[Question]: Google Gemini 1.5 flash model support

[dinonovak]

Question Validation

• I have searched both the documentation and discord for an answer.

Question

Hi,

I am trying to use gemini flash with following model definition
llm = Gemini(
model="models/gemini-1.5-flash-latest",
api_key="SOME-KEY",
is_chat_model=True,
is_function_calling_model=False,
temperatue=0.1
)

but on llm.complete() I am getting:
Error 400 Add an image to use models/gemini-pro-vision, or switch your model to a text model.

[dosubot]

To address the error you're encountering with the Gemini 1.5 flash model, it's important to ensure you're using the model correctly for text-based tasks, as it seems you're not intending to use it with images. Here's what you need to do:

1. Correct Model Name: Double-check that the model name "models/gemini-1.5-flash-latest" is correctly specified. This model can handle text inputs without requiring images.

2. Text-Only Requests: If your use case is text-only, make sure not to include any image parameters in your request. The model should work without needing to add images.

3. Including Images: If you decide to include images in the future, you'll need to provide valid ImageDocument objects in the image_documents parameter. Ensure each ImageDocument has a valid image path.

4. API Key and Authentication: Verify that your API key and any other authentication methods are correctly set up. This is crucial for accessing the model without errors.

By following these steps, you should be able to use the Gemini 1.5 flash model for your text or multi-modal tasks without encountering the error. Ensure your environment is correctly configured, especially if you're integrating with Google's API or any other external services.

Details

Sources

• llama-index-legacy/llama_index/legacy/multi_modal_llms/gemini.py
• llama-index-integrations/multi_modal_llms/llama-index-multi-modal-llms-gemini/llama_index/multi_modal_llms/gemini/base.py
• llama-index-integrations/llms/llama-index-llms-openai/llama_index/llms/openai/utils.py
• llama-index-legacy/llama_index/legacy/llms/gemini.py
• llama-index-integrations/llms/llama-index-llms-gemini/llama_index/llms/gemini/base.py
• llama-index-legacy/llama_index/legacy/llms/gemini_utils.py

About Dosu
This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

To continue the conversation, mention @dosu.

[carlisia]

I am having the same issue, and have tried with different generative models.

[edoardolobl]

Unfortunately, I am encountering the same problem. I've tried everything and couldn't find a workaround.