A Streamlit app for querying and comparing responses from multiple Language Models (ChatGPT, Claude, Llama 3, Gemma) simultaneously.
-
Updated
Jul 25, 2024 - Python
#
multi-query
Here are 5 public repositories matching this topic...
Transformer attention, worked through numerically; from self-attention and RoPE to KV cache, MQA, and GQA.
nlp key-value transformers pytorch attention attention-mechanism nlp-machine-learning attention-model attention-is-all-you-need multi-query attention-mechanisms pytorch-implementation multi-query-attention kv-cache transformers-models grouped-query-attention key-value-cache kv-cache-optimization kv-cache-management
-
Updated
Aug 18, 2026 - Python
Compare 4 RAG query transformation techniques side by side — Rewrite, Multi-Query, Step-Back and HyDE
python nlp openai document-retrieval hyde multi-query rag streamlit llm generative-ai langchain llmops langchain-python retrieval-augmented-generation query-transformations
-
Updated
Apr 7, 2026 - Python
Agentic RAG for financial document analysis. Hybrid retrieval (BM25 + FAISS + multi-query + FlashRank rerank) and a LangChain ReAct agent, with RAGAS quantitative evaluation (faithfulness 0.20 → 0.60).
financial-analysis bm25 multi-query faiss rag fastapi langchain hybrid-retrieval react-agent ragas agentic-rag
-
Updated
May 1, 2026 - Python
Retrieval-Augment Generation with Citation
-
Updated
May 12, 2026 - Python
Add this topic to your repo
To associate your repository with the multi-query topic, visit your repo's landing page and select "manage topics."