mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-26 00:33:35 +08:00
391 lines
13 KiB
Plaintext
391 lines
13 KiB
Plaintext
import os
|
||
MODEL_ROOT_PATH = ""
|
||
EMBEDDING_MODEL = "bge-large-zh-v1.5" # bge-large-zh
|
||
EMBEDDING_DEVICE = "auto"
|
||
|
||
# 选用的reranker模型
|
||
RERANKER_MODEL = "bge-reranker-large"
|
||
# 是否启用reranker模型
|
||
USE_RERANKER = False
|
||
RERANKER_MAX_LENGTH = 1024
|
||
|
||
# 如果需要在 EMBEDDING_MODEL 中增加自定义的关键字时配置
|
||
EMBEDDING_KEYWORD_FILE = "keywords.txt"
|
||
EMBEDDING_MODEL_OUTPUT_PATH = "output"
|
||
SUPPORT_AGENT_MODELS = [
|
||
"chatglm3-6b",
|
||
"openai-api"
|
||
]
|
||
LLM_MODEL_CONFIG = {
|
||
# 意图识别不需要输出，模型后台知道就行
|
||
"preprocess_model": {
|
||
"zhipu-api": {
|
||
"temperature": 0.4,
|
||
"max_tokens": 2048,
|
||
"history_len": 100,
|
||
"prompt_name": "default",
|
||
"callbacks": False
|
||
},
|
||
},
|
||
"llm_model": {
|
||
"chatglm3-6b": {
|
||
"temperature": 0.9,
|
||
"max_tokens": 4096,
|
||
"history_len": 3,
|
||
"prompt_name": "default",
|
||
"callbacks": True
|
||
},
|
||
"zhipu-api": {
|
||
"temperature": 0.9,
|
||
"max_tokens": 4000,
|
||
"history_len": 5,
|
||
"prompt_name": "default",
|
||
"callbacks": True
|
||
},
|
||
"Qwen-1_8B-Chat": {
|
||
"temperature": 0.4,
|
||
"max_tokens": 2048,
|
||
"history_len": 100,
|
||
"prompt_name": "default",
|
||
"callbacks": True
|
||
},
|
||
},
|
||
"action_model": {
|
||
"chatglm3-6b": {
|
||
"temperature": 0.01,
|
||
"max_tokens": 4096,
|
||
"prompt_name": "ChatGLM3",
|
||
"callbacks": True
|
||
},
|
||
"openai-api": {
|
||
"temperature": 0.01,
|
||
"max_tokens": 4096,
|
||
"prompt_name": "GPT-4",
|
||
"callbacks": True
|
||
},
|
||
},
|
||
"postprocess_model": {
|
||
"chatglm3-6b": {
|
||
"temperature": 0.01,
|
||
"max_tokens": 4096,
|
||
"prompt_name": "default",
|
||
"callbacks": True
|
||
}
|
||
},
|
||
|
||
}
|
||
|
||
TOOL_CONFIG = {
|
||
"search_local_knowledgebase": {
|
||
"use": True,
|
||
"top_k": 10,
|
||
"score_threshold": 1,
|
||
"conclude_prompt": {
|
||
"with_result":
|
||
'<指令>根据已知信息，简洁和专业的来回答问题。如果无法从中得到答案，请说 "根据已知信息无法回答该问题"，'
|
||
'不允许在答案中添加编造成分，答案请使用中文。 </指令>\n'
|
||
'<已知信息>{{ context }}</已知信息>\n'
|
||
'<问题>{{ question }}</问题>\n',
|
||
"without_result":
|
||
'请你根据我的提问回答我的问题:\n'
|
||
'{{ question }}\n'
|
||
'请注意，你必须在回答结束后强调，你的回答是根据你的经验回答而不是参考资料回答的。\n',
|
||
}
|
||
},
|
||
"search_internet": {
|
||
"use": True,
|
||
"search_engine_name": "bing",
|
||
"search_engine_config":
|
||
{
|
||
"bing": {
|
||
"result_len": 3,
|
||
"bing_search_url": "https://api.bing.microsoft.com/v7.0/search",
|
||
"bing_key": "",
|
||
},
|
||
"metaphor": {
|
||
"result_len": 3,
|
||
"metaphor_api_key": "",
|
||
"split_result": False,
|
||
"chunk_size": 500,
|
||
"chunk_overlap": 0,
|
||
},
|
||
"duckduckgo": {
|
||
"result_len": 3
|
||
}
|
||
},
|
||
"top_k": 10,
|
||
"verbose": "Origin",
|
||
"conclude_prompt":
|
||
"<指令>这是搜索到的互联网信息，请你根据这些信息进行提取并有调理，简洁的回答问题。如果无法从中得到答案，请说 “无法搜索到能回答问题的内容”。 "
|
||
"</指令>\n<已知信息>{{ context }}</已知信息>\n"
|
||
"<问题>\n"
|
||
"{{ question }}\n"
|
||
"</问题>\n"
|
||
},
|
||
"arxiv": {
|
||
"use": True,
|
||
},
|
||
"shell": {
|
||
"use": True,
|
||
},
|
||
"weather_check": {
|
||
"use": True,
|
||
"api-key": "",
|
||
},
|
||
"search_youtube": {
|
||
"use": False,
|
||
},
|
||
"wolfram": {
|
||
"use": False,
|
||
},
|
||
"calculate": {
|
||
"use": False,
|
||
},
|
||
|
||
}
|
||
|
||
# LLM 模型运行设备。设为"auto"会自动检测(会有警告)，也可手动设定为 "cuda","mps","cpu","xpu" 其中之一。
|
||
LLM_DEVICE = "auto"
|
||
|
||
ONLINE_LLM_MODEL = {
|
||
"openai-api": {
|
||
"model_name": "gpt-4-1106-preview",
|
||
"api_base_url": "https://api.openai.com/v1",
|
||
"api_key": "",
|
||
"openai_proxy": "",
|
||
},
|
||
"zhipu-api": {
|
||
"api_key": "",
|
||
"version": "chatglm_turbo",
|
||
"provider": "ChatGLMWorker",
|
||
},
|
||
"minimax-api": {
|
||
"group_id": "",
|
||
"api_key": "",
|
||
"is_pro": False,
|
||
"provider": "MiniMaxWorker",
|
||
},
|
||
"xinghuo-api": {
|
||
"APPID": "",
|
||
"APISecret": "",
|
||
"api_key": "",
|
||
"version": "v3.0",
|
||
"provider": "XingHuoWorker",
|
||
},
|
||
"qianfan-api": {
|
||
"version": "ernie-bot-4",
|
||
"version_url": "",
|
||
"api_key": "",
|
||
"secret_key": "",
|
||
"provider": "QianFanWorker",
|
||
},
|
||
"fangzhou-api": {
|
||
"version": "chatglm-6b-model",
|
||
"version_url": "",
|
||
"api_key": "",
|
||
"secret_key": "",
|
||
"provider": "FangZhouWorker",
|
||
},
|
||
"qwen-api": {
|
||
"version": "qwen-max",
|
||
"api_key": "",
|
||
"provider": "QwenWorker",
|
||
"embed_model": "text-embedding-v1" # embedding 模型名称
|
||
},
|
||
"baichuan-api": {
|
||
"version": "Baichuan2-53B",
|
||
"api_key": "",
|
||
"secret_key": "",
|
||
"provider": "BaiChuanWorker",
|
||
},
|
||
"azure-api": {
|
||
"deployment_name": "",
|
||
"resource_name": "",
|
||
"api_version": "2023-07-01-preview",
|
||
"api_key": "",
|
||
"provider": "AzureWorker",
|
||
},
|
||
|
||
# 昆仑万维天工 API https://model-platform.tiangong.cn/
|
||
"tiangong-api": {
|
||
"version": "SkyChat-MegaVerse",
|
||
"api_key": "",
|
||
"secret_key": "",
|
||
"provider": "TianGongWorker",
|
||
},
|
||
# Gemini API https://makersuite.google.com/app/apikey
|
||
"gemini-api": {
|
||
"api_key": "",
|
||
"provider": "GeminiWorker",
|
||
}
|
||
|
||
}
|
||
|
||
# 在以下字典中修改属性值，以指定本地embedding模型存储位置。支持3种设置方法：
|
||
# 1、将对应的值修改为模型绝对路径
|
||
# 2、不修改此处的值（以 text2vec 为例）：
|
||
# 2.1 如果{MODEL_ROOT_PATH}下存在如下任一子目录：
|
||
# - text2vec
|
||
# - GanymedeNil/text2vec-large-chinese
|
||
# - text2vec-large-chinese
|
||
# 2.2 如果以上本地路径不存在，则使用huggingface模型
|
||
|
||
MODEL_PATH = {
|
||
"embed_model": {
|
||
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
|
||
"ernie-base": "nghuyong/ernie-3.0-base-zh",
|
||
"text2vec-base": "shibing624/text2vec-base-chinese",
|
||
"text2vec": "GanymedeNil/text2vec-large-chinese",
|
||
"text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
|
||
"text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
|
||
"text2vec-multilingual": "shibing624/text2vec-base-multilingual",
|
||
"text2vec-bge-large-chinese": "shibing624/text2vec-bge-large-chinese",
|
||
"m3e-small": "moka-ai/m3e-small",
|
||
"m3e-base": "moka-ai/m3e-base",
|
||
"m3e-large": "moka-ai/m3e-large",
|
||
|
||
"bge-small-zh": "BAAI/bge-small-zh",
|
||
"bge-base-zh": "BAAI/bge-base-zh",
|
||
"bge-large-zh": "/media/zr/Data/Models/Embedding/bge-large-zh",
|
||
"bge-large-zh-noinstruct": "BAAI/bge-large-zh-noinstruct",
|
||
"bge-base-zh-v1.5": "BAAI/bge-base-zh-v1.5",
|
||
"bge-large-zh-v1.5": "/Models/bge-large-zh-v1.5",
|
||
"piccolo-base-zh": "sensenova/piccolo-base-zh",
|
||
"piccolo-large-zh": "sensenova/piccolo-large-zh",
|
||
"nlp_gte_sentence-embedding_chinese-large": "/Models/nlp_gte_sentence-embedding_chinese-large",
|
||
"text-embedding-ada-002": "Just write your OpenAI key like "sk-o3IGBhC9g8AiFvTGWVKsT*****" ",
|
||
},
|
||
|
||
"llm_model": {
|
||
"chatglm2-6b": "THUDM/chatglm2-6b",
|
||
"chatglm2-6b-32k": "THUDM/chatglm2-6b-32k",
|
||
"chatglm3-6b": "/Models/chatglm3-6b",
|
||
"chatglm3-6b-32k": "THUDM/chatglm3-6b-32k",
|
||
|
||
"Yi-34B-Chat": "/data/share/models/Yi-34B-Chat",
|
||
"BlueLM-7B-Chat": "/Models/BlueLM-7B-Chat",
|
||
|
||
"baichuan2-13b": "/media/zr/Data/Models/LLM/Baichuan2-13B-Chat",
|
||
"baichuan2-7b": "/media/zr/Data/Models/LLM/Baichuan2-7B-Chat",
|
||
"baichuan-7b": "baichuan-inc/Baichuan-7B",
|
||
"baichuan-13b": "baichuan-inc/Baichuan-13B",
|
||
'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat',
|
||
|
||
"aquila-7b": "BAAI/Aquila-7B",
|
||
"aquilachat-7b": "BAAI/AquilaChat-7B",
|
||
|
||
"internlm-7b": "internlm/internlm-7b",
|
||
"internlm-chat-7b": "internlm/internlm-chat-7b",
|
||
"internlm2-chat-7b": "internlm/internlm2-chat-7b",
|
||
"internlm2-chat-20b": "internlm/internlm2-chat-20b",
|
||
|
||
"BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat",
|
||
"BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k",
|
||
|
||
"Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat",
|
||
|
||
"agentlm-7b": "THUDM/agentlm-7b",
|
||
"agentlm-13b": "THUDM/agentlm-13b",
|
||
"agentlm-70b": "THUDM/agentlm-70b",
|
||
|
||
"falcon-7b": "tiiuae/falcon-7b",
|
||
"falcon-40b": "tiiuae/falcon-40b",
|
||
"falcon-rw-7b": "tiiuae/falcon-rw-7b",
|
||
|
||
"aquila-7b": "BAAI/Aquila-7B",
|
||
"aquilachat-7b": "BAAI/AquilaChat-7B",
|
||
"open_llama_13b": "openlm-research/open_llama_13b",
|
||
"vicuna-13b-v1.5": "lmsys/vicuna-13b-v1.5",
|
||
"koala": "young-geng/koala",
|
||
"mpt-7b": "mosaicml/mpt-7b",
|
||
"mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
|
||
"mpt-30b": "mosaicml/mpt-30b",
|
||
"opt-66b": "facebook/opt-66b",
|
||
"opt-iml-max-30b": "facebook/opt-iml-max-30b",
|
||
"gpt2": "gpt2",
|
||
"gpt2-xl": "gpt2-xl",
|
||
"gpt-j-6b": "EleutherAI/gpt-j-6b",
|
||
"gpt4all-j": "nomic-ai/gpt4all-j",
|
||
"gpt-neox-20b": "EleutherAI/gpt-neox-20b",
|
||
"pythia-12b": "EleutherAI/pythia-12b",
|
||
"oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
|
||
"dolly-v2-12b": "databricks/dolly-v2-12b",
|
||
"stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
|
||
|
||
"Llama-2-13b-hf": "meta-llama/Llama-2-13b-hf",
|
||
"Llama-2-70b-hf": "meta-llama/Llama-2-70b-hf",
|
||
"open_llama_13b": "openlm-research/open_llama_13b",
|
||
"vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3",
|
||
"koala": "young-geng/koala",
|
||
|
||
"mpt-7b": "mosaicml/mpt-7b",
|
||
"mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
|
||
"mpt-30b": "mosaicml/mpt-30b",
|
||
"opt-66b": "facebook/opt-66b",
|
||
"opt-iml-max-30b": "facebook/opt-iml-max-30b",
|
||
|
||
"Qwen-1_8B-Chat":"Qwen/Qwen-1_8B-Chat"
|
||
"Qwen-7B": "Qwen/Qwen-7B",
|
||
"Qwen-14B": "Qwen/Qwen-14B",
|
||
"Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
|
||
"Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
|
||
"Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8", # 确保已经安装了auto-gptq optimum flash-attn
|
||
"Qwen-14B-Chat-Int4": "/media/zr/Data/Models/LLM/Qwen-14B-Chat-Int4", # 确保已经安装了auto-gptq optimum flash-attn
|
||
},
|
||
|
||
NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
|
||
|
||
# 使用VLLM可能导致模型推理能力下降，无法完成Agent任务
|
||
VLLM_MODEL_DICT = {
|
||
"aquila-7b": "BAAI/Aquila-7B",
|
||
"aquilachat-7b": "BAAI/AquilaChat-7B",
|
||
|
||
"baichuan-7b": "baichuan-inc/Baichuan-7B",
|
||
"baichuan-13b": "baichuan-inc/Baichuan-13B",
|
||
'baichuan-13b-chat': 'baichuan-inc/Baichuan-13B-Chat',
|
||
|
||
'chatglm2-6b': 'THUDM/chatglm2-6b',
|
||
'chatglm2-6b-32k': 'THUDM/chatglm2-6b-32k',
|
||
'chatglm3-6b': 'THUDM/chatglm3-6b',
|
||
'chatglm3-6b-32k': 'THUDM/chatglm3-6b-32k',
|
||
|
||
"internlm-7b": "internlm/internlm-7b",
|
||
"internlm-chat-7b": "internlm/internlm-chat-7b",
|
||
"internlm2-chat-7b": "internlm/Models/internlm2-chat-7b",
|
||
"internlm2-chat-20b": "internlm/Models/internlm2-chat-20b",
|
||
|
||
"aquila-7b": "BAAI/Aquila-7B",
|
||
"aquilachat-7b": "BAAI/AquilaChat-7B",
|
||
|
||
"falcon-7b": "tiiuae/falcon-7b",
|
||
"falcon-40b": "tiiuae/falcon-40b",
|
||
"falcon-rw-7b": "tiiuae/falcon-rw-7b",
|
||
"gpt2": "gpt2",
|
||
"gpt2-xl": "gpt2-xl",
|
||
"gpt-j-6b": "EleutherAI/gpt-j-6b",
|
||
"gpt4all-j": "nomic-ai/gpt4all-j",
|
||
"gpt-neox-20b": "EleutherAI/gpt-neox-20b",
|
||
"pythia-12b": "EleutherAI/pythia-12b",
|
||
"oasst-sft-4-pythia-12b-epoch-3.5": "OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5",
|
||
"dolly-v2-12b": "databricks/dolly-v2-12b",
|
||
"stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
|
||
"open_llama_13b": "openlm-research/open_llama_13b",
|
||
"vicuna-13b-v1.3": "lmsys/vicuna-13b-v1.3",
|
||
"koala": "young-geng/koala",
|
||
"mpt-7b": "mosaicml/mpt-7b",
|
||
"mpt-7b-storywriter": "mosaicml/mpt-7b-storywriter",
|
||
"mpt-30b": "mosaicml/mpt-30b",
|
||
"opt-66b": "facebook/opt-66b",
|
||
"opt-iml-max-30b": "facebook/opt-iml-max-30b",
|
||
|
||
"Qwen-7B": "Qwen/Qwen-7B",
|
||
"Qwen-14B": "Qwen/Qwen-14B",
|
||
"Qwen-7B-Chat": "Qwen/Qwen-7B-Chat",
|
||
"Qwen-14B-Chat": "Qwen/Qwen-14B-Chat",
|
||
|
||
"agentlm-7b": "THUDM/agentlm-7b",
|
||
"agentlm-13b": "THUDM/agentlm-13b",
|
||
"agentlm-70b": "THUDM/agentlm-70b",
|
||
|
||
}
|