quivr
quivr copied to clipboard
Open-source RAG Framework for building GenAI Second Brains 🧠 Build productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthrop...
Add structured logging
There is concurrency issue with linking km to brain steps and removing the knowledge. * Link knowledge to brain : * Links the knowledge and children to the brain. (...
This PR contains the following updates: | Package | Change | Age | Adoption | Passing | Confidence | |---|---|---|---|---|---| | [langchain](https://redirect.github.com/langchain-ai/langchain) ([changelog](https://redirect.github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain%3D%3D0%22&expanded=true)) | `>=0.2.14, `>=0.3.1,
test with 406 knowledges takes \~2s to load. this is too slow Looking in profiling, serialization takes a lot of time. We are using pydantic v2 I think. I dont...
Process notion sync
* define failure mode and what to do * Sync files are processed in the same celery tasks (for limiting reason): * Define what to do if a sync knowledge...
* shouldn't remove knowledge from the KMS * if KM is folder remove all subsequent children from brain * Check what rules apply for the syncs vs local knowledge