JPonsa

PatientEligibility is a signature ```python class PatientEligibility(dspy.Signature): "Given a patient description, produce a list of 5 or less clinical trials ids where tha patient would be eligible for enrolment." patient_note:str...

+1

The models persist with a large dataset Please, see below an example fo the documents [Document(page_content='{"NCT00000173": {"protocolSection": {"identificationModule": {"nctId": "NCT00000173", "organization": {"fullName": "National Institute on Aging (NIA)", "class": "NIH"}, "briefTitle":...

@jjmachan have you been able to reproduce the issue? I am using publicly available data so happy to share the code with you in case you need to reproduce it.

Same here running enerator.generate_with_langchain_docs ```python from langchain_community.llms import VLLM generator_llm = VLLM(model=args.generator, trust_remote_code=True, # mandatory for hf models max_new_tokens=128, top_k=10, top_p=0.95, temperature=0.8, dtype="half", enforce_eager=True ) critic_llm = generator_llm.copy() embeddings =...

@omkar-334, thanks for spotting that. This was a typo when copying the code into the ticket. I am passing them as an argument to my script. In my code it...

@TomeHirata I understand the decision of removing the community retrievers as an architectural decision. However, is there a way to document them as examples in the DSPy documentation so the...

This was fixed in https://github.com/langchain-ai/langchain/pull/19119 The code in the main branch looks correct. However, the bug still exists in the version I get by doing pip install