Upload app.py with huggingface_hub

app.py

@@ -19,10 +19,16 @@ from langchain_community.agent_toolkits import create_sql_agent
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_core.tools import tool
 from langchain.agents import create_tool_calling_agent, AgentExecutor
+from langchain.agents import initialize_agent, Tool, AgentType
+from langchain.llms import OpenAI
 from langchain_community.vectorstores import Chroma
 from huggingface_hub import CommitScheduler
+from pydantic import BaseModel, Field, validator
+from langchain.llms import OpenAI
 from pathlib import Path
 
+np.float_ = np.float64
+
 from langchain_core.caches import BaseCache
 from langchain_openai.chat_models import ChatOpenAI
 
@@ -33,9 +39,8 @@ ChatOpenAI.model_rebuild()
 
 model_name = "gpt-4o-mini"
 
-#config = read_config("config_GANLP.json")  #Copy and paste the path of the config file uploaded in Colab
-api_key = "gl-U2FsdGVkX1/DTLQlsmj+RdJjPy3igB9qINuaX940XtJ0CPnGc/5sbBkPKah/C829"
-endpoint = "https://aibe.mygreatlearning.com/openai/v1"
+api_key = os.getenv("OPENAI_API_KEY")
+endpoint = os.getenv("OPENAI_API_BASE")
 
 # Define the location of the SQLite database
 db_loc = 'ecomm.db'
@@ -106,11 +111,10 @@ full_prompt = ChatPromptTemplate.from_messages(
 
 #Initialize the ChatOpenAI model with the extracted configuration
 llm = ChatOpenAI(
-    endpoint="https://aibe.mygreatlearning.com/openai/v1",
-    api_key="gl-U2FsdGVkX1/DTLQlsmj+RdJjPy3igB9qINuaX940XtJ0CPnGc/5sbBkPKah/C829",
-    model="gpt-4o-mini",
-    streaming=False  # Explicitly disabling streaming
-)
+    openai_api_base=endpoint,
+    openai_api_key=api_key,
+    model="gpt-4o-mini",  # Fill in the deployment name (e.g., gpt-4o-mini)
+    streaming=False)
 
 
 # Create the SQL agent using the ChatOpenAI model, database, and prompt template
@@ -123,31 +127,87 @@ sqlite_agent = create_sql_agent(
     max_iterations=5,
     verbose=True
 )
+
+conn = sqlite3.connect('/content/ecomm.db')
+cursor = conn.cursor()
 #### Let's convert the sql agent into a tool that our fin agent can use.
 
-@tool
-def sql_tool(user_input):
+# @tool
+# def sql_tool(user_input):
+#     """
+#     Gathers information regarding purchases, transactions, returns, refunds, etc.
+#     Executes a SQL query using the sqlite_agent and returns the result.
+#     Args:
+#         user_input (str): a natural language query string explaining what information is required while also providing the necessary details to get the information.
+#     Returns:
+#         str: The result of the SQL query execution. If an error occurs, the exception is returned as a string.
+#     """
+#     try:
+#         # Invoke the sqlite_agent with the user input (SQL query)
+#         response = sqlite_agent.invoke(user_input)
+
+#         # Extract the output from the response
+#         prediction = response['output']
+
+#     except Exception as e:
+#         # If an exception occurs, capture the exception message
+#         prediction = e
+
+#     # Return the result or the exception message
+#     return prediction
+
+
+def def_tool(query: str):
     """
-    Gathers information regarding purchases, transactions, returns, refunds, etc.
-    Executes a SQL query using the sqlite_agent and returns the result.
+    Executes a SQL query using the agent and returns the result based on the natural language query.
+
     Args:
-        user_input (str): a natural language query string explaining what information is required while also providing the necessary details to get the information.
+        query (str): A natural language query string to be processed by the agent.
+
     Returns:
-        str: The result of the SQL query execution. If an error occurs, the exception is returned as a string.
+        str: The result of the SQL query execution or any error message.
     """
     try:
-        # Invoke the sqlite_agent with the user input (SQL query)
-        response = sqlite_agent.invoke(user_input)
+        # Define the sql_tool function which is responsible for executing the query
+        @tool
+        def sql_tool(query: str):
+            """Executes a SQL query on the e-commerce database and returns the result."""
+            try:
+                conn = sqlite3.connect('/content/ecomm.db')
+                cursor = conn.cursor()
+                cursor.execute(query)
+                result = cursor.fetchall()
+                conn.close()
+                return result
+            except Exception as e:
+                return str(e)
+
+        # Define the tools array for agent
+        tools = [
+            Tool(
+                name="SQLite Tool",
+                func=sql_tool,
+                description="Execute SQL queries"
+            )
+        ]
+
+        # Initialize the agent with the tools
+        agent = initialize_agent(
+            tools,
+            agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+            llm=llm,  # Assuming llm is predefined somewhere
+            verbose=True
+        )
 
-        # Extract the output from the response
-        prediction = response['output']
+        # Use the agent to run the natural language query
+        response = agent.run(query)
 
-    except Exception as e:
-        # If an exception occurs, capture the exception message
-        prediction = e
+        # Return the response
+        return response
 
-    # Return the result or the exception message
-    return prediction
+    except Exception as e:
+        # If an error occurs in the process, capture and return the exception
+        return str(e)
 
 #=================================== RAG TOOL======================================#
 qna_system_message = """
@@ -522,8 +582,8 @@ def chatbot_interface():
 
             try:
                 # Pass the history to the agent
+                # response = agent_executor.invoke({"input": conversation_input})
                 response = agent_executor.invoke({"input": conversation_input})
-
                 # Add the chatbot's response to the history
                 chatbot_response = response['output']
                 st.session_state.conversation_history.append({"role": "assistant", "content": chatbot_response})