Alwrity - Bug fixes

lib/gpt_providers/audio_to_text_generation/stt_audio_blog.py

@@ -79,7 +79,7 @@ def speech_to_text(video_url, output_path='.'):
             logger.info("Transcribing using OpenAI's Whisper model.")
             transcript = client.audio.transcriptions.create(
                 model="whisper-1",
-                file=open(audio_file, "rb"),
+                file=open(audio_file, "rb", encoding="utf-8"),
                 response_format="text"
             )
             logger.info(f"\nYouTube video transcription:\n{yt.title}\n{transcript}\n")
@@ -133,7 +133,7 @@ def long_video(temp_file_name):
     for i, chunk in enumerate(chunks):
         with tempfile.NamedTemporaryFile(suffix=".mp3", delete=False) as audio_chunk_file:
             chunk.write_audiofile(audio_chunk_file.name, codec="mp3")
-            with open(audio_chunk_file.name, "rb") as audio_file:
+            with open(audio_chunk_file.name, "rb", encoding="utf-8") as audio_file:
                 # Transcribe each chunk using OpenAI's Whisper API
                 app.logger.info(f"Transcribing chunk {i+1}/{len(chunks)}")
                 transcript = openai.Audio.transcribe("whisper-1", audio_file)

lib/gpt_providers/image_generation/gen_variation_img.py

@@ -35,7 +35,7 @@ def gen_new_from_given_img(img_path, image_dir, num_img=1, img_size="1024x1024",
 
         client = OpenAI()
         variation_response = client.images.create_variation(
-            image=open(img_path, "rb"),
+            image=open(img_path, "rb", encoding="utf-8"),
             n=num_img,
             size=img_size,
             response_format=response_format

lib/gpt_providers/image_to_text_gen/openai_vision_img_details.py

@@ -32,7 +32,7 @@ def analyze_and_extract_details_from_image(image_path):
 
         def encode_image(path):
             """ Encodes an image to a base64 string. """
-            with open(path, "rb") as image_file:
+            with open(path, "rb", encoding="utf-8") as image_file:
                 return base64.b64encode(image_file.read()).decode('utf-8')
 
         base64_image = encode_image(image_path)

lib/gpt_providers/text_generation/gemini_pro_text.py

@@ -4,6 +4,7 @@ import sys
 from pathlib import Path
 
 import google.generativeai as genai
+from google.api_core import retry
 from dotenv import load_dotenv
 load_dotenv(Path('../../../.env'))
 from loguru import logger
@@ -13,16 +14,10 @@ logger.add(sys.stdout,
         format="<level>{level}</level>|<green>{file}:{line}:{function}</green>| {message}"
     )
 
-from tenacity import (
-    retry,
-    stop_after_attempt,
-    wait_random_exponential,
-)  # for exponential backoff
 
-
-@retry(wait=wait_random_exponential(min=1, max=60), stop=stop_after_attempt(6))
 def gemini_text_response(prompt, temperature, top_p, n, max_tokens):
     """ Common functiont to get response from gemini pro Text. """
+    #FIXME: Include : https://github.com/google-gemini/cookbook/blob/main/quickstarts/rest/System_instructions_REST.ipynb
     try:
         genai.configure(api_key=os.getenv('GEMINI_API_KEY'))
     except Exception as err:
@@ -35,10 +30,13 @@ def gemini_text_response(prompt, temperature, top_p, n, max_tokens):
         "top_k": n,
         "max_output_tokens": max_tokens
     }
+    # FIXME: Expose model_name in main_config
     model = genai.GenerativeModel(model_name="gemini-1.0-pro", generation_config=generation_config)
     try:
-        response = model.generate_content(prompt, stream=True)
+        # text_response = []
+        response = model.generate_content(prompt, stream=True, request_options={'retry':retry.Retry()})
         for chunk in response:
+            # text_response.append(chunk.text)
             print(chunk.text)
         return response.text
     except Exception as err: