llama_index

llama_index copied to clipboard

When we create a Index using "GPTSimpleVectorIndex" the index becomes a class. So we can use the method "ask" of this class. Then we have a "response" as a result.

Is there an upper limit to the length of the ask method response string?

It seems to me that in some cases the response string is cut, when the sting response is big.

@BrunoAPazetti the response string can be cut off, usually because the default max_tokens from a single OpenAI call is 256

See this page here for extending that: https://gpt-index.readthedocs.io/en/latest/how_to/custom_llms.html#example-changing-the-number-of-output-tokens-for-openai-cohere-ai21

@logan-markewich's answer is right on. Closing issue for now.

Thank you!

@BrunoAPazetti the response string can be cut off, usually because the default max_tokens from a single OpenAI call is 256

See this page here for extending that: https://gpt-index.readthedocs.io/en/latest/how_to/custom_llms.html#example-changing-the-number-of-output-tokens-for-openai-cohere-ai21

Seems like this link no longer works. Is there another resource that describes how to fix this issue?

@jmcrook

https://gpt-index.readthedocs.io/en/latest/how_to/customization/custom_llms.html#example-changing-the-number-of-output-tokens-for-openai-cohere-ai21