Closed stationeros closed 10 months ago
I would like to contribute to it
@kshitiz305 Assigned you this
@stationeros If this issue is not yet resolved, I would like to contribute to this issue.
@kshitiz305 Can you confirm if you are still working on this ?
@stationeros Since I am on a new job hunt I was not able to focus on this for a while, let me have a look into this
@bazzyadb Would you be interested in making some other contribution ?
@stationeros I can take https://github.com/intuit/Trapheus/issues/171
Sure
@stationeros Are there any models that need to added beyond gpt-4, gpt-4-0613, gpt-4-32k, gpt-4-32k-0613, gpt-3.5-turbo, gpt-3.5-turbo-0613, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613
Reference: https://platform.openai.com/docs/models/model-endpoint-compatibility
For starters we can use gpt-4, gpt-4-32k and gpt-3.5-turbo
This pull request has been automatically closed because it has been inactive for more than 14 days. Please reopen if you still intend to submit this pull request.
Have a look at the TrapheusAI demo https://github.com/intuit/Trapheus/tree/master/labs/TrapheusAI#-demo
We want the user to be given an option to choose between LLM models , which enables them to acquire a type of accuracy and exactness which is beyond just language related stuff.
Also the dataset might contain embedded contextual information (schema, short forms) that might not be standardised across the datasets for the same search query, hence might not be well learned by all models.
Hence allowing the users to choose model and iterate on the search.
https://github.com/intuit/Trapheus/blob/master/labs/TrapheusAI/llm/model.py#L22