Update app/main.py

app/main.py

@@ -16,30 +16,6 @@ import nltk  # Importing NLTK
 import time
 
 # Set writable paths for cache and data
-cache_dir = '/tmp'
-nltk_data_path = os.path.join(cache_dir, 'nltk_data')
-
-# Configure NLTK and other library paths
-os.environ['TRANSFORMERS_CACHE'] = os.path.join(cache_dir, 'transformers_cache')
-os.environ['HF_HOME'] = os.path.join(cache_dir, 'huggingface')
-os.environ['XDG_CACHE_HOME'] = cache_dir
-
-# Add NLTK data path
-nltk.data.path.append(nltk_data_path)
-
-# Ensure the directory exists
-try:
-    os.makedirs(nltk_data_path, exist_ok=True)
-except OSError as e:
-    print(f"Error creating directory {nltk_data_path}: {e}")
-    raise
-
-# Download required NLTK resources
-try:
-    nltk.download('punkt', download_dir=nltk_data_path)
-    print("NLTK 'punkt' resource downloaded successfully.")
-except Exception as e:
-    print(f"Error downloading NLTK resources: {e}")
     raise
 
 def clean_response(response):
@@ -58,34 +34,27 @@ def clean_response(response):
     return cleaned
 
 app = FastAPI()
-
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
 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,
-    max_tokens=200
+    temperature=0.7
 )
 
+
+
 @app.get("/")
 def read_root():
     return {"Hello": "World"}
 
 class Query(BaseModel):
+
     query_text: str
 
 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 in concised manner. 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.
-but avoid sounding boastful or exaggerating. Stay focused on the context provided.
+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]
@@ -97,16 +66,6 @@ Question: {input}
 )
 
 def vector_embedding():
-    try:
-        file_path = "./data/Data.docx"
-        if not os.path.exists(file_path):
-            print(f"The file {file_path} does not exist.")
-            return {"response": "Error: Data file not found"}
-
-        loader = DocxLoader(file_path)
-        documents = loader.load()
-
-        print(f"Loaded document: {file_path}")
 
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
         chunks = text_splitter.split_documents(documents)
@@ -123,19 +82,16 @@ def vector_embedding():
         print("Vector store created and saved successfully.")
         return {"response": "Vector Store DB Is Ready"}
 
-    except Exception as e:
-        print(f"An error occurred: {str(e)}")
-        return {"response": f"Error: {str(e)}"}
-
-def get_embeddings():
-    model_name = "BAAI/bge-base-en"
-    encode_kwargs = {'normalize_embeddings': True}
     model_norm = HuggingFaceBgeEmbeddings(model_name=model_name, encode_kwargs=encode_kwargs)
     return model_norm
 
 @app.post("/chat")  # Changed from /anthropic to /chat
 def read_item(query: Query):
     try:
+
+
+
+
         embeddings = get_embeddings()
         vectors = FAISS.load_local("./vectors_db", embeddings, allow_dangerous_deserialization=True)
     except Exception as e:
@@ -149,6 +105,7 @@ def read_item(query: Query):
         retriever = vectors.as_retriever()
         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
@@ -163,8 +120,9 @@ def read_item(query: Query):
 
 @app.get("/setup")
 def setup():
-    return vector_embedding()
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+