Review some GenAI assets.

* Fix Python `oci` package versioning.
* Update instructions slightly.
* Git ignore temporary files or remove the need for them.

Author: matz-e

ai/generative-ai-service/decode-Images-and-Videos-with-OCI-GenAI/.gitignore

@@ -0,0 +1,2 @@
+temp_uploaded_image.*
+temp_uploaded_video.*

ai/generative-ai-service/decode-Images-and-Videos-with-OCI-GenAI/README.md

@@ -5,7 +5,7 @@ This is an AI-powered application designed to unlock insights hidden within medi
 
 <img src="./image.png">
 </img>
-Reviewed date: 22.09.2025
+Reviewed date: 09.10.2025
 
 ## Features
 
@@ -39,8 +39,7 @@ Reviewed date: 22.09.2025
 
 ## Installation
 
-1. **Clone the repository:**
-   
+1. **Clone this repository.**
 
 2. **Install dependencies:**
    Make sure you have Python 3.8+ installed. Then, install the required libraries:
@@ -50,7 +49,7 @@ Reviewed date: 22.09.2025
 
 3. **Configure OCI:**
    - Set up your OCI configuration by creating or updating the `~/.oci/config` file with your credentials and profile.
-   - Replace placeholders like `compartmentId`, `llm_service_endpoint`, and `visionModel` in the code with your actual values.
+   - Replace placeholders like `compartmentId`, `llm_service_endpoint`, and `visionModel` in [`app.py`](./app.py) with your actual values.
 
 ---
 

ai/generative-ai-service/decode-Images-and-Videos-with-OCI-GenAI/app.py

@@ -61,7 +61,6 @@ def get_chat_request(encoded_image=None, user_prompt=None):
     return chat_request
 
 def cohere_chat_request(encoded_image=None, user_prompt=None):
-    print(" i am here")
     chat_request = oci.generative_ai_inference.models.CohereChatRequest()
     chat_request.api_format = oci.generative_ai_inference.models.BaseChatRequest.API_FORMAT_COHERE
     message = get_message(encoded_image, user_prompt)
@@ -92,7 +91,7 @@ def extract_frames(video_path, interval=1):
 
     while success:
         if count % (frame_rate * interval) == 0:
-            frames.append(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+            frames.append(frame)
         success, frame = cap.read()
         count += 1
     cap.release()

ai/generative-ai-service/decode-Images-and-Videos-with-OCI-GenAI/requirements.txt

@@ -1,5 +1,5 @@
 streamlit==1.37.0
-oci==3.50.1
+oci>=2.161.0,<3
 Pillow
 opencv-python-headless==4.10.0.84
-tqdm==4.66.3
+tqdm==4.66.3

ai/generative-ai-service/image-to-text/README.md

@@ -3,7 +3,7 @@
 
 This application is built using **Streamlit** and **Oracle OCI Generative AI**, allowing users to upload an image, input a prompt, and receive a text-based response generated by the AI model. It leverages Oracle's Gen AI Inference API for processing multimodal data (text and image).
 
-Reviewed: 22.09.2025
+Reviewed: 09.10.2025
 
 <img src="./image1.png">
 </img>
@@ -38,8 +38,7 @@ Reviewed: 22.09.2025
 
 ## Installation
 
-1. Clone the repository:
-  
+1. Clone this repository.
 
 2. Install dependencies:
    ```bash
@@ -49,6 +48,8 @@ Reviewed: 22.09.2025
 3. Configure OCI:
    Ensure your `~/.oci/config` file is set up with the correct credentials and profile.
 
+4. Edit [`app.py`](./app.py) and insert a valid Compartment OCID.
+
 ---
 
 ## Usage

ai/generative-ai-service/image-to-text/app.py

@@ -9,10 +9,6 @@
 llm_service_endpoint = "https://inference.generativeai.us-chicago-1.oci.oraclecloud.com"
 
 # Define functions
-def encode_image(image_path):
-    with open(image_path, "rb") as image_file:
-        return base64.b64encode(image_file.read()).decode("utf-8")
-
 def get_message(encoded_image, user_prompt):
     content1 = oci.generative_ai_inference.models.TextContent()
     content1.text = user_prompt
@@ -57,20 +53,15 @@ def get_chat_detail(chat_request):
 user_prompt = st.text_input("Enter your prompt for the image:", value="Tell me about this image.")
 
 if uploaded_file:
-    # Save the uploaded image temporarily
-    temp_image_path = "temp_uploaded_image.jpg"
-    with open(temp_image_path, "wb") as f:
-        f.write(uploaded_file.getbuffer())
-    
     # Display the uploaded image
-    st.image(temp_image_path, caption="Uploaded Image", use_column_width=True)
+    st.image(uploaded_file, caption="Uploaded Image", use_column_width=True)
 
     # Process and call the model
     if st.button("Generate Response"):
         with st.spinner("Please wait while the model processes the image..."):
             try:
                 # Encode the image
-                encoded_image = encode_image(temp_image_path)
+                encoded_image = base64.b64encode(uploaded_file.getvalue()).decode("utf-8")
 
                 # Setup OCI client
                 CONFIG_PROFILE = "DEFAULT"

ai/generative-ai-service/image-to-text/requirements.txt

@@ -1,3 +1,3 @@
 streamlit==1.37.0
-oci==3.50.1
-Pillow
+oci>=2.161.0,<3
+Pillow