Update app.py

app.py

@@ -1,74 +1,58 @@
+import os
 import streamlit as st
 import pandas as pd
-from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
-from langchain_google_genai import ChatGoogleGenerativeAI
-import os
-import traceback
-
-def main():
-    st.set_page_config(page_title="Data Analysis Agent 🤖")
-    st.title("🤖 Data Analysis Agent")
-    st.write("Upload a CSV file and ask questions about your data.")
-
-    # --- API Key Setup ---
-    # This block tries to get the API key from Hugging Face secrets
-    api_key = None
-    try:
-        api_key = st.secrets["GEMINI_API_KEY"]
-    except KeyError:
-        st.error("🔴 GEMINI_API_KEY not found in Hugging Face secrets!")
-        st.write("Please go to your Space's **Settings > Repository secrets** and add your Google AI Studio API key.")
-        st.write("The **Name** must be `GEMINI_API_KEY`.")
-        return # Stop the app if key is missing
-
-    if not api_key:
-        st.warning("Please add your Gemini API Key to the Hugging Face Space Secrets to use the app.")
-        return
-
-    # --- File Uploader ---
-    uploaded_file = st.file_uploader("Upload your CSV file", type=["csv"])
-
-    if uploaded_file is not None:
+import numpy as np
+import requests
+
+# --- CONFIG ---
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
+if not GEMINI_API_KEY:
+    st.error("❌ Missing Gemini API key. Add it as a secret: GEMINI_API_KEY")
+    st.stop()
+
+GEMINI_BASE = "https://generativelanguage.googleapis.com/v1beta"
+CHAT_MODEL = "models/gemini-1.5-flash"
+EMBED_MODEL = "models/embedding-001"
+
+# --- Helper Functions ---
+def get_embedding(text):
+    url = f"{GEMINI_BASE}/{EMBED_MODEL}:embedText?key={GEMINI_API_KEY}"
+    data = {"text": text}
+    r = requests.post(url, json=data)
+    r.raise_for_status()
+    return r.json()["embedding"]["value"]
+
+def chat_with_gemini(prompt, context=""):
+    url = f"{GEMINI_BASE}/{CHAT_MODEL}:generateContent?key={GEMINI_API_KEY}"
+    payload = {
+        "contents": [
+            {"parts": [{"text": f"{context}\n\nUser question: {prompt}"}]}
+        ]
+    }
+    r = requests.post(url, json=payload)
+    r.raise_for_status()
+    data = r.json()
+    return data["candidates"][0]["content"]["parts"][0]["text"]
+
+# --- UI ---
+st.title("📊 Data Analyst Agent (Gemini + Streamlit)")
+st.write("Upload a CSV file and ask natural language questions about your data.")
+
+uploaded = st.file_uploader("Upload CSV", type=["csv"])
+
+if uploaded:
+    df = pd.read_csv(uploaded)
+    st.dataframe(df.head())
+
+    question = st.text_input("Ask a question about your data:")
+    if st.button("Analyze") and question:
+        # Summarize dataset for context
+        summary = f"Columns: {', '.join(df.columns)}. Example rows:\n{df.head(3).to_string(index=False)}"
         try:
-            df = pd.read_csv(uploaded_file)
-            st.dataframe(df.head())
-
-            # Initialize the Gemini LLM
-            llm = ChatGoogleGenerativeAI(
-                model="gemini-1.5-pro-latest", # Using the latest, most capable model
-                google_api_key=api_key,
-                temperature=0
-            )
-
-            # Create the Pandas DataFrame Agent
-            agent = create_pandas_dataframe_agent(
-                llm,
-                df,
-                verbose=True, # This will print the agent's thoughts in the log
-                allow_dangerous_code=True,
-                handle_parsing_errors=True # Helps with bad LLM outputs
-            )
-
-            # --- User Interaction ---
-            user_question = st.text_input("Ask a question about your data:")
-
-            if user_question:
-                with st.spinner("Analyzing..."):
-                    try:
-                        # Invoke the agent
-                        response = agent.invoke(user_question)
-                        st.write("### Answer")
-                        st.success(response["output"])
-                    
-                    except Exception as e:
-                        # This is the most important error block
-                        st.error(f"🔴 An error occurred while analyzing the data.")
-                        st.write("Here is the full error message:")
-                        # Print the full error stack trace to the app
-                        st.exception(e)
-
+            response = chat_with_gemini(question, summary)
+            st.markdown("### 💬 Gemini Answer:")
+            st.write(response)
         except Exception as e:
-            st.error(f"🔴 An error occurred while reading the file: {e}")
-
-if __name__ == "__main__":
-    main()
+            st.error(f"Error: {e}")
+else:
+    st.info("👆 Upload a CSV file to begin.")