43 lines
1.3 KiB
YAML
43 lines
1.3 KiB
YAML
server:
|
|
env_name: ${APP_ENV:prod}
|
|
port: ${PORT:8080}
|
|
|
|
llm:
|
|
mode: ${PGPT_MODE:mock}
|
|
|
|
embedding:
|
|
mode: ${PGPT_EMBED_MODE:mock}
|
|
|
|
llamacpp:
|
|
llm_hf_repo_id: ${PGPT_HF_REPO_ID:lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF}
|
|
llm_hf_model_file: ${PGPT_HF_MODEL_FILE:Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf}
|
|
|
|
huggingface:
|
|
embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:nomic-ai/nomic-embed-text-v1.5}
|
|
|
|
sagemaker:
|
|
llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}
|
|
embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:}
|
|
|
|
ollama:
|
|
#llm_model: ${PGPT_OLLAMA_LLM_MODEL:llama3:8b-instruct-q4_K_M}
|
|
#llm_model: llama3:8b-instruct-q4_K_M
|
|
llm_model: qwen3:14b
|
|
context_window: 5000
|
|
# llm_model: gemma3:12b
|
|
# llm_model: deepseek-r1:14b
|
|
embedding_model: ${PGPT_OLLAMA_EMBEDDING_MODEL:mxbai-embed-large}
|
|
api_base: ${PGPT_OLLAMA_API_BASE:http://ollama:11434}
|
|
embedding_api_base: ${PGPT_OLLAMA_EMBEDDING_API_BASE:http://ollama:11434}
|
|
tfs_z: ${PGPT_OLLAMA_TFS_Z:1.0}
|
|
top_k: ${PGPT_OLLAMA_TOP_K:40}
|
|
top_p: ${PGPT_OLLAMA_TOP_P:0.9}
|
|
repeat_last_n: ${PGPT_OLLAMA_REPEAT_LAST_N:64}
|
|
repeat_penalty: ${PGPT_OLLAMA_REPEAT_PENALTY:1.2}
|
|
request_timeout: ${PGPT_OLLAMA_REQUEST_TIMEOUT:6000.0}
|
|
autopull_models: ${PGPT_OLLAMA_AUTOPULL_MODELS:true}
|
|
|
|
ui:
|
|
enabled: true
|
|
path: /
|