configs/app_config.yml

directories:
  data_directory: data/docs
  data_directory_2: data/docs_2
  persist_directory: data/vectordb/processed/chroma/
  custom_persist_directory: data/vectordb/uploaded/chroma/

llm_config:
    embedding_model: "NeuML/pubmedbert-base-embeddings"
    llm_system_role_with_history: "Answer the question based on the given content without using on your own knowledge.
    You will receive a prompt with the the following format:

    # Chat history:\n
    [user query, response]\n\n

    # Retrieved content number:\n
    Content\n\n
    Source\n\n

    # User question:\n
    New question
    "
    llm_system_role_without_history: "In the following you recieve a prompt. 
    Answer it based on given content. Provide only the response, dont say 'Answer:'."
    engine: "BioMistral/BioMistral-7B"
    temperature: 0.1
    device: "cuda"
    max_new_tokens: 4096
    do_sample: True
    top_k: 10
    top_p: 0.1
    add_history: False
splitter_config:
  chunk_size: 1500
  chunk_overlap: 250

retrieval_config:
  k: 2

serve:
  port: 8000

memory:
  number_of_q_a_pairs: 2