190 lines
4.6 KiB
YAML
190 lines
4.6 KiB
YAML
|
|
# 模型配置项
|
|||
|
|
|
|||
|
|
|
|||
|
|
# 默认选用的 LLM 名称
|
|||
|
|
DEFAULT_LLM_MODEL: qwen2-instruct
|
|||
|
|
|
|||
|
|
# 默认选用的 Embedding 名称
|
|||
|
|
DEFAULT_EMBEDDING_MODEL: bge-large-zh-v1.5
|
|||
|
|
|
|||
|
|
# AgentLM模型的名称 (可以不指定,指定之后就锁定进入Agent之后的Chain的模型,不指定就是 DEFAULT_LLM_MODEL)
|
|||
|
|
Agent_MODEL: ''
|
|||
|
|
|
|||
|
|
# 默认历史对话轮数
|
|||
|
|
HISTORY_LEN: 3
|
|||
|
|
|
|||
|
|
# 大模型最长支持的长度,如果不填写,则使用模型默认的最大长度,如果填写,则为用户设定的最大长度
|
|||
|
|
MAX_TOKENS:
|
|||
|
|
|
|||
|
|
# LLM通用对话参数
|
|||
|
|
TEMPERATURE: 0.7
|
|||
|
|
|
|||
|
|
# 支持的Agent模型
|
|||
|
|
SUPPORT_AGENT_MODELS:
|
|||
|
|
- chatglm3-6b
|
|||
|
|
- glm-4
|
|||
|
|
- openai-api
|
|||
|
|
- Qwen-2
|
|||
|
|
- qwen2-instruct
|
|||
|
|
- gpt-3.5-turbo
|
|||
|
|
- gpt-4o
|
|||
|
|
|
|||
|
|
# LLM模型配置,包括了不同模态初始化参数。
|
|||
|
|
# `model` 如果留空则自动使用 DEFAULT_LLM_MODEL
|
|||
|
|
LLM_MODEL_CONFIG:
|
|||
|
|
preprocess_model:
|
|||
|
|
model: ''
|
|||
|
|
temperature: 0.05
|
|||
|
|
max_tokens: 4096
|
|||
|
|
history_len: 10
|
|||
|
|
prompt_name: default
|
|||
|
|
callbacks: false
|
|||
|
|
llm_model:
|
|||
|
|
model: ''
|
|||
|
|
temperature: 0.9
|
|||
|
|
max_tokens: 4096
|
|||
|
|
history_len: 10
|
|||
|
|
prompt_name: default
|
|||
|
|
callbacks: true
|
|||
|
|
action_model:
|
|||
|
|
model: ''
|
|||
|
|
temperature: 0.01
|
|||
|
|
max_tokens: 4096
|
|||
|
|
history_len: 10
|
|||
|
|
prompt_name: ChatGLM3
|
|||
|
|
callbacks: true
|
|||
|
|
postprocess_model:
|
|||
|
|
model: ''
|
|||
|
|
temperature: 0.01
|
|||
|
|
max_tokens: 4096
|
|||
|
|
history_len: 10
|
|||
|
|
prompt_name: default
|
|||
|
|
callbacks: true
|
|||
|
|
image_model:
|
|||
|
|
model: sd-turbo
|
|||
|
|
size: 256*256
|
|||
|
|
|
|||
|
|
# # 模型加载平台配置
|
|||
|
|
|
|||
|
|
|
|||
|
|
# # 平台名称
|
|||
|
|
# platform_name: xinference
|
|||
|
|
|
|||
|
|
# # 平台类型
|
|||
|
|
# # 可选值:['xinference', 'ollama', 'oneapi', 'fastchat', 'openai', 'custom openai']
|
|||
|
|
# platform_type: xinference
|
|||
|
|
|
|||
|
|
# # openai api url
|
|||
|
|
# api_base_url: http://127.0.0.1:9997/v1
|
|||
|
|
|
|||
|
|
# # api key if available
|
|||
|
|
# api_key: EMPTY
|
|||
|
|
|
|||
|
|
# # API 代理
|
|||
|
|
# api_proxy: ''
|
|||
|
|
|
|||
|
|
# # 该平台单模型最大并发数
|
|||
|
|
# api_concurrencies: 5
|
|||
|
|
|
|||
|
|
# # 是否自动获取平台可用模型列表。设为 True 时下方不同模型类型可自动检测
|
|||
|
|
# auto_detect_model: false
|
|||
|
|
|
|||
|
|
# # 该平台支持的大语言模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# llm_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的嵌入模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# embed_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的图像生成模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# text2image_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的多模态模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# image2text_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的重排模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# rerank_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的 STT 模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# speech2text_models: []
|
|||
|
|
|
|||
|
|
# # 该平台支持的 TTS 模型列表,auto_detect_model 设为 True 时自动检测
|
|||
|
|
# text2speech_models: []
|
|||
|
|
MODEL_PLATFORMS:
|
|||
|
|
- platform_name: xinference
|
|||
|
|
platform_type: xinference
|
|||
|
|
api_base_url: http://127.0.0.1:9997/v1
|
|||
|
|
api_key: EMPTY
|
|||
|
|
api_proxy: ''
|
|||
|
|
api_concurrencies: 5
|
|||
|
|
auto_detect_model: true
|
|||
|
|
llm_models: []
|
|||
|
|
embed_models: []
|
|||
|
|
text2image_models: []
|
|||
|
|
image2text_models: []
|
|||
|
|
rerank_models: []
|
|||
|
|
speech2text_models: []
|
|||
|
|
text2speech_models: []
|
|||
|
|
- platform_name: ollama
|
|||
|
|
platform_type: ollama
|
|||
|
|
api_base_url: http://127.0.0.1:11434/v1
|
|||
|
|
api_key: EMPTY
|
|||
|
|
api_proxy: ''
|
|||
|
|
api_concurrencies: 5
|
|||
|
|
auto_detect_model: false
|
|||
|
|
llm_models:
|
|||
|
|
- qwen:7b
|
|||
|
|
- qwen2:7b
|
|||
|
|
embed_models:
|
|||
|
|
- quentinz/bge-large-zh-v1.5
|
|||
|
|
text2image_models: []
|
|||
|
|
image2text_models: []
|
|||
|
|
rerank_models: []
|
|||
|
|
speech2text_models: []
|
|||
|
|
text2speech_models: []
|
|||
|
|
- platform_name: oneapi
|
|||
|
|
platform_type: oneapi
|
|||
|
|
api_base_url: http://127.0.0.1:3000/v1
|
|||
|
|
api_key: sk-
|
|||
|
|
api_proxy: ''
|
|||
|
|
api_concurrencies: 5
|
|||
|
|
auto_detect_model: false
|
|||
|
|
llm_models:
|
|||
|
|
- chatglm_pro
|
|||
|
|
- chatglm_turbo
|
|||
|
|
- chatglm_std
|
|||
|
|
- chatglm_lite
|
|||
|
|
- qwen-turbo
|
|||
|
|
- qwen-plus
|
|||
|
|
- qwen-max
|
|||
|
|
- qwen-max-longcontext
|
|||
|
|
- ERNIE-Bot
|
|||
|
|
- ERNIE-Bot-turbo
|
|||
|
|
- ERNIE-Bot-4
|
|||
|
|
- SparkDesk
|
|||
|
|
embed_models:
|
|||
|
|
- text-embedding-v1
|
|||
|
|
- Embedding-V1
|
|||
|
|
text2image_models: []
|
|||
|
|
image2text_models: []
|
|||
|
|
rerank_models: []
|
|||
|
|
speech2text_models: []
|
|||
|
|
text2speech_models: []
|
|||
|
|
- platform_name: openai
|
|||
|
|
platform_type: openai
|
|||
|
|
api_base_url: https://api.openai.com/v1
|
|||
|
|
api_key: sk-proj-
|
|||
|
|
api_proxy: ''
|
|||
|
|
api_concurrencies: 5
|
|||
|
|
auto_detect_model: false
|
|||
|
|
llm_models:
|
|||
|
|
- gpt-4o
|
|||
|
|
- gpt-3.5-turbo
|
|||
|
|
embed_models:
|
|||
|
|
- text-embedding-3-small
|
|||
|
|
- text-embedding-3-large
|
|||
|
|
text2image_models: []
|
|||
|
|
image2text_models: []
|
|||
|
|
rerank_models: []
|
|||
|
|
speech2text_models: []
|
|||
|
|
text2speech_models: []
|