Hugging Face (Twitter)

RT @mishig25: At @huggingface, how we created doc chatbot system using open weights LLMs & open source software stack:

1. chunk & embed docs markdowns using open weights embedding models (BAAI/bge-base-en-v1.5, google/embeddinggemma-300m, we usually use http://hf.co/spaces/mteb/leaderboard to find the hottest models), use @meilisearch (http://github.com/meilisearch/meilisearch) as our semantic search db

2. hf.co/mcp that acts as gateway to semantically search hf docs (among other things). http://github.com/huggingface/hf-mcp-server by @evalstate

3. add hf.co/mcp to hf.co/chat, which uses latest open weights LLMs such as zai-org/GLM-4.6 (hf.co/models) through HF Inference Providers (http://hf.co/docs/inference-providers) that runs your inference through @FireworksAI_HQ, @togethercompute, @GroqInc, @novita_labs