Create interim_v1.py

mylab/interim_v1.py

@@ -0,0 +1,166 @@
+import streamlit as st
+import pandas as pd
+import sqlite3
+import os
+import json
+from pathlib import Path
+from datetime import datetime, timezone
+from crewai import Agent, Crew, Process, Task
+from crewai.tools import tool
+from langchain_groq import ChatGroq
+from langchain_openai import ChatOpenAI
+from langchain.schema.output import LLMResult
+from langchain_core.callbacks.base import BaseCallbackHandler
+from langchain_community.tools.sql_database.tool import (
+    InfoSQLDatabaseTool,
+    ListSQLDatabaseTool,
+    QuerySQLCheckerTool,
+    QuerySQLDataBaseTool,
+)
+from langchain_community.utilities.sql_database import SQLDatabase
+from datasets import load_dataset
+import tempfile
+
+# API Key
+os.environ["GROQ_API_KEY"] = st.secrets.get("GROQ_API_KEY", "")
+
+st.title("Blah Blah App Using CrewAI 🚀")
+st.write("Analyze datasets using natural language queries powered by SQL and CrewAI.")
+
+# Initialize LLM
+llm = None
+
+# Model Selection
+model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
+
+
+# API Key Validation and LLM Initialization
+groq_api_key = os.getenv("GROQ_API_KEY")
+openai_api_key = os.getenv("OPENAI_API_KEY")
+
+if model_choice == "llama-3.3-70b":
+    if not groq_api_key:
+        st.error("Groq API key is missing. Please set the GROQ_API_KEY environment variable.")
+        llm = None
+    else:
+        llm = ChatGroq(groq_api_key=groq_api_key, model="groq/llama-3.3-70b-versatile")
+elif model_choice == "GPT-4o":
+    if not openai_api_key:
+        st.error("OpenAI API key is missing. Please set the OPENAI_API_KEY environment variable.")
+        llm = None
+    else:
+        llm = ChatOpenAI(api_key=openai_api_key, model="gpt-4o")
+        
+# Initialize session state for data persistence
+if "df" not in st.session_state:
+    st.session_state.df = None
+
+# Dataset Input
+input_option = st.radio("Select Dataset Input:", ["Use Hugging Face Dataset", "Upload CSV File"])
+if input_option == "Use Hugging Face Dataset":
+    dataset_name = st.text_input("Enter Hugging Face Dataset Name:", value="HUPD/hupd")
+    if st.button("Load Dataset"):
+        try:
+            with st.spinner("Loading dataset..."):
+                dataset = load_dataset(dataset_name, name="sample", split="train", trust_remote_code=True, uniform_split=True)
+                st.session_state.df = pd.DataFrame(dataset)
+                st.success(f"Dataset '{dataset_name}' loaded successfully!")
+                st.dataframe(st.session_state.df.head())
+        except Exception as e:
+            st.error(f"Error: {e}")
+elif input_option == "Upload CSV File":
+    uploaded_file = st.file_uploader("Upload CSV File:", type=["csv"])
+    if uploaded_file:
+        st.session_state.df = pd.read_csv(uploaded_file)
+        st.success("File uploaded successfully!")
+        st.dataframe(st.session_state.df.head())
+
+
+if st.session_state.df is not None:
+    # Database setup
+    temp_dir = tempfile.TemporaryDirectory()
+    db_path = os.path.join(temp_dir.name, "patent_data.db")
+    connection = sqlite3.connect(db_path)
+    st.session_state.df.to_sql("patents", connection, if_exists="replace", index=False)
+    db = SQLDatabase.from_uri(f"sqlite:///{db_path}")
+
+    # SQL Tools
+    @tool("list_tables")
+    def list_tables() -> str:
+        """List all tables in the patent database."""
+        return ListSQLDatabaseTool(db=db).invoke("")
+
+    @tool("tables_schema")
+    def tables_schema(tables: str) -> str:
+        """Get schema and sample rows for given tables."""
+        return InfoSQLDatabaseTool(db=db).invoke(tables)
+
+    @tool("execute_sql")
+    def execute_sql(sql_query: str) -> str:
+        """Execute a SQL query against the patent database."""
+        return QuerySQLDataBaseTool(db=db).invoke(sql_query)
+
+    # --- CrewAI Agents for Patent Analysis ---
+    patent_sql_dev = Agent(
+        role="Patent Data Analyst",
+        goal="Extract patent data using optimized SQL queries.",
+        backstory="An expert in writing optimized SQL queries for complex patent databases.",
+        llm=llm,
+        tools=[list_tables, tables_schema, execute_sql],
+    )
+
+    patent_data_analyst = Agent(
+        role="Patent Data Analyst",
+        goal="Analyze the data and produce insights.",
+        backstory="A seasoned analyst who identifies trends and patterns in datasets.",
+        llm=llm,
+    )
+
+    patent_report_writer = Agent(
+        role="Patent Report Writer",
+        goal="Summarize patent insights into a clear report.",
+        backstory="Expert in summarizing patent data insights into comprehensive reports.",
+        llm=llm,
+    )
+
+    # --- Crew Tasks ---
+    extract_data = Task(
+        description="Extract patents related to the query: {query}.",
+        expected_output="Patent data matching the query.",
+        agent=patent_sql_dev,
+    )
+
+    analyze_data = Task(
+        description="Analyze the extracted patent data for query: {query}.",
+        expected_output="Analysis text summarizing findings.",
+        agent=patent_data_analyst,
+        context=[extract_data],
+    )
+
+    write_report = Task(
+        description="Summarize analysis into an executive report.",
+        expected_output="Markdown report of insights.",
+        agent=patent_report_writer,
+        context=[analyze_data],
+    )
+
+    # Assemble Crew
+    crew = Crew(
+        agents=[patent_sql_dev, patent_data_analyst, patent_report_writer],
+        tasks=[extract_data, analyze_data, write_report],
+        process=Process.sequential,
+        verbose=True,
+    )
+
+    #Query Input for Patent Analysis
+    query = st.text_area("Enter Patent Analysis Query:", placeholder="e.g., 'How many patents related to Machine Learning were filed after 2016?'")
+    if st.button("Submit Query"):
+        with st.spinner("Processing your query..."):
+            inputs = {"query": query}
+            result = crew.kickoff(inputs=inputs)
+            st.markdown("### 📊 Patent Analysis Report")
+            st.markdown(result)
+
+    temp_dir.cleanup()
+else:
+    st.info("Please load a patent dataset to proceed.")