mirror of
https://github.com/imartinez/privateGPT.git
synced 2025-04-28 03:32:18 +00:00
45f05711eb
* Extract optional dependencies * Separate local mode into llms-llama-cpp and embeddings-huggingface for clarity * Support Ollama embeddings * Upgrade to llamaindex 0.10.14. Remove legacy use of ServiceContext in ContextChatEngine * Fix vector retriever filters
25 lines
566 B
YAML
25 lines
566 B
YAML
server:
|
|
env_name: ${APP_ENV:prod}
|
|
port: ${PORT:8080}
|
|
|
|
llm:
|
|
mode: ${PGPT_MODE:mock}
|
|
|
|
embedding:
|
|
mode: ${PGPT_MODE:sagemaker}
|
|
|
|
llamacpp:
|
|
llm_hf_repo_id: ${PGPT_HF_REPO_ID:TheBloke/Mistral-7B-Instruct-v0.1-GGUF}
|
|
llm_hf_model_file: ${PGPT_HF_MODEL_FILE:mistral-7b-instruct-v0.1.Q4_K_M.gguf}
|
|
|
|
huggingface:
|
|
embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:BAAI/bge-small-en-v1.5}
|
|
|
|
sagemaker:
|
|
llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}
|
|
embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:}
|
|
|
|
ui:
|
|
enabled: true
|
|
path: /
|