190 lines
4.7 KiB
YAML
190 lines
4.7 KiB
YAML
# 模型配置项
|
||
|
||
|
||
# 默认选用的 LLM 名称
|
||
DEFAULT_LLM_MODEL: qwen2.5-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://192.168.0.21:9997/v1
|
||
api_key: EMPTY
|
||
api_proxy: ''
|
||
api_concurrencies: 5
|
||
auto_detect_model: true
|
||
llm_models: [qwen2.5-instruct]
|
||
embed_models: [bge-large-zh-v1.5]
|
||
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: []
|