All projects

deepdoc

Oqura-ai/deepdoc

Deep research tool for local knowledge base.

Python
Stars
318
Forks
46

Why it is listed

A local-document research workflow using TypeSafe Jev to check and rerank Qdrant retrieval results and assess whether evidence covers required subsections. A separate generative LLM handles planning and report writing, so Jev is the evidence-decision layer rather than the prose generator.

Related projects

  • jev-recipes

    200+ plug-and-play Jev recipes: small, calibrated AI decisions that route, grade, gate, compare, and label text for agents, RAG, support, code review, and music. Import from JavaScript or TypeScript, or call the CLI with JSON from any language.

    Shared topics: jev-api, jev-model

  • jev-py-integration

    Jev System one AI model, very fast decision making engine. Jev AI will use input tokens but no output tokens

    Shared topics: jev-api, jev-model

  • duomind

    When Jev meets LLM -- Pair a small local LLM (System 2) with Jev model (System 1) to make small model more faster and accurate — OpenAI-compatible, private, and almost free to run in Kilo code and Cline.

    Shared topics: jev-api, jev-model