paper-qa
paper-qa copied to clipboard
Future-House
High accuracy RAG for answering questions from scientific documents with citations
I'm running in jupyter notebook with paper-qa==5.3.0, tyring to use an alternative OPENAI compatiable api. here is my script ```python # make sure to run in jupyter import os import...
Coming from https://github.com/Future-House/paper-qa/pull/628#issuecomment-2435055914. A huge speedup can be attained by moving our indexing's `paperqa.agents.search.process_file` implementation from `asyncio` to `multiprocessing`.
Hello, I saw in the code there is only only one fixed size chunking strategy. I read there are many chunking strategies (https://stackoverflow.blog/2024/06/06/breaking-up-is-hard-to-do-chunking-in-rag-applications/) Is it planned to implement other chunking...
Hello, After reading repro doc, reading posts and asking a lot of questions, I wonder if a complete API documentation is planned by developpement team. I know the API is...
Hello, I finally managed to use a local embedding model (mxbai-embed-large-v1) using new SentenceTransformerEmbeddingModel class (thenks to developper team for this work !!! ;-)). ``` sparse_embedding_model = SparseEmbeddingModel(ndim=4096) sentence_transformer =...
Hello, I'm trying to setting up a local SentenceTransformerEmbeddingModel : ``` sentence_transformer = SentenceTransformerEmbeddingModel(name='my-embedding-model', config=dict( model=f"openai/my-embedding-model", api_base="http://192.168.1.15:8081/v1/", api_key="sk-no-key-required", ) ) ``` I got this error : ``` No sentence-transformers model...
I use the following CLI command from the README for incorporating a rate limit into my response ``` pqa --summary_llm_config '{"rate_limit": {"gpt-4o-2024-08-06": "30000 per 1 minute"}}' ask 'Are there nm...
Hello, I tried to execute the same query with sync and async methods : See here : https://github.com/Future-House/paper-qa?tab=readme-ov-file#adding-documents-manually But both methods takes the same amount of time... Is it something...
Hello, I changed batch size from 1 (default) to 8, 32 and saw no changes on paperQA behavioural (answer quality end speed), as follows : ``` settings=Settings( llm=f"openai/mixtral:8x7b", llm_config=local_llm_config, summary_llm=f"openai/mixtral:8x7b",...
Hello, I recently updated paper-qa and now get this error : ``` Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'. InMemoryCache: set_cache....
Metadata
Owner
Metadata
High accuracy RAG for answering questions from scientific documents with citations