From 352d8f2162413059a81bf6274eb782e1eec64051 Mon Sep 17 00:00:00 2001
From: Madhu <madhushantangot@gmail.com>
Date: Mon, 17 Mar 2025 19:41:15 +0530
Subject: [PATCH] fixed a few bug - multimodal agent working perfect now

---
 .../multimodal_ai_agent/mutimodal_agent.py    | 97 ++++++++++---------
 1 file changed, 49 insertions(+), 48 deletions(-)

diff --git a/ai_agent_tutorials/multimodal_ai_agent/mutimodal_agent.py b/ai_agent_tutorials/multimodal_ai_agent/mutimodal_agent.py
index 79ee9e3..23b77c1 100644
--- a/ai_agent_tutorials/multimodal_ai_agent/mutimodal_agent.py
+++ b/ai_agent_tutorials/multimodal_ai_agent/mutimodal_agent.py
@@ -1,8 +1,7 @@
 import streamlit as st
 from agno.agent import Agent
 from agno.models.google import Gemini
-from agno.tools.duckduckgo import DuckDuckGoTools
-from google.generativeai import upload_file, get_file
+from agno.media import Video
 import time
 from pathlib import Path
 import tempfile
@@ -15,63 +14,65 @@ st.set_page_config(
 
 st.title("Multimodal AI Agent 🧬")
 
+# Get Gemini API key from user
+gemini_api_key = st.text_input("Enter your Gemini API Key", type="password")
+
 # Initialize single agent with both capabilities
 @st.cache_resource
-def initialize_agent():
+def initialize_agent(api_key):
     return Agent(
         name="Multimodal Analyst",
-        model=Gemini(id="gemini-2.0-flash-exp"),
-        tools=[DuckDuckGoTools()],
+        model=Gemini(id="gemini-2.0-flash", api_key=api_key),
         markdown=True,
     )
 
-agent = initialize_agent()
+if gemini_api_key:
+    agent = initialize_agent(gemini_api_key)
 
-# File uploader
-uploaded_file = st.file_uploader("Upload a video file", type=['mp4', 'mov', 'avi'])
+    # File uploader
+    uploaded_file = st.file_uploader("Upload a video file", type=['mp4', 'mov', 'avi'])
 
-if uploaded_file:
-    with tempfile.NamedTemporaryFile(delete=False, suffix='.mp4') as tmp_file:
-        tmp_file.write(uploaded_file.read())
-        video_path = tmp_file.name
-    
-    st.video(video_path)
-    
-    user_prompt = st.text_area(
-        "What would you like to know?",
-        placeholder="Ask any question related to the video - the AI Agent will analyze it and search the web if needed",
-        help="You can ask questions about the video content and get relevant information from the web"
-    )
-    
-    if st.button("Analyze & Research"):
-        if not user_prompt:
-            st.warning("Please enter your question.")
-        else:
-            try:
-                with st.spinner("Processing video and researching..."):
-                    video_file = upload_file(video_path)
-                    while video_file.state.name == "PROCESSING":
-                        time.sleep(2)
-                        video_file = get_file(video_file.name)
+    if uploaded_file:
+        with tempfile.NamedTemporaryFile(delete=False, suffix='.mp4') as tmp_file:
+            tmp_file.write(uploaded_file.read())
+            video_path = tmp_file.name
+        
+        st.video(video_path)
+        
+        user_prompt = st.text_area(
+            "What would you like to know?",
+            placeholder="Ask any question related to the video - the AI Agent will analyze it and search the web if needed",
+            help="You can ask questions about the video content and get relevant information from the web"
+        )
+        
+        if st.button("Analyze & Research"):
+            if not user_prompt:
+                st.warning("Please enter your question.")
+            else:
+                try:
+                    with st.spinner("Processing video and researching..."):
+                        video = Video(filepath=video_path)
+                        
+                        prompt = f"""
+                        First analyze this video and then answer the following question using both 
+                        the video analysis and web research: {user_prompt}
+                        
+                        Provide a comprehensive response focusing on practical, actionable information.
+                        """
+                        
+                        result = agent.run(prompt, videos=[video])
+                        
+                    st.subheader("Result")
+                    st.markdown(result.content)
 
-                    prompt = f"""
-                    First analyze this video and then answer the following question using both 
-                    the video analysis and web research: {user_prompt}
-                    
-                    Provide a comprehensive response focusing on practical, actionable information.
-                    """
-                    
-                    result = agent.run(prompt, videos=[video_file])
-                    
-                st.subheader("Result")
-                st.markdown(result.content)
-
-            except Exception as e:
-                st.error(f"An error occurred: {str(e)}")
-            finally:
-                Path(video_path).unlink(missing_ok=True)
+                except Exception as e:
+                    st.error(f"An error occurred: {str(e)}")
+                finally:
+                    Path(video_path).unlink(missing_ok=True)
+    else:
+        st.info("Please upload a video to begin analysis.")
 else:
-    st.info("Please upload a video to begin analysis.")
+    st.warning("Please enter your Gemini API key to continue.")
 
 st.markdown("""
     <style>