Deprecate Multi Modal LLMs #19115
Open
Deprecate Multi Modal LLMs #19115
+899
−2,422
Conversation
This file contains hidden or 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
dosubot
bot
added
size:XL
AstraBert
commented
Jun 19, 2025
llama-index-core/llama_index/core/evaluation/multi_modal/faithfulness.py
Show resolved
Hide resolved
...l_llms/llama-index-multi-modal-llms-anthropic/llama_index/multi_modal_llms/anthropic/base.py
Outdated
Show resolved
Hide resolved
...i_modal_llms/llama-index-multi-modal-llms-nvidia/llama_index/multi_modal_llms/nvidia/base.py
Outdated
Show resolved
Hide resolved
…recation messages
dosubot
bot
added
size:XXL
| @@ -116,20 +116,23 @@ def __call__( | |||
| async def acall( | |||
| self, | |||
| llm_kwargs: Optional[Dict[str, Any]] = None, | |||
| image_documents: Optional[List[ImageNode]] = None, | |||
| image_documents: Optional[List[ImageBlock]] = None, | |||
There was a problem hiding this comment.
We should probably continue to handle passing in ImageNode here and just translate it to ImageBlock
| @@ -130,19 +130,22 @@ def evaluate( | |||
| context_str=context_str, query_str=evaluation_query_str | |||
| ) | |||
|
|
|||
| image_nodes: List[Any] = [] | |||
There was a problem hiding this comment.
slightly misleading name (and if we can avoid typing things as Any, that'd be good too)
There was a problem hiding this comment.
(This pops up in a few places)
| for image_node in image_nodes | ||
| if isinstance(image_node.node, ImageNode) | ||
| ], | ||
| image_documents: List[Any] = [ |
There was a problem hiding this comment.
Lets make the variable name and typing here better
| @@ -192,154 +184,165 @@ def _get_response_token_counts(self, raw_response: Any) -> dict: | |||
| } | |||
|
|
|||
| def _complete( | |||
There was a problem hiding this comment.
for complete and stream_complete, I think we can just translate into message dicts, call chat, and convert the chat response to completion response?
There are a few utils for doing this in core that other LLMs use
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.
Description
Deprecate Multi Modal LLMs in favor of multi modal support of their sibling LLM classes.