Update app.py

app.py

@@ -0,0 +1,159 @@
+import streamlit as st
+import pandas as pd
+import sqlite3
+import os
+from crewai import Agent, Crew, Process, Task
+from crewai.tools import tool
+from langchain_groq import ChatGroq
+from langchain_openai import ChatOpenAI
+from langchain_community.tools.sql_database.tool import (
+    InfoSQLDatabaseTool,
+    ListSQLDatabaseTool,
+    QuerySQLDataBaseTool,
+)
+from langchain_community.utilities.sql_database import SQLDatabase
+from datasets import load_dataset
+import tempfile
+
+st.title("Blah App")
+st.write("Analyze datasets using natural language queries.")
+
+def initialize_llm(model_choice):
+    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.")
+            return None
+        return 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.")
+            return None
+        return ChatOpenAI(api_key=openai_api_key, model="gpt-4o")
+
+model_choice = st.radio("Select LLM", ["GPT-4o", "llama-3.3-70b"], index=0, horizontal=True)
+llm = initialize_llm(model_choice)
+
+def load_dataset_into_session():
+    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:
+                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(10))
+            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(10))
+
+if "df" not in st.session_state:
+    st.session_state.df = None
+load_dataset_into_session()
+
+def initialize_database(df):
+    temp_dir = tempfile.TemporaryDirectory()
+    db_path = os.path.join(temp_dir.name, "patent_data.db")
+    connection = sqlite3.connect(db_path)
+    df.to_sql("patents", connection, if_exists="replace", index=False)
+    db = SQLDatabase.from_uri(f"sqlite:///{db_path}")
+    return db, temp_dir
+
+def create_sql_tools(db):
+    @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)
+
+    return list_tables, tables_schema, execute_sql
+
+def initialize_agents(llm, tools):
+    list_tables, tables_schema, execute_sql = tools
+
+    sql_agent = Agent(
+        role="Patent Data Analyst",
+        goal="Extract patent data using optimized SQL queries.",
+        backstory="Expert in optimized SQL for patent databases.",
+        llm=llm,
+        tools=[list_tables, tables_schema, execute_sql],
+    )
+
+    analyst_agent = Agent(
+        role="Patent Data Analyst",
+        goal="Analyze the data and produce insights.",
+        backstory="Data analyst identifying trends.",
+        llm=llm,
+    )
+
+    writer_agent = Agent(
+        role="Patent Report Writer",
+        goal="Summarize patent insights into a report.",
+        backstory="Expert in clear, concise reporting.",
+        llm=llm,
+    )
+
+    return sql_agent, analyst_agent, writer_agent
+
+def setup_crew(sql_agent, analyst_agent, writer_agent):
+    extract_task = Task(
+        description="Extract patents related to the query: {query}.",
+        expected_output="Patent data matching the query.",
+        agent=sql_agent,
+    )
+
+    analyze_task = Task(
+        description="Analyze the extracted patent data.",
+        expected_output="Analysis text summarizing findings.",
+        agent=analyst_agent,
+        context=[extract_task],
+    )
+
+    report_task = Task(
+        description="Summarize analysis into a report.",
+        expected_output="Markdown report of insights.",
+        agent=writer_agent,
+        context=[analyze_task],
+    )
+
+    return Crew(
+        agents=[sql_agent, analyst_agent, writer_agent],
+        tasks=[extract_task, analyze_task, report_task],
+        process=Process.sequential,
+        verbose=True,
+    )
+
+if st.session_state.df is not None:
+    db, temp_dir = initialize_database(st.session_state.df)
+    tools = create_sql_tools(db)
+    sql_agent, analyst_agent, writer_agent = initialize_agents(llm, tools)
+    crew = setup_crew(sql_agent, analyst_agent, writer_agent)
+
+    query = st.text_area("Enter Patent Analysis Query:", value="How many patents related to Machine Learning were filed after 2016?")
+    if st.button("Submit Query"):
+        if query.strip():
+            with st.spinner("Processing your query..."):
+                result = crew.kickoff(inputs={"query": query})
+                st.markdown("### 📊 Patent Analysis Report")
+                st.markdown(result)
+        else:
+            st.warning("Please enter a valid query.")
+else:
+    st.info("Please load a patent dataset to proceed.")