Contents Menu Expand Light mode Dark mode Auto light/dark mode
LlamaIndex 🦙 0.6.2
LlamaIndex 🦙 0.6.2

Getting Started

  • Installation and Setup
  • Starter Tutorial

Guides

  • A Primer to using LlamaIndex
    • LlamaIndex Usage Pattern
    • How Each Index Works
  • Tutorials
    • 💬🤖 How to Build a Chatbot
    • A Guide to Building a Full-Stack Web App with LLamaIndex
    • A Guide to Building a Full-Stack LlamaIndex Web App with Delphic
    • A Guide to LlamaIndex + Structured Data
    • A Guide to Extracting Terms and Definitions
    • A Guide to Creating a Unified Query Framework over your Indexes
    • SEC 10k Analysis

Use Cases

  • Queries over your Data
  • Integrations into LLM Applications

Key Components

  • 🔌 Data Connectors (LlamaHub)
    • 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
  • 🗃️ Index Structures
    • How Each Index Works
    • Updating an Index
    • Composability
      • Composable Graph Basic
      • Composable Graph with Weaviate
      • Composable Graph
    • Knowledge Graph Index
    • Pandas Index
    • SQL Index
    • Document Summary Index Demo
  • 🔍 Query Interface
    • LlamaIndex Usage Pattern
    • Composability
      • Composable Graph Basic
      • Composable Graph with Weaviate
      • Composable Graph
    • Query Transformations
      • HyDE Query Transform
      • Multi-Step Decompose Query Transform
    • Second-Stage Processing
      • Forward/Backward Augmentation
      • Recency Filtering
      • Time-Weighted Rerank
      • PII Masking
      • Cohere Rerank
    • Optimizers
      • Sentence Embedding Optimizer
    • Response Synthesis
    • Query Engines
      • Retriever Query Engine with Custom Retrievers - Simple Hybrid Search
      • Router Query Engine
      • Retriever Router Query Engine
      • Joint QA Summary Query Engine
  • 🛠️ Customization
    • Defining LLMs
      • Azure OpenAI
    • Defining Prompts
    • Embedding support
    • Customizing Storage
  • 🧠 Analysis
    • Cost Analysis
      • Token Predictors
    • Playground
      • Playground
  • 🔢 Output Parsing
    • Guardrails Output Parsing
    • Langchain Output Parsing
  • 🔬 Evaluation
    • Response Evaluator
    • Query Response Evaluator
    • Question Generation
  • ⛓️ Integrations
    • Using Vector Stores
      • Simple Vector Store
      • Qdrant Vector Store
      • Faiss Vector Store
      • DeepLake Vector Store
      • MyScale Vector Store
      • Metal Vector Store
      • Weaviate Vector Store
      • Using as a vector index.
      • Pinecone Vector Store
      • Chroma Vector Store
      • LanceDB Vector Store
      • Milvus Vector Store
      • Weaviate Vector Store - Hybrid Search
      • Pinecone Vector Store - Hybrid Search
      • Simple Vector Store - Async Index Creation
    • ChatGPT Plugin Integrations
    • Using with Langchain 🦜🔗
  • 💾 Storage
    • Persisting & Loading Data
    • Customizing Storage
    • Document Stores
    • Index Stores
    • Vector Stores
      • Simple Vector Store
      • Qdrant Vector Store
      • Faiss Vector Store
      • DeepLake Vector Store
      • MyScale Vector Store
      • Metal Vector Store
      • Weaviate Vector Store
      • Using as a vector index.
      • Pinecone Vector Store
      • Chroma Vector Store
      • LanceDB Vector Store
      • Milvus Vector Store
      • Weaviate Vector Store - Hybrid Search
      • Pinecone Vector Store - Hybrid Search
      • Simple Vector Store - Async Index Creation
    • Key-Value Stores

Reference

  • Indices
    • List 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
      • SQL Query Engine
      • Pandas Query Engine
    • Query Bundle
    • Query Transform
  • Node
  • LLM Predictors
  • Node Postprocessor
  • Storage Context
    • Document Store
    • Index Store
    • Vector Store
    • KV Storage
    • Loading Indices
  • Composability
  • Data Connectors
  • Prompt Templates
  • Service Context
    • Embeddings
    • LLMPredictor
    • PromptHelper
    • Llama Logger 🪵
  • Optimizers
  • Callbacks
  • Structured Index Configuration
  • Response
  • Playground
  • Node Parser
  • Example Notebooks
  • Langchain Integrations

Gallery

  • 😎 App Showcase
  v: v0.6.3
Versions
latest
stable
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

🛠️ Customization

LlamaIndex provides the ability to customize the following components:

  • LLM

  • Prompts

  • Embedding model

These are described in their respective guides below.

Customizable Modules

  • Defining LLMs
  • Defining Prompts
  • Embedding support
  • Customizing Storage
Next
Defining LLMs
Previous
Joint QA Summary Query Engine
Copyright © 2022, Jerry Liu
Made with Sphinx and @pradyunsg's Furo