修改知识问答

app.py

@@ -99,27 +99,6 @@ model = AutoModel(model="E:\\yuyin_model\\Voice_translation", model_revision="v2
 #     model_revision="v2.0.4",
 #     device='gpu')
 
-#知识问答
-llm = ChatOllama(model=LLM_MODEL,keep_alive=-1,num_gpu=0)
-        # Get the vector database instance
-db = get_vector_db()
-# Get the prompt templates
-QUERY_PROMPT, prompt = get_prompt()
-
-# Set up the retriever to generate multiple queries using the language model and the query prompt
-retriever = MultiQueryRetriever.from_llm(
-    db.as_retriever(), 
-    llm,
-    prompt=QUERY_PROMPT
-)
-
-# Define the processing chain to retrieve context, generate the answer, and parse the output
-chain = (
-    {"context": retriever, "question": RunnablePassthrough()}
-    | prompt
-    | llm
-    | StrOutputParser()
-)
 
 
 # 后台接口
@@ -149,15 +128,14 @@ def route_embed():
 def route_query(msg):
     response = query(msg)
     # print(response)
-    if response:
-        resObj = {}
-        resObj["data"] = response
-        resObj["code"] = 200
-        resObj["type"] = "answer"
-
-        return resObj
-
-    return {"error": "Something went wrong"}, 400
+    # if response:
+    #     resObj = {}
+    #     resObj["data"] = response
+    #     resObj["code"] = 200
+    #     resObj["type"] = "answer"
+    #     return resObj
+    # return {"error": "Something went wrong"}, 400
+    return response
 
 @app.route('/delete', methods=['DELETE'])
 def route_delete():

get_vector_db.py

@@ -7,7 +7,7 @@ COLLECTION_NAME = os.getenv('COLLECTION_NAME', 'siwei_ai')
 TEXT_EMBEDDING_MODEL = os.getenv('TEXT_EMBEDDING_MODEL', 'nomic-embed-text')
 
 def get_vector_db():
-    embedding = OllamaEmbeddings(model=TEXT_EMBEDDING_MODEL,show_progress=True,num_gpu=0)
+    embedding = OllamaEmbeddings(model=TEXT_EMBEDDING_MODEL,show_progress=True,num_gpu=0,num_thread=4)
 
     db = Chroma(
         collection_name=COLLECTION_NAME,