Upload app.py with huggingface_hub

app.py

@@ -29,9 +29,10 @@ from langchain.agents import create_tool_calling_agent, AgentExecutor
 from langchain_core.prompts import ChatPromptTemplate
 
 # LangChain OpenAI imports
+# Commented cout - not used
 #from langchain_openai import AzureOpenAIEmbeddings, AzureChatOpenAI  # OpenAI embeddings and models
 #from langchain.embeddings.openai import OpenAIEmbeddings  # OpenAI embeddings for text vectors
-# Added
+# Added and used below
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
 #from langchain_openai import ChatOpenAI
 
@@ -58,15 +59,10 @@ from datetime import datetime
 #====================================SETUP=====================================#
 # Fetch secrets from Hugging Face Spaces
 api_key = os.environ["API_KEY"]
-#print(f"api_key::{api_key}")
 endpoint = os.environ["OPENAI_API_BASE"]
-#print(f"endpoint::{endpoint}" )
 groq_api_key = os.environ['LLAMA_API_KEY'] # llama_api_key = os.environ['GROQ_API_KEY']
-#print(f"groq_api_key::{groq_api_key}")
 MEM0_api_key = os.environ['MEM0_API_KEY'] # MEM0_api_key = os.environ['mem0']
-#print(f"MEM0_api_key::{MEM0_api_key}")
 my_api_key = os.environ["MY_API_KEY"]
-#print(f"my_api_key::{my_api_key}")
 
 # Initialize the OpenAI embedding function for Chroma
 embedding_function = chromadb.utils.embedding_functions.OpenAIEmbeddingFunction(
@@ -74,7 +70,6 @@ embedding_function = chromadb.utils.embedding_functions.OpenAIEmbeddingFunction(
     api_key=api_key, # Complete the code to define the API key
     model_name='text-embedding-ada-002' # This is a fixed value and does not need modification
 )
-print("embedding_function initialized...")
 
 # This initializes the OpenAI embedding function for the Chroma vectorstore, using the provided endpoint and API key.
 
@@ -84,7 +79,6 @@ embedding_model = OpenAIEmbeddings(
     openai_api_key=api_key,
     model='text-embedding-ada-002'
 )
-print("embedding_model initialized...")
 
 # Initialize the Chat OpenAI model
 llm = ChatOpenAI(
@@ -93,7 +87,6 @@ llm = ChatOpenAI(
     model="gpt-4o", # used gpt4o instead of gpt-4o-mini to get improved results
     streaming=False
 )
-print("llm initialized...")
 
 # This initializes the Chat OpenAI model with the provided endpoint, API key, deployment name, and a temperature setting of 0 (to control response variability).
 
@@ -161,7 +154,6 @@ vector_store = Chroma(
     persist_directory="./nutritional_db",
     embedding_function=embedding_model
 )
-print("vector_store initialized...")
 
 # Create a retriever from the vector store
 retriever = vector_store.as_retriever(
@@ -180,7 +172,8 @@ def retrieve_context(state):
         Dict: The updated state with the retrieved context.
     """
     print("---------retrieve_context---------")
-    query = state['query'] # Complete the code to define the key for the expanded query
+    # Add original query to the state to improve result.
+    query = f"{state['query']}; {state['expanded_query']}" # Complete the code to define the key for the expanded query
     #print("Query used for retrieval:", query)  # Debugging: Print the query
 
     # Retrieve documents from the vector store
@@ -575,17 +568,13 @@ class NutritionBot:
         # Initialize a memory client to store and retrieve customer interactions
         self.memory = MemoryClient(api_key=MEM0_api_key) # userdata.get("mem0"))  # Complete the code to define the memory client API key
 
-        #st.write(f"my_api_key:{my_api_key}")
-        api_key = os.environ["API_KEY"]
-        st.write(f"api_key:{api_key}")
-        '''
-        model="gpt-4o",
-        temperature=0.0,
-        streaming=False, # Explicitly disabling streaming
-        api_key=my_api_key,
-        openai_api_key=my_api_key,
-        #base_url=endpoint,
-        #openai_api_base=endpoint # api_key
+        self.client = ChatOpenAI(
+            model_name="gpt-4o-mini",  # Specify the model to use (e.g., GPT-4 optimized version)
+            api_key = api_key, # config.get("API_KEY"),  # API key for authentication
+            endpoint = endpoint, # config.get("OPENAI_API_BASE"),
+            temperature=0  # Controls randomness in responses; 0 ensures deterministic results
+        )
+
         '''
         try:
           self.client = ChatOpenAI(
@@ -600,6 +589,7 @@ class NutritionBot:
         except Exception as e:
           print(f"Error with OpenAI: {str(e)}")
           return None
+        '''
 
         # Define tools available to the chatbot, such as web search
         tools = [agentic_rag]