feat: add solar pro llm and document parser #16099
Conversation
dosubot
bot
added
the
size:XL
| @@ -207,3 +231,50 @@ def get_num_tokens_from_message(self, messages: Sequence[ChatMessage]) -> int: | |||
| ) | |||
| num_tokens += tokens_suffix | |||
| return num_tokens | |||
|
|
|||
| @llm_retry_decorator | |||
| def _chat(self, messages: Sequence[ChatMessage], **kwargs: Any) -> ChatResponse: | |||
There was a problem hiding this comment.
curious why we subclass _chat, but not any other method like _stream_chat or _achat, etc.
There was a problem hiding this comment.
I guess you only support parse documents with .chat() ?
There was a problem hiding this comment.
There was a mistake in following llamaindex interface. Added some more methods.
| for i, doc in enumerate(docs): | ||
| file_title = file_titles[min(i, len(file_titles) - 1)] | ||
| document_contents += f"{file_title}:\n{doc.text}\n\n" | ||
| print("DOCUMENT CONTENTS", document_contents) |
There was a problem hiding this comment.
lets remove this print
| tokenizers = "^0.19.1" | ||
| llama-index-core = "^0.11.0" | ||
| llama-index-llms-openai = "^0.2.0" |
There was a problem hiding this comment.
we need to add the upstage reader as a dependency now right?
There was a problem hiding this comment.
(should also bump the version of the integration package here)
There was a problem hiding this comment.
Or, maybe we need to publish the reader first actually
There was a problem hiding this comment.
Yeah you are right. we should publish reader first.
we need to add the upstage reader as a dependency now right?
yes, we need to add it
There was a problem hiding this comment.
no need to check this in
There was a problem hiding this comment.
no need to check this in
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Description
Add new llm model and readers api of upstage.
New llm model,
solar-procan be found here https://developers.upstage.ai/docs/apis/chat .New document parse model
Document Parsecan be found here https://developers.upstage.ai/docs/apis/document-parse .New Package?
Did I fill in the
tool.llamahubsection in thepyproject.tomland provide a detailed README.md for my new integration or package?Version Bump?
Did I bump the version in the
pyproject.tomlfile of the package I am updating? (Except for thellama-index-corepackage)Type of Change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Suggested Checklist:
make format; make lintto appease the lint gods