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...
Current generate query: ``` EXPLAIN ANALYZE WITH RECURSIVE knowledge_tree(id, file_name, url, extension, status, SOURCE, source_link, file_size, file_sha1, created_at, updated_at, metadata, is_folder, user_id, parent_id, sync_id, sync_file_id) AS (SELECT knowledge_1.id AS id,...
We need to be able to easily pass different prompts / prompt IDs to our LangGraph nodes, for instance via a metadata dictionary, then use the prompt service to collect...
Currently, all nodes used in our retrieval pipeline are defined in the `QuivrQARAGLangGraph` class in `backend/core/quivr_core/quivr_rag_langgraph.py`. We want to enable nodes to be defined in external (proprietary) modules, for instance...
* Should process a knowledge instance (syncs or local) * Takes a KnowledgeDTO Object * If Local * Build file -> downloads from S3 using SupabaseS3Storage(knowledge_id) * Skip * If...
This PR contains the following updates: | Package | Type | Update | Change | |---|---|---|---| | [actions/checkout](https://redirect.github.com/actions/checkout) | action | major | `v3` -> `v4` | --- ### Release...
# Description Please include a summary of the changes and the related issue. Please also include relevant motivation and context. ## Checklist before requesting a review Please delete options that...
* Most TPM routes : /user /user/identity /user/settings : 0.176 t/min * Slowing down all routes * Should be written to user Postgres directly IF NECESSARY 1: * Add caching...
[https://quivr-brain.sentry.io/performance/trace/c48989fba52d43fe918cb8edd1cd9b8d/?environment=production&fov=0%2C538.625&node=span-a4d6f76b8e608621&node=txn-7cc8826f05934c3f87c628f3addac2e3&project=4505455607808000&query=http.method%3ADELETE&referrer=performance-transaction-summary&source=performance_transaction_summary&statsPeriod=7d×tamp=1726539141&transaction=%2Fknowledge%2F%7Bknowledge_id%7D&unselectedSeries=p100%28%29&unselectedSeries=avg%28%29](https://quivr-brain.sentry.io/performance/trace/c48989fba52d43fe918cb8edd1cd9b8d/?environment=production&fov=0%2C538.625&node=span-a4d6f76b8e608621&node=txn-7cc8826f05934c3f87c628f3addac2e3&project=4505455607808000&query=http.method%3ADELETE&referrer=performance-transaction-summary&source=performance_transaction_summary&statsPeriod=7d×tamp=1726539141&transaction=%2Fknowledge%2F%7Bknowledge_id%7D&unselectedSeries=p100%28%29&unselectedSeries=avg%28%29)Shouldnt block on supbase slow delete
[https://quivr-brain.sentry.io/performance/trace/f1030ff6332442f6955c8656ba2eac49/?environment=production&fov=165.7060546875%2C415.5721664428711&node=span-bc2495be04ccfb79&node=txn-75fb16b04606492f8dfa60c5989c3b3e&project=4505455607808000&query=http.method%3APOST&referrer=performance-transaction-summary&source=performance_transaction_summary&statsPeriod=7d×tamp=1726635285&transaction=%2Fbrains%2F&unselectedSeries=p100%28%29&unselectedSeries=avg%28%29](https://quivr-brain.sentry.io/performance/trace/f1030ff6332442f6955c8656ba2eac49/?environment=production&fov=165.7060546875%2C415.5721664428711&node=span-bc2495be04ccfb79&node=txn-75fb16b04606492f8dfa60c5989c3b3e&project=4505455607808000&query=http.method%3APOST&referrer=performance-transaction-summary&source=performance_transaction_summary&statsPeriod=7d×tamp=1726635285&transaction=%2Fbrains%2F&unselectedSeries=p100%28%29&unselectedSeries=avg%28%29) * Move openai meaning embedding to asynchronous operation or remove it
* Rewrite : syncs.get_files : * Move to async calls * Deal with pagination with caching