PageIndex

Open-source document RAG engine with local indexing and storage, page citations, and LLM retrieval over document trees. MIT licensed.

PageIndex is an open-source document RAG engine for developers building question answering over long PDFs, such as financial reports, legal documents and technical manuals. It organizes documents into a hierarchical tree and uses an LLM to find relevant sections, rather than relying on vector similarity search. It doesn't require a vector database or document chunking.

The Python SDK supports local indexing, retrieval and chat with your own LLM key. Document indexing and storage stay on your machine in local mode; model calls use the LLM you connect, so local mode doesn't itself mean offline inference. The MIT-licensed version focuses on text-based PDFs and provides page-level citations. Retrieval can take conversation history and domain knowledge into account, and it reads selected sections instead of sending the entire PDF for every question.

For applications, the SDK supports streaming responses and searches across multiple documents. You can connect its retrieval tools to the OpenAI Agents SDK or Claude Agent SDK. Its explicit document references help readers check answers against the original pages.

PageIndex Cloud runs document indexing and storage on PageIndex's servers. It adds OCR and image understanding for scanned or image-rich documents, block-level citations, and an MCP server. Chat and retrieval remain compatible with your chosen model provider. The cloud offering also has a file-level tree index for searching across a document corpus; dedicated VPC and on-premises deployments are available.

LLM Libraries and SDKs Chat With Your Documents Document Parsing for LLMs RAG Frameworks and Pipelines RAG Source citations Streaming inference Tool calling

Are you the owner or maker of PageIndex?

Claim this page with an email at pageindex.ai. PageIndex gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.

Want more people to find PageIndex?Promote it

Something wrong or outdated on this page?

Videos about PageIndex

View all PageIndex videos

PageIndex tutorial: vectorless RAG vs vector RAG

PageIndex

PageIndex and Codex: build vectorless RAG with Docker

PageIndex tutorial: vectorless RAG with OpenAI

PageIndex

Similar to PageIndex

View all tools

Similar to PageIndex

LightRAG

3 videos

An open-source RAG framework under the MIT license. Run it locally or in Docker with local models or hosted LLMs to query your documents.

39.9KUpdated 6 days agoMIT

macOS · Windows · Linux · Docker · Web#Knowledge graphs#LLM tracing#Multimodal input

LightRAG combines knowledge graphs with vector search to answer questions across a document collection. It's a self-hosted Python framework for developers building document assistants, particularly where answers depend on relationships between facts in different files, such as legal or financial material.

Chat With Your DocumentsDocument Parsing for LLMsRAG Frameworks and Pipelines

RAGFlow

1 video

An open-source RAG engine for document search and AI agents, with self-hosted deployment, hybrid retrieval, citations and a separate cloud service.

91.6KUpdated 23 hours agoApache-2.0

macOS · Windows · Linux · Docker#Hybrid search#MCP#Multi-agent workflows

LlamaIndex

4 videos

An MIT-licensed Python framework for document-based AI apps. It works with Ollama, while its separate document services run locally or in the cloud.

52.4KUpdated 13 hours agoMIT

#Ollama integration#RAG#Reranking

Morphik Core

A self-hosted multimodal retrieval engine for AI apps, with ColPali visual search, Docker deployment, and MCP access through Claude or Open Web UI.

3.7KUpdated 2 days ago

Docker · Web#MCP#Multi-user access#Multimodal input

Morphik Core is a self-hosted multimodal retrieval engine for developers building AI applications around visually rich documents. It searches diagrams, schematics, charts, and datasheets alongside text, so applications can retrieve information that text extraction alone can miss. You can run it on your own server, including through Docker, or use Morphik's hosted service.

Chonkie

An open-source RAG ingestion library for Python and JavaScript, with local processing, a self-hosted REST API, and an MIT license.

4.8KUpdated 1 month agoMIT

Docker#Agent Skills#Multilingual

Chonkie is an MIT-licensed, open-source library for developers preparing documents for retrieval-augmented generation (RAG). It combines text cleaning, chunking, embeddings and vector database ingestion, so you don't have to assemble each stage from separate libraries. It runs locally or in the cloud, with Python and JavaScript support and a self-hosted REST API that can run in Docker.

DocsGPT

Self-hosted AI document search and agents with source citations. Run local models through Ollama, vLLM or llama.cpp, including fully offline deployments.

18.3KUpdated 1 day agoMIT

macOS · Windows · Linux · Docker · Web#Human approval#Hybrid search#llama.cpp backend