link管理
链接快照平台
- 输入网页链接，自动生成快照
- 标签化管理网页链接
相关文章推荐
|
温暖的面包 · 王小云：十年破解MD5和SHA-1两大国际密 ...· 3 月前 · |
|
|
没有腹肌的沙滩裤 · 新文化运动代表：《新青年》-中国气象局政府门户网站· 6 月前 · |
|
|
谦逊的石榴 · 机器学习在网络安全中的未来 - Palo ...· 10 月前 · |
|
|
睡不着的地瓜 · 不同pH条件下高低致龋性变异链球菌sRNA ...· 1 年前 · |
|
|
玩命的小虾米 · 五指山市国民经济和社会发展第十四个 ...· 1 年前 · |
link管理
›
HuggingFace LLM - StableLM - LlamaIndex 🦙 v0.10.17
| chat toggle notebook vector |
| https://docs.llamaindex.ai/en/stable/examples/customization/llms/SimpleIndexDemo-Huggingface_stablelm.html |
|
怕老婆的西装
1 年前 |
-
Agents (Putting your RAG Pipeline Together)
- Build your own OpenAI Agent
- OpenAI Agent with Query Engine Tools
- OpenAI Agent Query Planning
- OpenAI Assistant Agent
- OpenAI Assistant Advanced Retrieval Cookbook
- OpenAI agent: specifying a forced function call
- Single-Turn Multi-Function Calling OpenAI Agents
- Context-Augmented OpenAI Agent
-
Agentic Strategies (Optimizing your RAG Pipeline)
-
Routers
- Router Query Engine
- Retriever Router Query Engine
- SQL Router Query Engine
- Router Retriever
-
Query Transformations
- 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
- 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
- Multi-Document Agents
- GPT Builder Demo
- Single-Turn Multi-Function Calling OpenAI Agents
- OpenAI Assistant Agent
- Benchmarking OpenAI Retrieval API (through Assistant Agent)
- OpenAI Assistant Advanced Retrieval Cookbook
- ReAct Agent - A Simple Intro with Calculator Tools
- ReAct Agent with Query Engine (RAG) Tools
- LLMCompiler Agent Cookbook
- Building a Custom Agent
- Building an Agent around a Query Pipeline
- Step-wise, Controllable Agents
- Controllable Agents for RAG
- Controllable Agents for RAG
-
Tools
- Usage Pattern
- LlamaHub Tools Guide
- Lower-Level Agent API
-
Tools
- Usage Pattern
- LlamaHub Tools Guide
-
Structured Data Extraction
-
Structured Outputs
-
Pydantic Program
- LLM Pydantic Program
- OpenAI Pydantic Program
- Guidance Pydantic Program
- Guidance for Sub-Question Query Engine
- DataFrame Structured Data Extraction
- Evaporate Demo
-
Query Engines + Pydantic Outputs
- Query Engine with Pydantic Outputs
- Pydantic Tree Summarize
- Download Data
-
Output Parsing Modules
- Guardrails Output Parsing
- Langchain Output Parsing
- Guidance Pydantic Program
- Guidance for Sub-Question Query Engine
- OpenAI Pydantic Program
-
Output Parsing Modules
- Guardrails Output Parsing
- Langchain Output Parsing
- Guidance Pydantic Program
- Guidance for Sub-Question Query Engine
- OpenAI Pydantic Program
- Extracting names and locations from descriptions of people
- Extracting album data from music reviews
- Extracting information from emails
-
Multi-modal
- Advanced Multi-Modal Retrieval using GPT4V and Multi-Modal Index/Retriever
- Multi-modal retrieval with CLIP
- Image to Image Retrieval
- Semi-structured Image Retrieval
- Chroma Multi-Modal Demo with LlamaIndex
- Multi-Modal on PDF’s with tables.
- Multi-Modal LLM using Google’s Gemini model for image understanding and build Retrieval Augmented Generation with LlamaIndex
- Multimodal Ollama Cookbook
- Multi-Modal GPT4V Pydantic Program
- Retrieval-Augmented Image Captioning
- [Beta] Multi-modal ReAct Agent
- GPT4-V Experiments with General, Specific questions and Chain Of Thought (COT) Prompting Technique.
- Multi-Modal LLM using Replicate LlaVa, Fuyu 8B, MiniGPT4 models for image reasoning
- GPT4-V:
- Evaluating Multi-Modal RAG
- Multi-Modal LLM using OpenAI GPT-4V model for image reasoning
- Multi-Modal LLM using Replicate LlaVa, Fuyu 8B, MiniGPT4 models for image reasoning
- Building an LLM application
-
Using LLMs
- Privacy and Security
-
Loading Data (Ingestion)
- LlamaHub
-
Documents / Nodes
-
Defining and Customizing Documents
-
Metadata Extraction Usage Pattern
- 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
-
Ingestion Pipeline
- Transformations
- Advanced Ingestion Pipeline
- Async Ingestion Pipeline + Metadata Extraction
- Ingestion Pipeline + Document Management
- Redis Ingestion Pipeline
- Building a Live RAG Pipeline over Google Drive Files
- Parallelizing Ingestion Pipeline
- Querying
-
Putting It All Together
-
Q&A patterns
- A Guide to Extracting Terms and Definitions
- Knowledge Graphs
- Structured Data
- A Guide to LlamaIndex + Structured Data
- Airbyte SQL Index Guide
-
Full-Stack Web Application
- 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
- Build your own OpenAI Agent
- OpenAI Agent with Query Engine Tools
- OpenAI Agent Query Planning
- OpenAI Assistant Agent
- OpenAI Assistant Advanced Retrieval Cookbook
- OpenAI agent: specifying a forced function call
- Single-Turn Multi-Function Calling OpenAI Agents
- Context-Augmented OpenAI Agent
-
Full-Stack Projects
- create-llama Blog
- create-llama Repo
- create-llama Additional Templates
- SEC Insights App
- SEC Insights Repo
- Chat LlamaIndex App
- Chat LlamaIndex Repo
- RAGs Repo
- RAG CLI
- Tracing and Debugging
-
Evaluating
-
Cost Analysis
- Usage Pattern
-
Basic Strategies
- Accessing/Customizing Prompts within Higher-Level Modules
- Advanced Prompt Techniques (Variable Mappings, Functions)
- Advanced Prompt Techniques (Variable Mappings, Functions)
- Prompt Engineering for RAG
- BM25 Retriever
- Reciprocal Rerank Fusion Retriever
- Weaviate Vector Store - Hybrid Search
- Pinecone Vector Store - Hybrid Search
- Vector Store Index usage examples
-
Defining and Customizing Documents
-
Metadata Extraction Usage Pattern
- 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
- Defining and Customizing Nodes
-
Metadata Extraction Usage Pattern
- 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
- Multi-Tenancy RAG with LlamaIndex
-
Advanced Retrieval Strategies
- Query Transform Cookbook
-
Query Transformations
- HyDE Query Transform
- Multi-Step Query Engine
- Composable Objects
- DeepMemory (Activeloop)
- Weaviate Vector Store - Hybrid Search
- Pinecone Vector Store - Hybrid Search
-
Agentic strategies
-
Routers
- Router Query Engine
- Retriever Router Query Engine
- SQL Router Query Engine
- Router Retriever
-
Query Transformations
- 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
-
End-to-End Evaluation
- QuestionGeneration
- BatchEvalRunner - Running Multiple Evaluations
- Correctness Evaluator
- Faithfulness Evaluator
- Guideline Evaluator
- Pairwise Evaluator
- Relevancy Evaluator
- Embedding Similarity Evaluator
-
Component Wise Evaluation
- BEIR Out of Domain Benchmark
- HotpotQADistractor Demo
-
Evaluating
- Usage Pattern (Response Evaluation)
- Usage Pattern (Retrieval)
-
Modules
- Faithfulness Evaluator
- Relevancy Evaluator
- Answer Relevancy and Context Relevancy Evaluations
- 🚀 RAG/LLM Evaluators - DeepEval
- Guideline Evaluator
- Correctness Evaluator
- Embedding Similarity Evaluator
- QuestionGeneration
- BatchEvalRunner - Running Multiple Evaluations
- Evaluating Multi-Modal RAG
- Retrieval Evaluation
-
Evaluating With
LabelledRagDataset’s-
Benchmarking RAG Pipelines With A
LabelledRagDatatset - Downloading a LlamaDataset from LlamaHub
-
Contributing A
LabelledRagDataset-
LlamaDatasetSubmission Template Notebook -
Component Wise Evaluation
- BEIR Out of Domain Benchmark
- HotpotQADistractor Demo
-
End-to-End Evaluation
- QuestionGeneration
- BatchEvalRunner - Running Multiple Evaluations
- Correctness Evaluator
- Faithfulness Evaluator
- Guideline Evaluator
- Pairwise Evaluator
- Relevancy Evaluator
- Embedding Similarity Evaluator
-
Fine-tuning
- Fine-tuning an Adapter
- Embedding Fine-tuning Guide
- Router Fine-tuning
- 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
- [WIP] Function Calling Fine-tuning
- GPT-3.5 Fine-tuning Notebook (Colab)
- GPT-3.5 Fine-tuning Notebook (in Repo)
- OpenAI Function Calling Fine-tuning
- Llama2 Structured Output Fine-tuning
- Llama 2 Text-to-SQL Fine-tuning (w/ Gradient.AI)
- Llama 2 Text-to-SQL Fine-tuning (w/ Modal, Repo)
- Llama 2 Text-to-SQL Fine-tuning (w/ Modal, Notebook)
- Knowledge Distillation For Fine-Tuning A GPT-3.5 Judge (Correctness)
- Knowledge Distillation For Fine-Tuning A GPT-3.5 Judge (Pairwise)
- Cross-Encoder Finetuning
- Finetuning Llama 2 for Text-to-SQL
- Finetuning GPT-3.5 to Distill GPT-4
- Cohere Custom Reranker
-
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)
- 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
- Writing Custom Modules
-
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 Evaluation from Scratch
- Building Hybrid Search from Scratch
- Building a Router from Scratch
- Building an Advanced Fusion Retriever from Scratch
- Query Pipeline for Advanced Text-to-SQL
- Query Pipeline over Pandas DataFrames
-
Models
-
Using LLMs
- Using LLMs as standalone modules
- Customizing LLMs within LlamaIndex Abstractions
-
Available LLM integrations
- Anthropic
- Anyscale
- Bedrock
- Connect to Bedrock with Access Keys
- Clarifai LLM
- Cohere
- DashScope LLMS
- Multi-Modal LLM using DashScope qwen-vl model for image reasoning
- EverlyAI
- Fireworks
- Friendli
- Gradient Base Model
- Gradient Model Adapter
- HuggingFace LLM - Camel-5b
- HuggingFace LLM - StableLM
- Local Llama2 + VectorStoreIndex
- Konko
- LangChain LLM
- LiteLLM
- Llama API
- LlamaCPP
- LocalAI
- Maritalk
- MistralAI
- MistralAI Cookbook
- Monster API <> LLamaIndex
- MyMagic AI LLM
- Neutrino AI
- Nvidia TensorRT-LLM
- Nvidia Triton
- Ollama - Llama 2 7B
- OpenAI
- Azure OpenAI
- OpenLLM
- OpenRouter
- Perplexity
- Portkey
- Predibase
- Replicate - Llama 2 13B
- Replicate - Vicuna 13B
- Llama2 + VectorStoreIndex
- RunGPT
- Setup
- Interacting with LLM deployed in Amazon SageMaker Endpoint with LlamaIndex
- Together AI LLM
- Getting Started
- Basic auth example for service account
- Streaming Usage
- Chat Usage
- Async Chat
- Streaming Chat
- Gemini Models
- Install Vllm
- Orca-7b Completion Example
- LLama-2-7b Completion Example
- mistral chat 7b Completion Example
- Api Response
- Xorbits Inference
-
Embeddings
- Azure OpenAI
- Embeddings with Clarifai
- CohereAI Embeddings
- Custom Embeddings
- Elasticsearch Embeddings
- Qdrant FastEmbed Embeddings
- Google PaLM Embeddings
- Gradient Embeddings
- Anyscale Embeddings
- Local Embeddings with HuggingFace
- Jina Embeddings
- LangChain Embeddings
- LLMRails Embeddings
- MistralAI Embeddings
- OpenAI Embeddings
- Interacting with Embeddings deployed in Amazon SageMaker Endpoint with LlamaIndex
- Text Embedding Inference
- Together AI Embeddings
- Voyage Embeddings
- Nomic Embedding
- Fireworks Embeddings
-
Prompts
- Usage Pattern
- Completion prompts
- Chat prompts
- Accessing/Customizing Prompts within Higher-Level Modules
- Advanced Prompt Techniques (Variable Mappings, Functions)
- Prompt Engineering for RAG
- “Optimization by Prompting” for RAG
- EmotionPrompt in RAG
- Using local models
- Run Llama2 locally
-
Embeddings
- Azure OpenAI
- Embeddings with Clarifai
- CohereAI Embeddings
- Custom Embeddings
- Elasticsearch Embeddings
- Qdrant FastEmbed Embeddings
- Google PaLM Embeddings
- Gradient Embeddings
- Anyscale Embeddings
- Local Embeddings with HuggingFace
- Jina Embeddings
- LangChain Embeddings
- LLMRails Embeddings
- MistralAI Embeddings
- OpenAI Embeddings
- Interacting with Embeddings deployed in Amazon SageMaker Endpoint with LlamaIndex
- Text Embedding Inference
- Together AI Embeddings
- Voyage Embeddings
- Nomic Embedding
- Fireworks Embeddings
-
[Beta] Multi-modal models
- Multi-Modal LLM using OpenAI GPT-4V model for image reasoning
- Multi-Modal LLM using Google’s Gemini model for image understanding and build Retrieval Augmented Generation with LlamaIndex
- Multi-Modal LLM using Replicate LlaVa, Fuyu 8B, MiniGPT4 models for image reasoning
- Multi-Modal GPT4V Pydantic Program
- GPT4-V Experiments with General, Specific questions and Chain Of Thought (COT) Prompting Technique.
- Retrieval-Augmented Image Captioning
- Multi-Modal LLM using Anthropic model for image reasoning
- Advanced Multi-Modal Retrieval using GPT4V and Multi-Modal Index/Retriever
- Multi-Modal on PDF’s with tables.
- Multi-Modal Retrieval using GPT text embedding and CLIP image embedding for Wikipedia Articles
- Image to Image Retrieval using CLIP embedding and image correlation reasoning using GPT4V
- Chroma Multi-Modal Demo with LlamaIndex
- Evaluating Multi-Modal RAG
- Chat prompts
- Accessing/Customizing Prompts within Higher-Level Modules
- Advanced Prompt Techniques (Variable Mappings, Functions)
- Prompt Engineering for RAG
- “Optimization by Prompting” for RAG
- EmotionPrompt in RAG
-
Loading Data
-
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
- Pathway 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
-
Metadata Extraction Usage Pattern
- 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
-
Ingestion Pipeline
- Transformations
- Advanced Ingestion Pipeline
- Async Ingestion Pipeline + Metadata Extraction
- Ingestion Pipeline + Document Management
- Redis Ingestion Pipeline
- Building a Live RAG Pipeline over Google Drive Files
- Parallelizing Ingestion Pipeline
-
Indexing
- LlamaCloudIndex + LlamaCloudRetriever
-
Using VectorStoreIndex
-
Metadata Extraction
- 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
- Document Management
- Vector Store Index usage examples
- Composable Objects
- How Each Index Works
-
Module Guides
-
VectorStoreIndex
-
Metadata Extraction
- 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
- Document Management
- Vector Store Index usage examples
- Composable Objects
- Summary Index
- Tree Index
- Keyword Table Index
- Knowledge Graph Index
- Knowledge Graph Query Engine
- Knowledge Graph RAG Query Engine
- REBEL + Knowledge Graph Index
- REBEL + Wikipedia Filtering
- SQL Index
- SQL Query Engine with LlamaIndex + DuckDB
- Document Summary Index
-
The
ObjectIndexClass -
Vector Stores
- Astra DB
- Simple Vector Store - Async Index Creation
- Azure AI Search
- Azure CosmosDB MongoDB Vector Store
- Cassandra Vector Store
- Chroma
- DashVector Vector Store
- Deep Lake Vector Store Quickstart
- DocArray Hnsw Vector Store
- DocArray InMemory Vector Store
- DuckDB
- Epsilla Vector Store
- Jaguar Vector Store
- LanceDB Vector Store
- Lantern Vector Store
- Metal Vector Store
- Milvus Vector Store
- MyScale Vector Store
- Elasticsearch Vector Store
- Faiss Vector Store
- MongoDB Atlas
- Neo4j vector store
- Opensearch Vector Store
- Pinecone Vector Store
- Pinecone Vector Store - Hybrid Search
- pgvecto.rs
- Postgres Vector Store
- Redis Vector Store
- Qdrant Vector Store
- Qdrant Hybrid Search
- Rockset Vector Store
- Simple Vector Store
- Supabase Vector Store
- Tair Vector Store
- Tencent Cloud VectorDB
- Timescale Vector Store (PostgreSQL)
- Weaviate Vector Store
- Weaviate Vector Store - Hybrid Search
- Zep Vector Store
- 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
- Chat Stores
-
Querying
-
Query Pipeline
- Usage Pattern
- Module Usage
-
Module Guides
- An Introduction to LlamaIndex Query Pipelines
- Query Pipeline with Async/Parallel Execution
- Query Pipeline over Pandas DataFrames
- Query Pipeline for Advanced Text-to-SQL
- Building an Agent around a Query Pipeline
-
Query Engine
-
Usage Pattern
- Response Modes
- Streaming
-
Module Guides
- Custom Query Engine
- Retriever Query Engine
- Text-to-SQL Guide (Query Engine + Retriever)
- JSON Query Engine
- Pandas Query Engine
- JSONalyze Query Engine
- Knowledge Graph Query Engine
- Knowledge Graph RAG Query Engine
- Structured Hierarchical Retrieval
- 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
- [Beta] Text-to-SQL with PGVector
- SQL Query Engine with LlamaIndex + DuckDB
- Retry Query Engine
- CitationQueryEngine
- Recursive Retriever + Query Engine Demo
- Joint Tabular/Semantic QA over Tesla 10K
- Recursive Retriever + Document Agents
- Ensemble Query Engine Guide
- Sub Question Query Engine
- Recursive Retriever + Document Agents
- Multi-Document Agents
- Multi-Document Agents (V1)
- 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
- Condense Question Chat Engine
- Context Chat Engine
- Context Plus Condense Chat Engine
- Simple Chat Engine
-
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
- Multi-Document Agents
- GPT Builder Demo
- Single-Turn Multi-Function Calling OpenAI Agents
- OpenAI Assistant Agent
- Benchmarking OpenAI Retrieval API (through Assistant Agent)
- OpenAI Assistant Advanced Retrieval Cookbook
- ReAct Agent - A Simple Intro with Calculator Tools
- ReAct Agent with Query Engine (RAG) Tools
- LLMCompiler Agent Cookbook
- Building a Custom Agent
- Building an Agent around a Query Pipeline
- Step-wise, Controllable Agents
- Controllable Agents for RAG
- Controllable Agents for RAG
-
Tools
- Usage Pattern
- LlamaHub Tools Guide
- Lower-Level Agent API
-
Retriever
- Retriever Modes
-
Retriever Modules
- Define Custom Retriever
- BM25 Hybrid Retriever
- Simple Fusion Retriever
- Reciprocal Rerank Fusion Retriever
- Relative Score Fusion and Distribution-Based Score Fusion
- Auto Merging Retriever
- Metadata Replacement + Node Sentence Window
- Composable Objects
- A Simple to Advanced Guide with Auto-Retrieval (with Pinecone + Arize Phoenix)
- Auto-Retrieval (with Lantern)
- Auto-Retrieval (with Chroma)
- Auto-Retrieval (with BagelDB)
- Structured Hierarchical Retrieval
- Auto-Retrieval from a Vectara Index
- Knowledge Graph RAG Retriever
- Recursive Retriever + Query Engine Demo
- Recursive Retriever + Node References
- Recursive Retriever + Node References + Braintrust
- Router Retriever
- Ensemble Retrieval Guide
- Google Generative Language Semantic Retriever
- Structured Hierarchical Retrieval
- Google Generative Language Semantic Retriever
- Vectara Managed Index
- Managed Index with Zilliz Cloud Pipelines
- VideoDB Retriever
- Chunk + Document Hybrid Retrieval with Long-Context Embeddings (Together.ai)
- You.com Retriever
- Text-to-SQL Guide (Query Engine + Retriever)
- DeepMemory (Activeloop)
- Pathway Retriever
-
Response Synthesizer
-
Response Synthesis Modules
- Refine
- Refine with Structured Answer Filtering
- Tree Summarize
- Pydantic Tree Summarize
-
Node Postprocessor
-
Node Postprocessor 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
- RankGPT Reranker Demonstration (Van Gogh Wiki)
- Colbert Rerank
- Jina Rerank
- mixedbread Rerank Cookbook
-
Structured Outputs
-
Pydantic Program
- LLM Pydantic Program
- OpenAI Pydantic Program
- Guidance Pydantic Program
- Guidance for Sub-Question Query Engine
- DataFrame Structured Data Extraction
- Evaporate Demo
-
Query Engines + Pydantic Outputs
- Query Engine with Pydantic Outputs
- Pydantic Tree Summarize
- Download Data
-
Output Parsing Modules
- Guardrails Output Parsing
- Langchain Output Parsing
- Guidance Pydantic Program
- Guidance for Sub-Question Query Engine
- OpenAI Pydantic Program
-
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
- Multi-Document Agents
- GPT Builder Demo
- Single-Turn Multi-Function Calling OpenAI Agents
- OpenAI Assistant Agent
- Benchmarking OpenAI Retrieval API (through Assistant Agent)
- OpenAI Assistant Advanced Retrieval Cookbook
- ReAct Agent - A Simple Intro with Calculator Tools
- ReAct Agent with Query Engine (RAG) Tools
- LLMCompiler Agent Cookbook
- Building a Custom Agent
- Building an Agent around a Query Pipeline
- Step-wise, Controllable Agents
- Controllable Agents for RAG
- Controllable Agents for RAG
-
Tools
- Usage Pattern
- LlamaHub Tools Guide
- Lower-Level Agent API
-
Observability
- Langfuse Callback Handler
- Wandb Callback Handler
- Observability with OpenLLMetry
- Arize Phoenix Tracing Tutorial
- OpenInference Callback Handler + Arize Phoenix
- Evaluating Search and Retrieval with Arize Phoenix
- Evaluating and Tracking with TruLens
- Quickstart Guide with LlamaIndex + TruLens
- Colab
- HoneyHive LlamaIndex Tracer
- PromptLayer Handler
-
Callbacks
- Langfuse Callback Handler
- Token Counting Handler
- Llama Debug Handler
- Wandb Callback Handler
- Aim Callback
- OpenInference Callback Handler + Arize Phoenix
- Token Counting - Migration Guide
-
Evaluating
- Usage Pattern (Response Evaluation)
- Usage Pattern (Retrieval)
-
Modules
- Faithfulness Evaluator
- Relevancy Evaluator
- Answer Relevancy and Context Relevancy Evaluations
- 🚀 RAG/LLM Evaluators - DeepEval
- Guideline Evaluator
- Correctness Evaluator
- Embedding Similarity Evaluator
- QuestionGeneration
- BatchEvalRunner - Running Multiple Evaluations
- Evaluating Multi-Modal RAG
- Retrieval Evaluation
-
Evaluating With
LabelledRagDataset’s-
Benchmarking RAG Pipelines With A
LabelledRagDatatset - Downloading a LlamaDataset from LlamaHub
-
Contributing A
LabelledRagDataset-
LlamaDatasetSubmission Template Notebook - Prompt Templates
-
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
- Condense Plus Context Chat Engine
- Query Bundle
- Query Transform
-
Data Connectors
- BasePydanticReader
- BaseReader
- ReaderConfig
- Response
-
Service Context
- Embeddings
- OpenAIEmbedding
- HuggingFaceEmbedding
- OptimumEmbedding
- InstructorEmbedding
- LangchainEmbedding
- GoogleUnivSentEncoderEmbedding
-
Node Parser
- get_leaf_nodes
- get_root_nodes
- get_child_nodes
- get_deeper_nodes
- TokenTextSplitter
- SentenceSplitter
- CodeSplitter
- SimpleFileNodeParser
- HTMLNodeParser
- MarkdownNodeParser
- JSONNodeParser
- SentenceWindowNodeParser
- SemanticSplitterNodeParser
- NodeParser
- HierarchicalNodeParser
- TextSplitter
- MarkdownElementNodeParser
- MetadataAwareTextSplitter
- LangchainNodeParser
- UnstructuredElementNodeParser
- SimpleNodeParser
- PromptHelper
-
Storage Context
- Document Store
- Index Store
-
Vector Store
- VectorStoreQuery
- VectorStoreQueryResult
- MetadataFilters
- MetadataFilter
- MetadataInfo
- ExactMatchFilter
- FilterCondition
- FilterOperator
- SimpleVectorStore
- VectorStoreInfo
- KV Storage
- Loading Indices
- Structured Index Configuration
-
Integrations
-
Llama Packs 🦙📦
- Llama Packs Example
- Llama Pack - Resume Screener 📄
- Ollama Llama Pack Example
-
Observability
- Langfuse Callback Handler
- Wandb Callback Handler
- Observability with OpenLLMetry
- Arize Phoenix Tracing Tutorial
- OpenInference Callback Handler + Arize Phoenix
- Evaluating Search and Retrieval with Arize Phoenix
- Evaluating and Tracking with TruLens
- Quickstart Guide with LlamaIndex + TruLens
- Colab
- HoneyHive LlamaIndex Tracer
- PromptLayer Handler
-
Callbacks
- Langfuse Callback Handler
- Token Counting Handler
- Llama Debug Handler
- Wandb Callback Handler
- Aim Callback
- OpenInference Callback Handler + Arize Phoenix
- Token Counting - Migration Guide
- Perform Evaluations on LlamaIndex with UpTrain
- How to go about it?
-
1. Using the UpTrain Callback Handler
- 1. RAG Query Engine Evaluation
- 2. Sub-Question Query Engine Evaluation
- 3. Re-ranking
- 3b. Re-ranking (With different number of nodes)
- UpTrain’s Managed Service Dashboard and Insights
-
2. Using EvalLlamaIndex
- Alternative 1: Evaluate using UpTrain’s Open-Source Software (OSS)
- Alternative 2: Evaluate using UpTrain’s Managed Service and Dashboards
- Unit Testing LLMs/RAG With DeepEval
- Tracing with Graphsignal
- Evaluating and Tracking with TruLens
- Guidance
- LM Format Enforcer
- Guardrails
- OpenAI Function Calling
-
Using Vector Stores
- Astra DB
- Simple Vector Store - Async Index Creation
- Azure AI Search
- Azure CosmosDB MongoDB Vector Store
- Cassandra Vector Store
- Chroma
- DashVector Vector Store
- Deep Lake Vector Store Quickstart
- DocArray Hnsw Vector Store
- DocArray InMemory Vector Store
- Epsilla Vector Store
- LanceDB Vector Store
- Lantern Vector Store
- Metal Vector Store
- Milvus Vector Store
- MyScale Vector Store
- Elasticsearch Vector Store
- Faiss Vector Store
- MongoDB Atlas
- Neo4j vector store
- Opensearch Vector Store
- Pinecone Vector Store
- Pinecone Vector Store - Hybrid Search
- pgvecto.rs
- Postgres Vector Store
- Redis Vector Store
- Qdrant Vector Store
- Qdrant Hybrid Search
- Rockset Vector Store
- Simple Vector Store
- Supabase Vector Store
- Tair Vector Store
- Tencent Cloud VectorDB
- Timescale Vector Store (PostgreSQL)
- Upstash Vector Store
- Weaviate Vector Store
- Weaviate Vector Store - Hybrid Search
- Zep Vector Store
-
Using Graph Stores
- Neo4j Graph Store
- Nebula Graph Store
- Knowledge Graph Query Engine
- Kuzu Graph Store
- FalkorDB Graph Store
-
Using Managed Indices
- Google Generative Language Semantic Retriever
- Vectara Managed Index
- Auto-Retrieval from a Vectara Index
- Managed Index with Zilliz Cloud Pipelines
- Using with Langchain 🦜🔗
- Streamlit
- Chainlit
- LlamaIndex + Ray
- ChatGPT Plugin Integrations
- Airbyte
- Fleet Context Embeddings - Building a Hybrid Search Engine for the Llamaindex Library
-
Frequently Asked Questions (FAQ)
- Large Language Models
- Embeddings
- Vector Database
- Query Engines
- Chat Engines
- Documents and Nodes
-
Full-Stack Projects
- create-llama Blog
- create-llama Repo
- create-llama Additional Templates
- SEC Insights App
- SEC Insights Repo
- Chat LlamaIndex App
- Chat LlamaIndex Repo
- RAGs Repo
- RAG CLI
- Contributing to LlamaIndex
- Documentation Guide
- ChangeLog
- Deprecated Terms
Contributing
Changes
HuggingFace LLM - StableLM #
If you’re opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
-
Llama Packs 🦙📦
Community
-
Retrievers
-
-
Benchmarking RAG Pipelines With A
-
Pydantic Program
-
Node Postprocessor Modules
-
Response Synthesis Modules
-
Query Transformations
-
Usage Pattern
-
Query Pipeline
-
Metadata Extraction
-
VectorStoreIndex
-
Metadata Extraction
-
Metadata Extraction Usage Pattern
-
Defining and Customizing Documents
-
Data Connectors (LlamaHub)
-
Using LLMs
Module Guides
-
-
Benchmarking RAG Pipelines With A
-
End-to-End Evaluation
-
Routers
-
Metadata Extraction Usage Pattern
-
Cost Analysis
-
Q&A patterns
-
Metadata Extraction Usage Pattern
-
Defining and Customizing Documents
Understanding
-
Pydantic Program
-
Structured Outputs
-
Routers