分词相关检索

src/agent/geo_tool.py

+from langchain_core.tools import tool,BaseTool
+from pydantic import BaseModel, Field
+from typing import Type, Any,List,Union
+from langchain_openai import ChatOpenAI
+from langchain.agents import initialize_agent,Tool,AgentType,AgentExecutor,create_structured_chat_agent,create_react_agent,create_openai_functions_agent
+from langchain_core.prompts.chat import ChatPromptTemplate,HumanMessagePromptTemplate,SystemMessagePromptTemplate,MessagesPlaceholder
+from langchain_core.prompts import PromptTemplate
+import langchain_core
+import random
+
+class IssuanceArgs(BaseModel):
+    location: str = Field(description="行政区名称")
+    type: list = Field(description="问题类型，如水文，气象，地质等")
+
+
+class GeoQuery(BaseTool):
+    name = "geo_query"
+    description = """你是一个区（县）级的水文气象地质知识库，当咨询区（县）的水文气象地质等相关信息的时候，你可以提供数据和资料。注意，这个查询只能获取单个区（县）的水文气象地质等相关信息"""
+    args_schema: Type[BaseModel] = IssuanceArgs
+
+    def __init__(self):
+        super().__init__()
+
+    def _run(self, location: str, type: str) -> str:
+        print(location)
+        print(type)
+        n = random.randint(0,100)
+        print(n)
+        mock_str = "平均降水量是"+str(n)+"ml,没发生特殊的地质灾害"
+        return mock_str
+
+
+base_llm = ChatOpenAI(
+    openai_api_key='xxxxxxxxxxxxx',
+    openai_api_base='http://192.168.10.14:8000/v1',
+    model_name='Qwen2-7B',
+    verbose=True,
+    temperature=0
+)
+
+tools = [GeoQuery()]
+
+input_variables=['agent_scratchpad', 'input', 'tool_names', 'tools']
+input_types={'chat_history': List[Union[langchain_core.messages.ai.AIMessage, langchain_core.messages.human.HumanMessage, langchain_core.messages.chat.ChatMessage, langchain_core.messages.system.SystemMessage, langchain_core.messages.function.FunctionMessage, langchain_core.messages.tool.ToolMessage]]}
+metadata={'lc_hub_owner': 'hwchase17', 'lc_hub_repo': 'structured-chat-agent', 'lc_hub_commit_hash': 'ea510f70a5872eb0f41a4e3b7bb004d5711dc127adee08329c664c6c8be5f13c'}
+messages=[
+  SystemMessagePromptTemplate(prompt=PromptTemplate(input_variables=['tool_names', 'tools'], template='Respond to the human as helpfully and accurately as possible. You have access to the following tools:\n\n{tools}\n\nUse a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\n\nValid "action" values: "Final Answer" or {tool_names}\n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{{\n  "action": $TOOL_NAME,\n  "action_input": $INPUT\n}}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{{\n  "action": "Final Answer",\n  "action_input": "Final response to human"\n}}\n\nBegin! 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')),
+  MessagesPlaceholder(variable_name='chat_history', optional=True),
+  HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['agent_scratchpad', 'input'], template='{input}\n\n{agent_scratchpad}\n (reminder to respond in a JSON blob no matter what)'))
+]
+
+prompt = ChatPromptTemplate(
+    input_variables=input_variables,
+    input_types=input_types,
+    metadata=metadata,
+    messages=messages
+)
+
+
+agent = create_structured_chat_agent(llm=base_llm, tools=tools, prompt=prompt)
+agent_executor = AgentExecutor(agent=agent, tools=tools,verbose=True,handle_parsing_errors=True)
+res = agent_executor.invoke({"input":"西宁市的平均降水量谁多"})
+# res = agent_executor.invoke({"input":"海东市化隆县的降水量是多少"})
+
+print("====== result: ======")
+print(res)

src/pgdb/knowledge/txt_doc_table.py

@@ -64,3 +64,22 @@ class TxtDoc:
             query = "DROP TABLE txt_doc"
             self.db.format(query)
             print("drop table txt_doc ok")
+
+
+    def find_like_doc(self,item:list):
+        print(item)
+        i0 = item[0]
+        if len(item)>1:
+            item = item[1:]
+            print(item)
+        query = "select text,matadate FROM txt_doc WHERE text like '%"+i0+"%' "
+        for i in item:
+            query+= "and text like '%"+i+"%' "
+        print(query)
+        self.db.execute(query)
+        answer = self.db.fetchall()
+
+        if len(answer) > 0:
+            return answer
+        else:
+            return None
\ No newline at end of file

src/server/get_similarity.py

@@ -51,6 +51,24 @@ class GetSimilarityWithExt:
         self.rerank_docs = rerank_docs[:top_k]
         return self.faiss_db.join_document(d_list)
 
+    def get_rerank_with_doc(self, reranker: BgeRerank,split_doc:list, top_k=5):
+        question = '\n'.join(self.question)
+        print(question)
+        split_doc.extend(self.similarity_docs)
+        content_set = set()
+        unique_documents = []
+        for doc in split_doc:
+            content = hash(doc.page_content)
+            if content not in content_set:
+                unique_documents.append(doc)
+                content_set.add(content)
+        rerank_docs = reranker.compress_documents(unique_documents, question)
+        d_list = []
+        for d in rerank_docs[:top_k]:
+            d_list.append(d)
+        self.rerank_docs = rerank_docs[:top_k]
+        return self.faiss_db.join_document(d_list)
+
     def get_similarity_doc(self):
         return self.similarity_doc_txt