2.2.gemini.md

Investigate the Google Gemini API

We following the instructions to set up the Google Gemini API documentation.

1. Prerequisites:

   • Install Python packages:

     pip install -q -U google-genai

2. Test the API for generating content:

   • Run the following code:

     from google import genai
     
     client = genai.Client(api_key="YOUR_API_KEY")
     response = client.models.generate_content(
     model="gemini-2.0-flash", 
     contents="Explain how AI works"
     )
     print(response.text)

   • Run the structured prompts:

     from google import genai
     
     prompt = """List a few popular cookie recipes in JSON format.
     
     Use this JSON schema:
     
     Recipe = {'recipe_name': str, 'ingredients': list[str]}
     Return: list[Recipe]"""
     
     client = genai.Client(api_key="GEMINI_API_KEY")
     response = client.models.generate_content(
         model='gemini-2.0-flash',
         contents=prompt,
     )
     
     # Use the response as a JSON string.
     print(response.text)

3. Test the API for captions/answers:

   • Run the following code:

     from PIL import Image
     from google import genai
     
     client = genai.Client(api_key="GEMINI_API_KEY")
     
     image = Image.open("sample.png")
     response = client.models.generate_content(
         model="gemini-2.0-flash",
         contents=[image, "Generate the detailed description of the image"])
     print(response.text)

More documentation can be found here.

4. Test the API for transcription or describing an audio:

   • Run the following code:

     myfile = client.files.upload(file='sample.mp3')
     prompt = 'Generate a transcript of the speech.'
     
     response = client.models.generate_content(
     model='gemini-2.0-flash',
     contents=[
         prompt,
         myfile]
     )
     
     print(response.text)

5. Test the API for image generation (need setup an a paid account):

   • Run the following code:

     from google import genai
     from google.genai import types
     from PIL import Image
     from io import BytesIO
     
     client = genai.Client(api_key='GEMINI_API_KEY')
     
     response = client.models.generate_images(
         model='imagen-3.0-generate-002',
         prompt='Fuzzy samoyed on snow',
         config=types.GenerateImagesConfig(
             number_of_images= 4,
         )
     )
     for generated_image in response.generated_images:
     image = Image.open(BytesIO(generated_image.image.image_bytes))
     image.show()

6. Test Deep search API by searching in Google Search:

   • Run the following code:

     from google import genai
     from google.genai.types import Tool, GenerateContentConfig, GoogleSearch
     
     client = genai.Client()
     model_id = "gemini-2.0-flash"
     
     google_search_tool = Tool(
         google_search = GoogleSearch()
     )
     
     response = client.models.generate_content(
         model=model_id,
         contents="When is the next total solar eclipse in the United States?",
         config=GenerateContentConfig(
             tools=[google_search_tool],
             response_modalities=["TEXT"],
         )
     )
     
     for each in response.candidates[0].content.parts:
         print(each.text)
     # Example response:
     # The next total solar eclipse visible in the contiguous United States will be on ...
     
     # To get grounding metadata as web content.
     print(response.candidates[0].grounding_metadata.search_entry_point.rendered_content)

Return README.md