240908-联合DBGPT与Ollama实现RAG本地知识检索增强 - IT评测·应用市场-qidao123.com技术社区

#*******************************************************************#
#** DB-GPT - GENERAL SETTINGS **#
#*******************************************************************#
#*******************************************************************#
#** Webserver Port **#
#*******************************************************************#
# DBGPT_WEBSERVER_PORT=5670
## Whether to enable the new web UI, enabled by default,False use old ui
# USE_NEW_WEB_UI=True
#*******************************************************************#
#*** LLM PROVIDER ***#
#*******************************************************************#
# TEMPERATURE=0
#*******************************************************************#
#** LLM MODELS **#
#*******************************************************************#
# ⭐️ 添加Ollama配置
LLM_MODEL=ollama_proxyllm
PROXY_SERVER_URL=http://127.0.0.1:11434
PROXYLLM_BACKEND="qwen2:1.5b"
PROXY_API_KEY=not_used
EMBEDDING_MODEL=proxy_ollama
proxy_ollama_proxy_server_url=http://127.0.0.1:11434
proxy_ollama_proxy_backend="nomic-embed-text:latest"
# LLM_MODEL=ollama_proxyllm
# MODEL_SERVER=http://127.0.0.1:11434
# PROXYLLM_BACKEND=llama3.1:8b
# EMBEDDING_MODEL=proxy_ollama
# proxy_ollama_proxy_server_url=http://127.0.0.1:11434
# proxy_ollama_proxy_backend=llama3.1:8b
# LLM_MODEL=ollama_proxyllm
# PROXY_SERVER_URL=http://127.0.0.1:11434
# PROXYLLM_BACKEND="qwen:0.5b"
# PROXY_API_KEY=not_used
# EMBEDDING_MODEL=proxy_ollama
# proxy_ollama_proxy_server_url=http://127.0.0.1:11434
# proxy_ollama_proxy_backend="nomic-embed-text:latest"
# # LLM_MODEL, see dbgpt/configs/model_config.LLM_MODEL_CONFIG
# LLM_MODEL=glm-4-9b-chat
# ## LLM model path, by default, DB-GPT will read the model path from LLM_MODEL_CONFIG based on the LLM_MODEL.
# ## Of course you can specify your model path according to LLM_MODEL_PATH
# ## In DB-GPT, the priority from high to low to read model path:
# ## 1. environment variable with key: {LLM_MODEL}_MODEL_PATH (Avoid multi-model conflicts)
# ## 2. environment variable with key: MODEL_PATH
# ## 3. environment variable with key: LLM_MODEL_PATH
# ## 4. the config in dbgpt/configs/model_config.LLM_MODEL_CONFIG
# # LLM_MODEL_PATH=/app/models/glm-4-9b-chat
# # LLM_PROMPT_TEMPLATE=vicuna_v1.1
# MODEL_SERVER=http://127.0.0.1:8000
# LIMIT_MODEL_CONCURRENCY=5
# MAX_POSITION_EMBEDDINGS=4096
# QUANTIZE_QLORA=True
# QUANTIZE_8bit=True
# # QUANTIZE_4bit=False
# ## SMART_LLM_MODEL - Smart language model (Default: vicuna-13b)
# ## FAST_LLM_MODEL - Fast language model (Default: chatglm-6b)
# # SMART_LLM_MODEL=vicuna-13b
# # FAST_LLM_MODEL=chatglm-6b
# ## Proxy llm backend, this configuration is only valid when "LLM_MODEL=proxyllm", When we use the rest API provided by deployment frameworks like fastchat as a proxyllm,
# ## "PROXYLLM_BACKEND" is the model they actually deploy. We can use "PROXYLLM_BACKEND" to load the prompt of the corresponding scene.
# # PROXYLLM_BACKEND=
# ### You can configure parameters for a specific model with {model name}_{config key}=xxx
# ### See dbgpt/model/parameter.py
# ## prompt template for current model
# # llama_cpp_prompt_template=vicuna_v1.1
# ## llama-2-70b must be 8
# # llama_cpp_n_gqa=8
# ## Model path
# # llama_cpp_model_path=/data/models/TheBloke/vicuna-13B-v1.5-GGUF/vicuna-13b-v1.5.Q4_K_M.gguf
# ### LLM cache
# ## Enable Model cache
# # MODEL_CACHE_ENABLE=True
# ## The storage type of model cache, now supports: memory, disk
# # MODEL_CACHE_STORAGE_TYPE=disk
# ## The max cache data in memory, we always store cache data in memory fist for high speed.
# # MODEL_CACHE_MAX_MEMORY_MB=256
# ## The dir to save cache data, this configuration is only valid when MODEL_CACHE_STORAGE_TYPE=disk
# ## The default dir is pilot/data/model_cache
# # MODEL_CACHE_STORAGE_DISK_DIR=
#*******************************************************************#
#** EMBEDDING SETTINGS **#
#*******************************************************************#
# ⭐️ 取消非Ollama的Embedding设置
# EMBEDDING_MODEL=text2vec
# #EMBEDDING_MODEL=m3e-large
# #EMBEDDING_MODEL=bge-large-en
# #EMBEDDING_MODEL=bge-large-zh
# KNOWLEDGE_CHUNK_SIZE=500
# KNOWLEDGE_SEARCH_TOP_SIZE=5
# KNOWLEDGE_GRAPH_SEARCH_TOP_SIZE=200
# ## Maximum number of chunks to load at once, if your single document is too large,
# ## you can set this value to a higher value for better performance.
# ## if out of memory when load large document, you can set this value to a lower value.
# # KNOWLEDGE_MAX_CHUNKS_ONCE_LOAD=10
# #KNOWLEDGE_CHUNK_OVERLAP=50
# # Control whether to display the source document of knowledge on the front end.
# KNOWLEDGE_CHAT_SHOW_RELATIONS=False
# # Whether to enable Chat Knowledge Search Rewrite Mode
# KNOWLEDGE_SEARCH_REWRITE=False
# ## EMBEDDING_TOKENIZER - Tokenizer to use for chunking large inputs
# ## EMBEDDING_TOKEN_LIMIT - Chunk size limit for large inputs
# # EMBEDDING_MODEL=all-MiniLM-L6-v2
# # EMBEDDING_TOKENIZER=all-MiniLM-L6-v2
# # EMBEDDING_TOKEN_LIMIT=8191
# ## Openai embedding model, See dbgpt/model/parameter.py
# # EMBEDDING_MODEL=proxy_openai
# # proxy_openai_proxy_server_url=https://api.openai.com/v1
# # proxy_openai_proxy_api_key={your-openai-sk}
# # proxy_openai_proxy_backend=text-embedding-ada-002
# ## qwen embedding model, See dbgpt/model/parameter.py
# # EMBEDDING_MODEL=proxy_tongyi
# # proxy_tongyi_proxy_backend=text-embedding-v1
# # proxy_tongyi_proxy_api_key={your-api-key}
# ## qianfan embedding model, See dbgpt/model/parameter.py
# #EMBEDDING_MODEL=proxy_qianfan
# #proxy_qianfan_proxy_backend=bge-large-zh
# #proxy_qianfan_proxy_api_key={your-api-key}
# #proxy_qianfan_proxy_api_secret={your-secret-key}
# ## Common HTTP embedding model
# # EMBEDDING_MODEL=proxy_http_openapi
# # proxy_http_openapi_proxy_server_url=http://localhost:8100/api/v1/embeddings
# # proxy_http_openapi_proxy_api_key=1dce29a6d66b4e2dbfec67044edbb924
# # proxy_http_openapi_proxy_backend=text2vec
#*******************************************************************#
#** RERANK SETTINGS **#
#*******************************************************************#
## Rerank model
# RERANK_MODEL=bge-reranker-base
## If you not set RERANK_MODEL_PATH, DB-GPT will read the model path from EMBEDDING_MODEL_CONFIG based on the RERANK_MODEL.
# RERANK_MODEL_PATH=
## The number of rerank results to return
# RERANK_TOP_K=3
## Common HTTP rerank model
# RERANK_MODEL=rerank_proxy_http_openapi
# rerank_proxy_http_openapi_proxy_server_url=http://127.0.0.1:8100/api/v1/beta/relevance
# rerank_proxy_http_openapi_proxy_api_key={your-api-key}
# rerank_proxy_http_openapi_proxy_backend=bge-reranker-base
#*******************************************************************#
#** DB-GPT METADATA DATABASE SETTINGS **#
#*******************************************************************#
### SQLite database (Current default database)
LOCAL_DB_TYPE=sqlite
### MYSQL database
# LOCAL_DB_TYPE=mysql
# LOCAL_DB_USER=root
# LOCAL_DB_PASSWORD={your_password}
# LOCAL_DB_HOST=127.0.0.1
# LOCAL_DB_PORT=3306
# LOCAL_DB_NAME=dbgpt
### This option determines the storage location of conversation records. The default is not configured to the old version of duckdb. It can be optionally db or file (if the value is db, the database configured by LOCAL_DB will be used)
#CHAT_HISTORY_STORE_TYPE=db
#*******************************************************************#
#** COMMANDS **#
#*******************************************************************#
EXECUTE_LOCAL_COMMANDS=False
#*******************************************************************#
#** VECTOR STORE / KNOWLEDGE GRAPH SETTINGS **#
#*******************************************************************#
VECTOR_STORE_TYPE=Chroma
GRAPH_STORE_TYPE=TuGraph
GRAPH_COMMUNITY_SUMMARY_ENABLED=True
KNOWLEDGE_GRAPH_EXTRACT_SEARCH_TOP_SIZE=5
KNOWLEDGE_GRAPH_EXTRACT_SEARCH_RECALL_SCORE=0.3
KNOWLEDGE_GRAPH_COMMUNITY_SEARCH_TOP_SIZE=20
KNOWLEDGE_GRAPH_COMMUNITY_SEARCH_RECALL_SCORE=0.0
### Chroma vector db config
#CHROMA_PERSIST_PATH=/root/DB-GPT/pilot/data
### Milvus vector db config
#VECTOR_STORE_TYPE=Milvus
#MILVUS_URL=127.0.0.1
#MILVUS_PORT=19530
#MILVUS_USERNAME
#MILVUS_PASSWORD
#MILVUS_SECURE=
### Weaviate vector db config
#VECTOR_STORE_TYPE=Weaviate
#WEAVIATE_URL=https://kt-region-m8hcy0wc.weaviate.network
## ElasticSearch vector db config
#VECTOR_STORE_TYPE=ElasticSearch
ElasticSearch_URL=127.0.0.1
ElasticSearch_PORT=9200
ElasticSearch_USERNAME=elastic
ElasticSearch_PASSWORD={your_password}
### TuGraph config
#TUGRAPH_HOST=127.0.0.1
#TUGRAPH_PORT=7687
#TUGRAPH_USERNAME=admin
#TUGRAPH_PASSWORD=73@TuGraph
#TUGRAPH_VERTEX_TYPE=entity
#TUGRAPH_EDGE_TYPE=relation
#TUGRAPH_PLUGIN_NAMES=leiden
#*******************************************************************#
#** WebServer Language Support **#
#*******************************************************************#
# en, zh, fr, ja, ko, ru
LANGUAGE=en
#LANGUAGE=zh
#*******************************************************************#
# ** PROXY_SERVER (openai interface | chatGPT proxy service), use chatGPT as your LLM.
# ⭐️ 注释掉Ollama之外的PROXY_SERVER_URL
# ** if your server can visit openai, please set PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
# ** else if you have a chatgpt proxy server, you can set PROXY_SERVER_URL={your-proxy-serverip:port/xxx}
#*******************************************************************#
# PROXY_API_KEY={your-openai-sk}
# PROXY_SERVER_URL=https://api.openai.com/v1/chat/completions
# # from https://bard.google.com/ f12-> application-> __Secure-1PSID
# BARD_PROXY_API_KEY={your-bard-token}
#*******************************************************************#
# ** PROXY_SERVER + **#
#*******************************************************************#
# Aliyun tongyi
TONGYI_PROXY_API_KEY={your-tongyi-sk}
## Baidu wenxin
#WEN_XIN_MODEL_VERSION={version}
#WEN_XIN_API_KEY={your-wenxin-sk}
#WEN_XIN_API_SECRET={your-wenxin-sct}
## Zhipu
#ZHIPU_MODEL_VERSION={version}
#ZHIPU_PROXY_API_KEY={your-zhipu-sk}
## Baichuan
#BAICHUN_MODEL_NAME={version}
#BAICHUAN_PROXY_API_KEY={your-baichuan-sk}
#BAICHUAN_PROXY_API_SECRET={your-baichuan-sct}
# Xunfei Spark
#XUNFEI_SPARK_API_VERSION={version}
#XUNFEI_SPARK_APPID={your_app_id}
#XUNFEI_SPARK_API_KEY={your_api_key}
#XUNFEI_SPARK_API_SECRET={your_api_secret}
## Yi Proxyllm, https://platform.lingyiwanwu.com/docs
#YI_MODEL_VERSION=yi-34b-chat-0205
#YI_API_BASE=https://api.lingyiwanwu.com/v1
#YI_API_KEY={your-yi-api-key}
## Moonshot Proxyllm, https://platform.moonshot.cn/docs/
# MOONSHOT_MODEL_VERSION=moonshot-v1-8k
# MOONSHOT_API_BASE=https://api.moonshot.cn/v1
# MOONSHOT_API_KEY={your-moonshot-api-key}
## Deepseek Proxyllm, https://platform.deepseek.com/api-docs/
# DEEPSEEK_MODEL_VERSION=deepseek-chat
# DEEPSEEK_API_BASE=https://api.deepseek.com/v1
# DEEPSEEK_API_KEY={your-deepseek-api-key}
#*******************************************************************#
#** SUMMARY_CONFIG **#
#*******************************************************************#
SUMMARY_CONFIG=FAST
#*******************************************************************#
#** MUlti-GPU **#
#*******************************************************************#
## See https://developer.nvidia.com/blog/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/
## If CUDA_VISIBLE_DEVICES is not configured, all available gpus will be used
# CUDA_VISIBLE_DEVICES=0
## You can configure the maximum memory used by each GPU.
# MAX_GPU_MEMORY=16Gib
#*******************************************************************#
#** LOG **#
#*******************************************************************#
# FATAL, ERROR, WARNING, WARNING, INFO, DEBUG, NOTSET
DBGPT_LOG_LEVEL=INFO
# LOG dir, default: ./logs
#DBGPT_LOG_DIR=
#*******************************************************************#
#** API_KEYS **#
#*******************************************************************#
# API_KEYS - The list of API keys that are allowed to access the API. Each of the below are an option, separated by commas.
# API_KEYS=dbgpt
#*******************************************************************#
#** ENCRYPT **#
#*******************************************************************#
# ENCRYPT KEY - The key used to encrypt and decrypt the data
# ENCRYPT_KEY=your_secret_key
#*******************************************************************#
#** File Server **#
#*******************************************************************#
## The local storage path of the file server, the default is pilot/data/file_server
# FILE_SERVER_LOCAL_STORAGE_PATH =
#*******************************************************************#
#** Application Config **#
#*******************************************************************#
## Non-streaming scene retries
# DBGPT_APP_SCENE_NON_STREAMING_RETRIES_BASE=1
## Non-streaming scene parallelism
# DBGPT_APP_SCENE_NON_STREAMING_PARALLELISM_BASE=1
#*******************************************************************#
#** Observability Config **#
#*******************************************************************#
## Whether to enable DB-GPT send trace to OpenTelemetry
# TRACER_TO_OPEN_TELEMETRY=False
## Following configurations are only valid when TRACER_TO_OPEN_TELEMETRY=True
## More details see https://opentelemetry-python.readthedocs.io/en/latest/exporter/otlp/otlp.html
# OTEL_EXPORTER_OTLP_TRACES_ENDPOINT=http://localhost:4317
# OTEL_EXPORTER_OTLP_TRACES_INSECURE=False
# OTEL_EXPORTER_OTLP_TRACES_CERTIFICATE=
# OTEL_EXPORTER_OTLP_TRACES_HEADERS=
# OTEL_EXPORTER_OTLP_TRACES_TIMEOUT=
# OTEL_EXPORTER_OTLP_TRACES_COMPRESSION=
#*******************************************************************#
#** FINANCIAL CHAT Config **#
#*******************************************************************#
# FIN_REPORT_MODEL=/app/models/bge-large-zh

复制代码