generative-ai-python

google.generativeai.types.GenerateContentResponse

Instances of this class manage the response of the generate_content method.

google.generativeai.types.GenerateContentResponse(
    done: bool,
    iterator: (None | Iterable[protos.GenerateContentResponse] | AsyncIterable[protos.
        GenerateContentResponse]),
    result: protos.GenerateContentResponse,
    chunks: (Iterable[protos.GenerateContentResponse] | None) = None
)

These are returned by GenerativeModel.generate_content and ChatSession.send_message. This object is based on the low level protos.GenerateContentResponse class which just has prompt_feedback and candidates attributes. This class adds several quick accessors for common use cases.

The same object type is returned for both stream=True/False.

Streaming

When you pass stream=True to GenerativeModel.generate_content or ChatSession.send_message, iterate over this object to receive chunks of the response:

response = model.generate_content(..., stream=True):
for chunk in response:
  print(chunk.text)

GenerateContentResponse.prompt_feedback is available immediately but GenerateContentResponse.candidates, and all the attributes derived from them (.text, .parts), are only available after the iteration is complete.

Attributes

`candidates` The list of candidate responses.
`parts` A quick accessor equivalent to `self.candidates[0].content.parts`
`prompt_feedback`
`text` A quick accessor equivalent to `self.candidates[0].content.parts[0].text`
`usage_metadata`

Methods

from_iterator

View source

@classmethod
from_iterator(
    iterator: Iterable[protos.GenerateContentResponse]
)

from_response

View source

@classmethod
from_response(
    response: protos.GenerateContentResponse
)

resolve

View source

resolve()

to_dict

View source

to_dict()

Returns the result as a JSON-compatible dict.

Note: This doesn’t capture the iterator state when streaming, it only captures the accumulated GenerateContentResponse fields.

>>> import json
>>> response = model.generate_content('Hello?')
>>> json.dumps(response.to_dict())

__iter__

View source

__iter__()
This site is open source. Improve this page.