together-ai
#10558
model_input_error
The selected model does not support image inputs.
This error has been identified and solved.
Reason
The 400 status error in the TogetherAI API, indicating a "Bad Request," in this context is likely due to the following reasons:
Incorrect Model Type
The target model you are using is not a vision model, which means it is not designed to handle image inputs. This mismatch between the model type and the input type (image) is a primary cause of the error.
Data Schema Violations
The structure and format of the data sent in the request (specifically, including image inputs) do not comply with the data schema defined for the model you are using. Since the model does not support image inputs, the request violates the expected data schema.
Solution
To fix the 400 status error in the TogetherAI API, you can take the following steps:
Ensure you are using a model that is compatible with the type of input you are providing. Here are some key actions to consider:
Use the correct model type: Switch to a model that supports the input type you are using, such as a vision model if you are sending image inputs.
Check the API documentation: Review the TogetherAI API documentation to ensure your request adheres to the expected format and parameters for the specific model.
Remove unsupported inputs: If the model does not support image inputs, remove these from your request to avoid data schema violations.
Verify input format: Ensure that the structure and format of your input data comply with the defined schema for the model you are using.
Suggested Links
https://portkey.ai/collection/input-error-10148
https://www.googlecloudcommunity.com/gc/AI-ML/Gemini-Pro-Vision-API-error-Unable-to-submit-request-because-it/m-p/784566
https://github.com/evo-design/evo/issues/95
https://github.com/openai/openai-openapi/issues/15
https://www.npmjs.com/package/together-ai?activeTab=readme
https://github.com/guidance-ai/guidance/issues/795
https://js.langchain.com/docs/integrations/chat/togetherai/
https://github.com/charmbracelet/mods/issues/206
https://community.retool.com/t/gpt-4-vision-not-working/32758
