refact: make GeminiMultiModal a thin wrapper around Gemini #17501
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dosubot
bot
added
the
size:L
masci
commented
Jan 13, 2025
| self._guess_mimetype(decoded_img) | ||
| return self | ||
|
|
||
| def _guess_mimetype(self, img_data: bytes) -> None: |
There was a problem hiding this comment.
Adding this function to guess the mimetype not only in the init but also every time we resolve the image
masci
commented
Jan 13, 2025
| @@ -26,6 +26,9 @@ class CustomLLM(LLM): | |||
| `_stream_complete`, and `metadata` methods. | |||
| """ | |||
|
|
|||
| def __init__(self, *args: Any, **kwargs: Any): | |||
| super().__init__(*args, **kwargs) | |||
There was a problem hiding this comment.
This is to make mypy happy
There was a problem hiding this comment.
Mypy never had an issue with this before?
There was a problem hiding this comment.
sorry it was Pyright not mypy, it's mostly annoying in IDEs
masci
commented
Jan 13, 2025
| @@ -17,17 +18,21 @@ | |||
| MessageRole.TOOL: MessageRole.USER, | |||
| MessageRole.FUNCTION: MessageRole.USER, | |||
| } | |||
| ROLES_FROM_GEMINI: Dict[MessageRole, MessageRole] = { | |||
There was a problem hiding this comment.
I think this worked only brecause MessageRole derives from str but let's be explicit
llama-index-integrations/llms/llama-index-llms-gemini/llama_index/llms/gemini/base.py
Show resolved
Hide resolved
llama-index-integrations/llms/llama-index-llms-gemini/llama_index/llms/gemini/base.py
Outdated
Show resolved
Hide resolved
...i_modal_llms/llama-index-multi-modal-llms-gemini/llama_index/multi_modal_llms/gemini/base.py
Outdated
Show resolved
Hide resolved
masci
force-pushed
the
massi/gemini-refact
branch
from
1b19bcf to
af2aab2
Compare
dosubot
bot
added
size:XL
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
masci
force-pushed
the
massi/gemini-refact
branch
from
0c0af0d to
ac32d8b
Compare
fix unit test fix request_options handling save progress address review comment update notebook example fix completion docs handling
masci
force-pushed
the
massi/gemini-refact
branch
from
1f2ed00 to
a80e2ab
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Blocked on #17509
Description
llms.gemini.Geminiclass.GeminiMultiModalclass a thin wrapper aroundGeminito keep backward compatibilityPart of #15950
Version Bump?
Not releasing the package multimodal llm package, that needs to happen after we release core.