake Vector Store
      • MyScale Vector Store
      • Metal Vector Store
      • Weaviate Vector Store
      • Zep Vector Store
      • Create a Zep Vector Store and Index
      • Querying with Metadata filters
      • Opensearch Vector Store
      • Pinecone Vector Store
      • Cassandra Vector Store
      • Chroma
      • Epsilla Vector Store
      • LanceDB Vector Store
      • Milvus Vector Store
      • Weaviate Vector Store - Hybrid Search
      • Pinecone Vector Store - Hybrid Search
      • Simple Vector Store - Async Index Creation
      • Supabase Vector Store
      • DocArray Hnsw Vector Store
      • DocArray InMemory Vector Store
      • MongoDB Atlas
      • Postgres Vector Store
      • Awadb Vector Store
      • Neo4j vector store
      • Azure Cognitive Search
      • Basic Example
      • Create Index (if it does not exist)
      • Use Existing Index
      • Adding a document to existing index
      • Filtering
      • Timescale Vector Store (PostgreSQL)
    • Using Graph Stores
      • Neo4j Graph Store
      • Nebula Graph Store
      • Knowledge Graph Query Engine
      • Kuzu Graph Store
      • FalkorDB Graph Store
    • Using Managed Indices
    • Using with Langchain 🦜🔗
    • Streamlit
    • Chainlit
    • LlamaIndex + Ray
    • ChatGPT Plugin Integrations
    • Poe
    • Airbyte
  • App Showcase

API Reference

  • API Reference
    • Indices
      • Summary Index
      • Table Index
      • Tree Index
      • Vector Store Index
      • Structured Store Index
      • Knowledge Graph Index
      • Empty Index
    • Querying an Index
      • Retrievers
        • Empty Index Retriever
        • Knowledge Graph Retriever
        • List Retriever
        • Keyword Table Retrievers
        • Tree Retrievers
        • Vector Store Retrievers
        • Transform Retriever
      • Response Synthesizer
      • Query Engines
        • Graph Query Engine
        • Multistep Query Engine
        • Retriever Query Engine
        • Transform Query Engine
        • Router Query Engine
        • Retriever Router Query Engine
        • Sub Question Query Engine
        • SQL Join Query Engine
        • Flare Query Engine
        • Citation Query Engine
        • Knowledge Graph Query Engine
        • SQL Query Engine
        • Pandas Query Engine
      • Chat Engines
        • Simple Chat Engine
        • Condense Question Chat Engine
      • Query Bundle
      • Query Transform
    • Node
    • LLM Predictors
    • LLMs
      • OpenAI
      • Azure OpenAI
      • HuggingFaceLLM
      • LangChainLLM
      • Anthropic
      • Gradient Base Model
      • Gradient Model Adapter
      • LiteLLM
      • LlamaCPP
      • PaLM
      • Predibase
      • Replicate
      • XOrbits Xinference
    • Prompt Templates
    • Embeddings
    • OpenAIEmbedding
    • HuggingFaceEmbedding
    • OptimumEmbedding
    • InstructorEmbedding
    • LangchainEmbedding
    • GoogleUnivSentEncoderEmbedding
    • Node Postprocessor
    • Storage Context
      • Document Store
      • Index Store
      • Vector Store
      • KV Storage
      • Loading Indices
    • Composability
    • Data Connectors
    • Service Context
      • Embeddings
      • OpenAIEmbedding
      • HuggingFaceEmbedding
      • OptimumEmbedding
      • InstructorEmbedding
      • LangchainEmbedding
      • GoogleUnivSentEncoderEmbedding
      • Node Parser
      • PromptHelper
      • LLMs
        • OpenAI
        • Azure OpenAI
        • HuggingFaceLLM
        • LangChainLLM
        • Anthropic
        • Gradient Base Model
        • Gradient Model Adapter
        • LiteLLM
        • LlamaCPP
        • PaLM
        • Predibase
        • Replicate
        • XOrbits Xinference
    • Callbacks
    • Structured Index Configuration
    • Evaluation
    • Response
    • Playground
    • Finetuning
    • Memory
    • Example Notebooks
    • Langchain Integrations
  • Deprecated Terms
  v: latest
Versions
latest
stable
v0.8.36
v0.8.35
v0.8.34
v0.8.33
v0.8.32
v0.8.31
v0.8.30
v0.8.29.post1
v0.8.29
v0.8.28
v0.8.27
v0.8.26.post1
v0.8.26
v0.8.25
v0.8.24.post1
v0.8.24
v0.8.23.post1
v0.8.23
v0.8.22
v0.8.21
v0.8.20
v0.8.19
v0.8.18
v0.8.17
v0.8.16
v0.8.15
v0.8.14
v0.8.13
v0.8.12
v0.8.11.post3
v0.8.11.post2
v0.8.11.post1
v0.8.11
v0.8.10.post1
v0.8.10
v0.8.9
v0.8.8
v0.8.7
v0.8.6
v0.8.5.post2
v0.8.5.post1
v0.8.5
v0.8.4
v0.8.3
v0.8.2.post1
v0.8.2
v0.8.1.post1
v0.8.1
v0.8.0
v0.7.24.post1
v0.7.24
v0.7.23.post1
v0.7.23
v0.7.22
v0.7.21
v0.7.20
v0.7.19
v0.7.18
v0.7.17
v0.7.16
v0.7.15
v0.7.14
v0.7.13
v0.7.12
v0.7.11.post1
v0.7.11
v0.7.10.post1
v0.7.10
v0.7.9
v0.7.8
v0.7.7
v0.7.6
v0.7.5
v0.7.4
v0.7.3
v0.7.2
v0.7.1
v0.7.0
v0.6.38.post1
v0.6.38
v0.6.37
v0.6.36
v0.6.35
v0.6.34.post1
v0.6.34
v0.6.33
v0.6.32
v0.6.31
v0.6.30
v0.6.29
v0.6.28
v0.6.27
v0.6.26
v0.6.25.post1
v0.6.25
v0.6.24
v0.6.23
v0.6.22
v0.6.21.post1
v0.6.21
v0.6.20
v0.6.19
v0.6.18
v0.6.17
v0.6.16.post1
v0.6.16
v0.6.15
v0.6.14
v0.6.13
v0.6.12
v0.6.11
v0.6.10.post1
v0.6.10
v0.6.9
v0.6.8
v0.6.7
v0.6.6
v0.6.5
v0.6.4
v0.6.3
v0.6.2
v0.6.1
v0.6.0
v0.5.27
Downloads
On Read the Docs
Project Home
Builds
Back to top
Edit this page

Use Cases

  • Q&A over Documents
  • Chatbots
  • Agents
  • Knowledge Graphs
  • Structured Data
  • Full-Stack Web Application
  • Private Setup
  • Finetuning Llama 2 for Text-to-SQL
  • Finetuning GPT-3.5 to Distill GPT-4
Next
Q&A over Documents
Previous
Building Evaluation from Scratch
Copyright © 2022, Jerry Liu
Made with Sphinx and @pradyunsg's Furo