Update app/main.py

app/main.py

@@ -12,92 +12,57 @@ from fastapi.middleware.cors import CORSMiddleware
 from fastapi import FastAPI
 from pydantic import BaseModel
 from langchain_community.embeddings import HuggingFaceBgeEmbeddings
-import nltk  # Importing NLTK
+import nltk
 import time
 
-# Set writable paths for cache and data
-    raise
-
-def clean_response(response):
-    # Remove any leading/trailing whitespace, including newlines
-    cleaned = response.strip()
-    
-    # Remove any enclosing quotation marks
-    cleaned = re.sub(r'^["\']+|["\']+$', '', cleaned)
-    
-    # Replace multiple newlines with a single newline
-    cleaned = re.sub(r'\n+', '\n', cleaned)
-    
-    # Remove any remaining '\n' characters
-    cleaned = cleaned.replace('\\n', '')
-    
-    return cleaned
-
+# Set up FastAPI app
 app = FastAPI()
+
+# Get OpenAI API key
 openai_api_key = os.environ.get('OPENAI_API_KEY')
 llm = ChatOpenAI(
     api_key=openai_api_key,
-    model_name="gpt-4-turbo-preview",  # or "gpt-3.5-turbo" for a more economical option
-    temperature=0.7
+    model_name="gpt-4-turbo-preview",
+    temperature=0.7,
 )
 
-
-
 @app.get("/")
 def read_root():
     return {"Hello": "World"}
 
 class Query(BaseModel):
-
     query_text: str
 
+def clean_response(response):
+    cleaned = response.strip()
+    cleaned = re.sub(r'^["\']+|["\']+$', '', cleaned)
+    cleaned = re.sub(r'\n+', '\n', cleaned)
+    cleaned = cleaned.replace('\\n', '')
+    return cleaned
+
 prompt = ChatPromptTemplate.from_template(
 """
-You are a helpful assistant designed specifically for the Thapar Institute of Engineering and Technology (TIET), a renowned technical college. Your task is to answer all queries related to TIET. Every response you provide should be relevant to the context of TIET. If a question falls outside of this context, please decline by stating, 'Sorry, I cannot help with that.' If you do not know the answer to a question, do not attempt to fabricate a response; instead, politely decline.
-You may elaborate on your answers slightly to provide more information, but avoid sounding boastful or exaggerating. Stay focused on the context provided.
-If the query is not related to TIET or falls outside the context of education, respond with:
-        "Sorry, I cannot help with that. I'm specifically designed to answer questions about the Thapar Institute of Engineering and Technology. 
-        For more information, please contact at our toll-free number: 18002024100 or E-mail us at [email protected]
+You are a helpful assistant designed specifically for the Thapar Institute of Engineering and Technology (TIET), a renowned technical college. Your task is to answer all queries related to TIET. If a question falls outside of this context, please decline by stating, 'Sorry, I cannot help with that.' For more information, please contact our toll-free number: 18002024100 or email us at admissions@thapar.edu.
 <context>
 {context}
 </context>
-Question: {input}  
+Question: {input}
 """
 )
 
-def vector_embedding():
-
-        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
-        chunks = text_splitter.split_documents(documents)
-        
-        print(f"Created {len(chunks)} chunks.")
-
-        model_name = "BAAI/bge-base-en"
-        encode_kwargs = {'normalize_embeddings': True}
-        model_norm = HuggingFaceBgeEmbeddings(model_name=model_name, encode_kwargs=encode_kwargs)
-        
-        db = FAISS.from_documents(chunks, model_norm)
-        db.save_local("./vectors_db")
-        
-        print("Vector store created and saved successfully.")
-        return {"response": "Vector Store DB Is Ready"}
-
-    model_norm = HuggingFaceBgeEmbeddings(model_name=model_name, encode_kwargs=encode_kwargs)
-    return model_norm
-
-@app.post("/chat")  # Changed from /anthropic to /chat
+@app.post("/chat")
 def read_item(query: Query):
     try:
-
-
-
-
-        embeddings = get_embeddings()
+        # Load vector store
+        embeddings = HuggingFaceBgeEmbeddings(
+            model_name="BAAI/bge-base-en",
+            encode_kwargs={'normalize_embeddings': True}
+        )
         vectors = FAISS.load_local("./vectors_db", embeddings, allow_dangerous_deserialization=True)
     except Exception as e:
         print(f"Error loading vector store: {str(e)}")
         return {"response": "Vector Store Not Found or Error Loading. Please run /setup first."}
-    
+
     prompt1 = query.query_text
     if prompt1:
         start = time.process_time()
@@ -106,23 +71,28 @@ def read_item(query: Query):
         retrieval_chain = create_retrieval_chain(retriever, document_chain)
         response = retrieval_chain.invoke({'input': prompt1})
 
-        print("Response time:", time.process_time() - start)
-        
-        # Apply the cleaning function to the response
         cleaned_response = clean_response(response['answer'])
-        
-        # For debugging, print the cleaned response
-        print("Cleaned response:", repr(cleaned_response))
-        
-        return cleaned_response
+        print("Response time:", time.process_time() - start)
+        return {"response": cleaned_response}
     else:
-        return "No Query Found"
+        return {"response": "No Query Found"}
 
 @app.get("/setup")
 def setup():
+    # Example setup function for vector embedding
+    documents = []  # Load your documents here
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+    chunks = text_splitter.split_documents(documents)
+
+    model_name = "BAAI/bge-base-en"
+    encode_kwargs = {'normalize_embeddings': True}
+    embeddings = HuggingFaceBgeEmbeddings(model_name=model_name, encode_kwargs=encode_kwargs)
+
+    db = FAISS.from_documents(chunks, embeddings)
+    db.save_local("./vectors_db")
+    print("Vector store created and saved successfully.")
+    return {"response": "Vector Store DB Is Ready"}
 
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=8000)
-
-