Merge branch 'dev' of https://github.com/chatchat-space/Langchain-Cha…

…tchat into dev
youfak · Dec 6, 2023 · 4c2fda7 · 4c2fda7
2 parents d1f94c2 + 1fac51f
commit 4c2fda7
Show file tree

Hide file tree

Showing 48 changed files with 1,439 additions and 554 deletions.
diff --git a/README.md b/README.md
@@ -148,7 +148,7 @@ $ python startup.py -a
 [![Telegram](https://img.shields.io/badge/Telegram-2CA5E0?style=for-the-badge&logo=telegram&logoColor=white "langchain-chatglm")](https://t.me/+RjliQ3jnJ1YyN2E9)
 
 ### 项目交流群
-<img src="img/qr_code_74.jpg" alt="二维码" width="300" />
+<img src="img/qr_code_76.jpg" alt="二维码" width="300" />
 
 🎉 Langchain-Chatchat 项目微信交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。
 

diff --git a/configs/__init__.py b/configs/__init__.py
@@ -5,4 +5,4 @@
 from .prompt_config import *
 
 
-VERSION = "v0.2.8-preview"
+VERSION = "v0.2.9-preview"
diff --git a/configs/kb_config.py.example b/configs/kb_config.py.example
@@ -106,7 +106,7 @@ kbs_config = {
 # TextSplitter配置项，如果你不明白其中的含义，就不要修改。
 text_splitter_dict = {
     "ChineseRecursiveTextSplitter": {
-        "source": "huggingface",  ## 选择tiktoken则使用openai的方法
+        "source": "huggingface",   # 选择tiktoken则使用openai的方法
         "tokenizer_name_or_path": "",
     },
     "SpacyTextSplitter": {

diff --git a/configs/model_config.py.example b/configs/model_config.py.example
@@ -15,9 +15,11 @@ EMBEDDING_DEVICE = "auto"
 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。
-# 第一个将作为 API 和 WEBUI 的默认模型
-LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api"]
+# 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。
+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
@@ -112,10 +114,10 @@ ONLINE_LLM_MODEL = {
         "api_key": "",
         "provider": "AzureWorker",
     },
-    
+
     # 昆仑万维天工 API https://model-platform.tiangong.cn/
     "tiangong-api": {
-        "version":"SkyChat-MegaVerse",
+        "version": "SkyChat-MegaVerse",
         "api_key": "",
         "secret_key": "",
         "provider": "TianGongWorker",
@@ -163,6 +165,25 @@ MODEL_PATH = {
 
         "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",
+        "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",
@@ -204,18 +225,11 @@ MODEL_PATH = {
         "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",
-        "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": "Qwen/Qwen-14B-Chat-Int4",  # 确保已经安装了auto-gptq optimum flash-attn
-
         "agentlm-7b": "THUDM/agentlm-7b",
         "agentlm-13b": "THUDM/agentlm-13b",
         "agentlm-70b": "THUDM/agentlm-70b",
 
-        "Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat", # 更多01-ai模型尚未进行测试。如果需要使用，请自行测试。
+        "Yi-34B-Chat": "https://huggingface.co/01-ai/Yi-34B-Chat",
     },
 }
 
@@ -242,11 +256,11 @@ VLLM_MODEL_DICT = {
     "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",
+    # "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",
@@ -273,10 +287,23 @@ VLLM_MODEL_DICT = {
     "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-14B": "Qwen/Qwen-14B",
     "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",

diff --git a/configs/prompt_config.py.example b/configs/prompt_config.py.example
@@ -1,7 +1,6 @@
 # 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
 
@@ -17,125 +16,112 @@
 #   - input: 用户输入内容
 #   - agent_scratchpad: Agent的思维记录
 
-PROMPT_TEMPLATES = {}
-
-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.
-
-Current conversation:
-{history}
-Human: {input}
-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 }}
-""",
-}
-
-PROMPT_TEMPLATES["knowledge_base_chat"] = {
-"default":
-"""
-<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>
-<已知信息>{{ context }}</已知信息>、
-<问题>{{ question }}</问题>
-""",
-"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。 </指令>
-<已知信息>{{ context }}</已知信息>、
-<问题>{{ question }}</问题>
-""",
-"Empty":  # 搜不到知识库的时候使用
-"""
-请你回答我的问题:
-{{ question }}
-\n
-""",
-}
-PROMPT_TEMPLATES["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”。 </指令>
-<已知信息>{{ context }}</已知信息>
-<问题>{{ question }}</问题>
-""",
-"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。 </指令>
-<已知信息>{{ context }}</已知信息>、
-<问题>{{ question }}</问题>
-""",
-}
-PROMPT_TEMPLATES["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:
-
-{tools}
-
-Please note that the "知识库查询工具" is information about the "西交利物浦大学" ,and if a question is asked about it, you must answer with the knowledge base，
-Please note that the "天气查询工具" can only be used once since Question begin.
-
-Use the following format:
-Question: the input question you must answer1
-Thought: you should always think about what to do and what tools to use.
-Action: the action to take, should be one of [{tool_names}]
-Action Input: the input to the action
-Observation: the result of the action
-... (this Thought/Action/Action Input/Observation can be repeated zero or more times)
-Thought: I now know the final answer
-Final Answer: the final answer to the original input question
-Begin!
-
-history: {history}
-
-Question: {input}
-
-Thought: {agent_scratchpad}
-""",
-
-"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.
-You have access to the following tools:
-{tools}
-Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).
-Valid "action" values: "Final Answer" or  [{tool_names}]
-Provide only ONE action per $JSON_BLOB, as shown:
-
-```
-{{{{
-  "action": $TOOL_NAME,
-  "action_input": $INPUT
-}}}}
-```
-
-Follow this format:
-
-Question: input question to answer
-Thought: consider previous and subsequent steps
-Action:
-```
-$JSON_BLOB
-```
-Observation: action result
-... (repeat Thought/Action/Observation N times)
-Thought: I know what to respond
-Action:
-```
-{{{{
-  "action": "Final Answer",
-  "action_input": "Final response to human"
-}}}}
-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:.
-
-history: {history}
-
-Question: {input}
-
-Thought: {agent_scratchpad}
-""",
+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>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',
+
+        "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。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\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”。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\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。 </指令>\n'
+            '<已知信息>{{ context }}</已知信息>\n'
+            '<问题>{{ question }}</问题>\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}',
+    }
 }