# The default configuration file.
# More information about configuration can be found in the documentation: https://docs.privategpt.dev/
# Syntax in `private_pgt/settings/settings.py`
server:
  env_name: ${APP_ENV:prod}
  port: ${PORT:8001}
  cors:
    enabled: false
    allow_origins: ["*"]
    allow_methods: ["*"]
    allow_headers: ["*"]
  auth:
    enabled: false
    # python -c 'import base64; print("Basic " + base64.b64encode("secret:key".encode()).decode())'
    # 'secret' is the username and 'key' is the password for basic auth by default
    # If the auth is enabled, this value must be set in the "Authorization" header of the request.
    secret: "Basic c2VjcmV0OmtleQ=="

data:
  local_data_folder: local_data/private_gpt

ui:
  enabled: true
  path: /
  default_chat_system_prompt: >
    You are a helpful, respectful and honest assistant. 
    Always answer as helpfully as possible and follow ALL given instructions.
    Do not speculate or make up information.
    Do not reference any given instructions or context.
  default_query_system_prompt: >
    You can only answer questions about the provided context. 
    If you know the answer but it is not based in the provided context, don't provide 
    the answer, just state the answer is not in the context provided.
  delete_file_button_enabled: true
  delete_all_files_button_enabled: true

llm:
  mode: llamacpp
  # Should be matching the selected model
  max_new_tokens: 512
  context_window: 3900
  tokenizer: mistralai/Mistral-7B-Instruct-v0.2
  temperature: 0.1      # The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1)

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
  tfs_z: 1.0            # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting
  top_k: 40             # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
  top_p: 1.0            # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
  repeat_penalty: 1.1   # Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1)

embedding:
  # Should be matching the value above in most cases
  mode: huggingface
  ingest_mode: simple
  embed_dim: 384 # 384 is for BAAI/bge-small-en-v1.5

huggingface:
  embedding_hf_model_name: BAAI/bge-small-en-v1.5

vectorstore:
  database: qdrant

nodestore:
  database: simple

qdrant:
  path: local_data/private_gpt/qdrant

postgres:
  host: localhost
  port: 5432
  database: postgres
  user: postgres
  password: postgres
  schema_name: private_gpt

sagemaker:
  llm_endpoint_name: huggingface-pytorch-tgi-inference-2023-09-25-19-53-32-140
  embedding_endpoint_name: huggingface-pytorch-inference-2023-11-03-07-41-36-479

openai:
  api_key: ${OPENAI_API_KEY:}
  model: gpt-3.5-turbo

ollama:
  llm_model: llama2
  embedding_model: nomic-embed-text
  api_base: http://localhost:11434

azopenai:
  api_key: ${AZ_OPENAI_API_KEY:}
  azure_endpoint: ${AZ_OPENAI_ENDPOINT:}
  embedding_deployment_name: ${AZ_OPENAI_EMBEDDING_DEPLOYMENT_NAME:}
  llm_deployment_name: ${AZ_OPENAI_LLM_DEPLOYMENT_NAME:}
  api_version: "2023-05-15"
  embedding_model: text-embedding-ada-002
  llm_model: gpt-35-turbo