diff --git a/configs/model_config.py b/configs/model_config.py new file mode 100644 index 0000000..5bcdee4 --- /dev/null +++ b/configs/model_config.py @@ -0,0 +1,344 @@ +import os + +# 可以指定一个绝对路径，统一存放所有的Embedding和LLM模型。 +# 每个模型可以是一个单独的目录，也可以是某个目录下的二级子目录。 +# 如果模型目录名称和 MODEL_PATH 中的 key 或 value 相同，程序会自动检测加载，无需修改 MODEL_PATH 中的路径。 +MODEL_ROOT_PATH = "" + +# 选用的 Embedding 名称 +EMBEDDING_MODEL = "bge-large-zh" + +# Embedding 模型运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。 +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 + +# 是否启用精排 +USE_RANKING = False + +# 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" + +# 要运行的 LLM 名称，可以包括本地模型和在线模型。列表中本地模型将在启动项目时全部加载。 +# 列表中第一个模型将作为 API 和 WEBUI 的默认模型。 +# 在这里，我们使用目前主流的两个离线模型，其中，chatglm3-6b 为默认加载模型。 +# 如果你的显存不足，可使用 Qwen-1_8B-Chat, 该模型 FP16 仅需 3.8G显存。 + +# chatglm3-6b输出角色标签<|user|>及自问自答的问题详见项目wiki->常见问题->Q20. + +LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api"] # "Qwen-1_8B-Chat", + +# 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LLM_MODELS[0]) +Agent_MODEL = None + +# LLM 运行设备。设为"auto"会自动检测，也可手动设定为"cuda","mps","cpu"其中之一。 +LLM_DEVICE = "auto" + +# 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 = None + +# LLM通用对话参数 +TEMPERATURE = 0.7 +# TOP_P = 0.95 # ChatOpenAI暂不支持该参数 + +ONLINE_LLM_MODEL = { + # 线上模型。请在server_config中为每个在线API设置不同的端口 + + "openai-api": { + "model_name": "gpt-3.5-turbo", + "api_base_url": "https://api.openai.com/v1", + "api_key": "", + "openai_proxy": "", + }, + + # 具体注册及api key获取请前往 http://open.bigmodel.cn + "zhipu-api": { + "api_key": "", + "version": "chatglm_turbo", # 可选包括 "chatglm_turbo" + "provider": "ChatGLMWorker", + }, + + + # 具体注册及api key获取请前往 https://api.minimax.chat/ + "minimax-api": { + "group_id": "", + "api_key": "", + "is_pro": False, + "provider": "MiniMaxWorker", + }, + + + # 具体注册及api key获取请前往 https://xinghuo.xfyun.cn/ + "xinghuo-api": { + "APPID": "", + "APISecret": "", + "api_key": "", + "version": "v1.5", # 你使用的讯飞星火大模型版本，可选包括 "v3.0", "v1.5", "v2.0" + "provider": "XingHuoWorker", + }, + + # 百度千帆 API，申请方式请参考 https://cloud.baidu.com/doc/WENXINWORKSHOP/s/4lilb2lpf + "qianfan-api": { + "version": "ERNIE-Bot", # 注意大小写。当前支持 "ERNIE-Bot" 或 "ERNIE-Bot-turbo"， 更多的见官方文档。 + "version_url": "", # 也可以不填写version，直接填写在千帆申请模型发布的API地址 + "api_key": "", + "secret_key": "", + "provider": "QianFanWorker", + }, + + # 火山方舟 API，文档参考 https://www.volcengine.com/docs/82379 + "fangzhou-api": { + "version": "chatglm-6b-model", # 当前支持 "chatglm-6b-model"， 更多的见文档模型支持列表中方舟部分。 + "version_url": "", # 可以不填写version，直接填写在方舟申请模型发布的API地址 + "api_key": "", + "secret_key": "", + "provider": "FangZhouWorker", + }, + + # 阿里云通义千问 API，文档参考 https://help.aliyun.com/zh/dashscope/developer-reference/api-details + "qwen-api": { + "version": "qwen-turbo", # 可选包括 "qwen-turbo", "qwen-plus" + "api_key": "", # 请在阿里云控制台模型服务灵积API-KEY管理页面创建 + "provider": "QwenWorker", + "embed_model": "text-embedding-v1" # embedding 模型名称 + }, + + # 百川 API，申请方式请参考 https://www.baichuan-ai.com/home#api-enter + "baichuan-api": { + "version": "Baichuan2-53B", # 当前支持 "Baichuan2-53B"， 见官方文档。 + "api_key": "", + "secret_key": "", + "provider": "BaiChuanWorker", + }, + + # Azure API + "azure-api": { + "deployment_name": "", # 部署容器的名字 + "resource_name": "", # https://{resource_name}.openai.azure.com/openai/ 填写resource_name的部分，其他部分不要填写 + "api_version": "", # API的版本，不是模型版本 + "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", + }, + +} + +# 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": "BAAI/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": "BAAI/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": "damo/nlp_gte_sentence-embedding_chinese-large", + "text-embedding-ada-002": "your OPENAI_API_KEY", + }, + + "llm_model": { + # 以下部分模型并未完全测试，仅根据fastchat和vllm模型的模型列表推定支持 + "chatglm2-6b": "THUDM/chatglm2-6b", + "chatglm2-6b-32k": "THUDM/chatglm2-6b-32k", + + "chatglm3-6b": "THUDM/chatglm3-6b", + "chatglm3-6b-32k": "THUDM/chatglm3-6b-32k", + "chatglm3-6b-base": "THUDM/chatglm3-6b-base", + + "Qwen-1_8B": "Qwen/Qwen-1_8B", + "Qwen-1_8B-Chat": "Qwen/Qwen-1_8B-Chat", + "Qwen-1_8B-Chat-Int8": "Qwen/Qwen-1_8B-Chat-Int8", + "Qwen-1_8B-Chat-Int4": "Qwen/Qwen-1_8B-Chat-Int4", + + "Qwen-7B": "Qwen/Qwen-7B", + "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat", + + "Qwen-14B": "Qwen/Qwen-14B", + "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat", + + "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8", + # 在新版的transformers下需要手动修改模型的config.json文件，在quantization_config字典中 + # 增加`disable_exllama:true` 字段才能启动qwen的量化模型 + "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4", + + "Qwen-72B": "Qwen/Qwen-72B", + "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat", + "Qwen-72B-Chat-Int8": "Qwen/Qwen-72B-Chat-Int8", + "Qwen-72B-Chat-Int4": "Qwen/Qwen-72B-Chat-Int4", + + "baichuan2-13b": "baichuan-inc/Baichuan2-13B-Chat", + "baichuan2-7b": "baichuan-inc/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", + + "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", + + "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", + + "agentlm-7b": "THUDM/agentlm-7b", + "agentlm-13b": "THUDM/agentlm-13b", + "agentlm-70b": "THUDM/agentlm-70b", + + "Yi-34B-Chat": "01-ai/Yi-34B-Chat", + }, + "reranker":{ + "bge-reranker-large":"BAAI/bge-reranker-large", + "bge-reranker-base":"BAAI/bge-reranker-base", + #TODO 增加在线reranker，如cohere + } +} + + +# 通常情况下不需要更改以下内容 + +# nltk 模型存储路径 +NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data") + +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", + + "BlueLM-7B-Chat": "vivo-ai/BlueLM-7B-Chat", + "BlueLM-7B-Chat-32k": "vivo-ai/BlueLM-7B-Chat-32k", + + # 注意：bloom系列的tokenizer与model是分离的，因此虽然vllm支持，但与fschat框架不兼容 + # "bloom": "bigscience/bloom", + # "bloomz": "bigscience/bloomz", + # "bloomz-560m": "bigscience/bloomz-560m", + # "bloomz-7b1": "bigscience/bloomz-7b1", + # "bloomz-1b7": "bigscience/bloomz-1b7", + + "internlm-7b": "internlm/internlm-7b", + "internlm-chat-7b": "internlm/internlm-chat-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", + "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": "Qwen/Qwen-1_8B", + "Qwen-1_8B-Chat": "Qwen/Qwen-1_8B-Chat", + "Qwen-1_8B-Chat-Int8": "Qwen/Qwen-1_8B-Chat-Int8", + "Qwen-1_8B-Chat-Int4": "Qwen/Qwen-1_8B-Chat-Int4", + + "Qwen-7B": "Qwen/Qwen-7B", + "Qwen-7B-Chat": "Qwen/Qwen-7B-Chat", + + "Qwen-14B": "Qwen/Qwen-14B", + "Qwen-14B-Chat": "Qwen/Qwen-14B-Chat", + "Qwen-14B-Chat-Int8": "Qwen/Qwen-14B-Chat-Int8", + "Qwen-14B-Chat-Int4": "Qwen/Qwen-14B-Chat-Int4", + + "Qwen-72B": "Qwen/Qwen-72B", + "Qwen-72B-Chat": "Qwen/Qwen-72B-Chat", + "Qwen-72B-Chat-Int8": "Qwen/Qwen-72B-Chat-Int8", + "Qwen-72B-Chat-Int4": "Qwen/Qwen-72B-Chat-Int4", + + "agentlm-7b": "THUDM/agentlm-7b", + "agentlm-13b": "THUDM/agentlm-13b", + "agentlm-70b": "THUDM/agentlm-70b", + +} + +# 你认为支持Agent能力的模型，可以在这里添加，添加后不会出现可视化界面的警告 +# 经过我们测试，原生支持Agent的模型仅有以下几个 +SUPPORT_AGENT_MODEL = [ + "azure-api", + "openai-api", + "qwen-api", + "Qwen", + "chatglm3", + "xinghuo-api", +] diff --git a/configs/prompt_config.py b/configs/prompt_config.py new file mode 100644 index 0000000..a23f4c5 --- /dev/null +++ b/configs/prompt_config.py @@ -0,0 +1,126 @@ +# prompt模板使用Jinja2语法，简单点就是用双大括号代替f-string的单大括号 +# 本配置文件支持热加载，修改prompt模板后无需重启服务。 + +# LLM对话支持的变量： +# - input: 用户输入内容 + +# 知识库和搜索引擎对话支持的变量： +# - context: 从检索结果拼接的知识文本 +# - question: 用户提出的问题 + +# Agent对话支持的变量： + +# - tools: 可用的工具列表 +# - tool_names: 可用的工具名称列表 +# - history: 用户和Agent的对话历史 +# - input: 用户输入内容 +# - agent_scratchpad: Agent的思维记录 + +PROMPT_TEMPLATES = { + "llm_chat": { + "default": + '{{ input }}', + + "with_history": + 'The following is a friendly conversation between a human and an AI. ' + 'The AI is talkative and provides lots of specific details from its context. ' + 'If the AI does not know the answer to a question, it truthfully says it does not know.\n\n' + 'Current conversation:\n' + '{history}\n' + 'Human: {input}\n' + 'AI:', + + "py": + '你是一个聪明的代码助手，请你给我写出简单的py代码。 \n' + '{{ input }}', + }, + + "knowledge_base_chat": { + "default": + '<指令>你是一个电力公司相关的专家，请完全依据已知信息的内容，先找出与问题相关的信息，然后再根据这些相关信息回答简洁、专业地来回答问题。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，不回答与问题无关的内容，答案请使用中文。 \n' + '<已知信息>{{ context }}\n' + '<问题>{{ question }}\n', + + "text": + '<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”，答案请使用中文。 \n' + '<已知信息>{{ context }}\n' + '<问题>{{ question }}\n', + + "empty": # 搜不到知识库的时候使用 + '请你回答我的问题:\n' + '{{ question }}\n\n', + }, + + + "search_engine_chat": { + "default": + '<指令>这是我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”。 \n' + '<已知信息>{{ context }}\n' + '<问题>{{ question }}\n', + + "search": + '<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”，答案请使用中文。 \n' + '<已知信息>{{ context }}\n' + '<问题>{{ question }}\n', + }, + + + "agent_chat": { + "default": + 'Answer the following questions as best you can. If it is in order, you can use some tools appropriately. ' + 'You have access to the following tools:\n\n' + '{tools}\n\n' + 'Use the following format:\n' + 'Question: the input question you must answer1\n' + 'Thought: you should always think about what to do and what tools to use.\n' + 'Action: the action to take, should be one of [{tool_names}]\n' + 'Action Input: the input to the action\n' + 'Observation: the result of the action\n' + '... (this Thought/Action/Action Input/Observation can be repeated zero or more times)\n' + 'Thought: I now know the final answer\n' + 'Final Answer: the final answer to the original input question\n' + 'Begin!\n\n' + 'history: {history}\n\n' + 'Question: {input}\n\n' + 'Thought: {agent_scratchpad}\n', + + "ChatGLM3": + 'You can answer using the tools, or answer directly using your knowledge without using the tools. ' + 'Respond to the human as helpfully and accurately as possible.\n' + 'You have access to the following tools:\n' + '{tools}\n' + 'Use a json blob to specify a tool by providing an action key (tool name) ' + 'and an action_input key (tool input).\n' + 'Valid "action" values: "Final Answer" or [{tool_names}]' + 'Provide only ONE action per $JSON_BLOB, as shown:\n\n' + '```\n' + '{{{{\n' + ' "action": $TOOL_NAME,\n' + ' "action_input": $INPUT\n' + '}}}}\n' + '```\n\n' + 'Follow this format:\n\n' + 'Question: input question to answer\n' + 'Thought: consider previous and subsequent steps\n' + 'Action:\n' + '```\n' + '$JSON_BLOB\n' + '```\n' + 'Observation: action result\n' + '... (repeat Thought/Action/Observation N times)\n' + 'Thought: I know what to respond\n' + 'Action:\n' + '```\n' + '{{{{\n' + ' "action": "Final Answer",\n' + ' "action_input": "Final response to human"\n' + '}}}}\n' + 'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. ' + 'Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\n' + 'history: {history}\n\n' + 'Question: {input}\n\n' + 'Thought: {agent_scratchpad}', + } +} diff --git a/document_loaders/mywordload.py b/document_loaders/mywordload.py index 9980d35..0f79386 100644 --- a/document_loaders/mywordload.py +++ b/document_loaders/mywordload.py @@ -7,6 +7,8 @@ from docx.oxml.text.paragraph import CT_P from docx.oxml.table import CT_Tbl from docx.table import _Cell, Table from docx.text.paragraph import Paragraph +#from langchain.document_loaders.unstructured import UnstructuredFileLoader +#from langchain.document_loaders.word_document import Docx2txtLoader class RapidWordLoader(UnstructuredFileLoader): def _get_elements(self) -> List: @@ -57,6 +59,8 @@ class RapidWordLoader(UnstructuredFileLoader): doc = docxDocument(filepath) for block in iter_block_items(doc): if isinstance(block,Paragraph): + + #print(f"Paragraph:{block.text}") resp += (block.text + "\n\n") elif isinstance(block, Table): resp += read_table(block) + "\n" @@ -68,10 +72,12 @@ class RapidWordLoader(UnstructuredFileLoader): text = word2text(self.file_path) from unstructured.partition.text import partition_text - return partition_text(text=text, **self.unstructured_kwargs) - + return partition_text(text=text, paragraph_grouper = False, **self.unstructured_kwargs) if __name__ == "__main__": - loader = RapidWordLoader(file_path="/Users/wangvivi/Desktop/MySelf/AI/Test/国家电网公司供电企业组织机构规范标准.docx") + loader = RapidWordLoader(file_path="/Users/wangvivi/Desktop/Work/思极GPT/数字化部/设备类all/sb389/10kV带电作业用绝缘斗臂车.docx") + #loader = Docx2txtLoader(file_path="/Users/wangvivi/Desktop/Work/思极GPT/数字化部/设备类all/sb389/10kV带电作业用绝缘斗臂车.docx") + #loader = RapidWordLoader(file_path="/Users/wangvivi/Desktop/MySelf/AI/Test/这是一个测试文档_副本2.docx") docs = loader.load() print(docs) + diff --git a/server/agent/tools/weather_check.py b/server/agent/tools/weather_check.py index db88b87..32ac113 100644 --- a/server/agent/tools/weather_check.py +++ b/server/agent/tools/weather_check.py @@ -27,7 +27,7 @@ from server.agent import model_container from pydantic import BaseModel, Field ## 使用和风天气API查询天气 -KEY = "ac880e5a877042809ac7ffdd19d95b0d" +KEY = "1234567890wangweiwei" # key长这样，这里提供了示例的key，这个key没法使用，你需要自己去注册和风天气的账号，然后在这里填入你的key diff --git a/server/agent/tools_select.py b/server/agent/tools_select.py index 821d324..b6fa9dc 100644 --- a/server/agent/tools_select.py +++ b/server/agent/tools_select.py @@ -19,7 +19,7 @@ tools = [ Tool.from_function( func=weathercheck, name="weather_check", - description="", + description="Use this tools to answer questons about weather", args_schema=WhetherSchema, ), Tool.from_function( diff --git a/server/chat/agent_chat.py b/server/chat/agent_chat.py index 03c0c2b..d32cc5f 100644 --- a/server/chat/agent_chat.py +++ b/server/chat/agent_chat.py @@ -17,7 +17,7 @@ from server.chat.utils import History import json from server.agent import model_container from server.knowledge_base.kb_service.base import get_kb_details - +from fastapi.responses import StreamingResponse async def agent_chat(query: str = Body(..., description="用户输入", examples=["恼羞成怒"]), history: List[History] = Body([], @@ -29,7 +29,7 @@ async def agent_chat(query: str = Body(..., description="用户输入", examples ), stream: bool = Body(False, description="流式输出"), model_name: str = Body(LLM_MODELS[0], description="LLM 模型名称。"), - temperature: float = Body(TEMPERATURE, description="LLM 采样温度", ge=0.0, le=1.0), + temperature: float = Body(TEMPERATURE, description="LLM 采样温度", ge=0.0, le=0.9), max_tokens: Optional[int] = Body(None, description="限制LLM生成Token数量，默认None代表模型最大值"), prompt_name: str = Body("default", description="使用的prompt模板名称(在configs/prompt_config.py中配置)"), @@ -59,6 +59,8 @@ async def agent_chat(query: str = Body(..., description="用户输入", examples kb_list = {x["kb_name"]: x for x in get_kb_details()} model_container.DATABASE = {name: details['kb_info'] for name, details in kb_list.items()} + print(f"agent_chat_iterator model_container.DATABASE:{model_container.DATABASE}") + print(f"agent_chat_iterator temperature:{temperature}") if Agent_MODEL: ## 如果有指定使用Agent模型来完成任务 model_agent = get_ChatOpenAI( @@ -68,8 +70,10 @@ async def agent_chat(query: str = Body(..., description="用户输入", examples callbacks=[callback], ) model_container.MODEL = model_agent + print(f"111 agent_chat_iterator :model_container.MODEL:{ model_container.MODEL}") else: model_container.MODEL = model + print(f"222 agent_chat_iterator :model_container.MODEL:{model_container.MODEL}") prompt_template = get_prompt_template("agent_chat", prompt_name) prompt_template_agent = CustomPromptTemplate( @@ -91,6 +95,7 @@ async def agent_chat(query: str = Body(..., description="用户输入", examples memory.chat_memory.add_ai_message(message.content) if "chatglm3" in model_container.MODEL.model_name: + print(f"model_container.MODEL.model_name is chatglm3") agent_executor = initialize_glm3_agent( llm=model, tools=tools, @@ -180,8 +185,13 @@ async def agent_chat(query: str = Body(..., description="用户输入", examples yield json.dumps({"answer": answer, "final_answer": final_answer}, ensure_ascii=False) await task - return EventSourceResponse(agent_chat_iterator(query=query, + return StreamingResponse(agent_chat_iterator(query=query, history=history, model_name=model_name, prompt_name=prompt_name), - ) + media_type="text/event-stream") + # return EventSourceResponse(agent_chat_iterator(query=query, + # history=history, + # model_name=model_name, + # prompt_name=prompt_name), + # ) diff --git a/webui_pages/dialogue/dialogue.py b/webui_pages/dialogue/dialogue.py index 325cd5d..3b41216 100644 --- a/webui_pages/dialogue/dialogue.py +++ b/webui_pages/dialogue/dialogue.py @@ -350,7 +350,9 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False): temperature=temperature, ): try: + print(f"1111自定义Agent问答, d:{d}") d = json.loads(d) + print(f"22222自定义Agent问答, d:{d}") except: pass if error_msg := check_error_msg(d): # check whether error occured