I am using PrivateGPT to chat with a PDF document. I ask a question and get an answer. If I am okay with the answer, and the same question is asked again, I want the previous answer instead of creating a new one. How can I handle this? Are there any options available?
settings-local.yaml
llm:
mode: llamacpp
max_new_tokens: 512
context_window: 3900
tokenizer: mistralai/Mistral-7B-Instruct-v0.2
llamacpp:
prompt_style: "mistral"
llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
embedding:
mode: huggingface
huggingface:
embedding_hf_model_name: BAAI/bge-small-en-v1.5
vectorstore:
database: qdrant
qdrant:
path: local_data/private_gpt/qdrant