Implement models API #344
Merged
Implement models API #344
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
…ods are built, and to better organize code now that we're adding models
…s endpoints, undo the breaking change in the embed function
austin-denoble
added a commit
that referenced
this pull request
May 9, 2025
## Problem
Inference has new APIs which were made available in `2025-04`. These
allow for listing and describing available models hosted by Pinecone.
## Solution
- I took the liberty to refactor the `Inference` class to better align
with other classes used in a similar way such as `Index` and `Pinecone`.
I broke out all inference actions into individual files / functions:
`embed.ts` and `rerank.ts`. I think a lot of this was implemented rather
quickly initially, so I've done a bunch of cleanup while I was in here
adding new methods.
- Add new `getModel.ts` and `listModels.ts` files/functions. These are
called and documented inside `Inference`.
- Rework unit tests for `embed` and `rerank`. Basically just
standardized to how we do mocking / testing elsewhere. They were a bit
awkward.
- Add unit tests for `getModel`, `listModels`, along with an integration
test file.
- Update README to add examples working with models.
## Type of Change
- [ ] Bug fix (non-breaking change which fixes an issue)
- [X] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [ ] This change requires a documentation update
- [ ] Infrastructure change (CI configs, etc)
- [ ] Non-code change (docs, etc)
- [ ] None of the above: (explain here)
## Test Plan
CI - external test, unit tests, integration tests
To test this you can pull this branch down, and run the repl locally:
from `pinecone-ts-client` root:
```
export PINECONE_API_KEY=<here>
npm run repl
await init()
await client.inference.listModels()
await client.inference.getModel('multilingual-e5-large')
```
---
- To see the specific tasks where the Asana app for GitHub is being
used, see below:
- https://app.asana.com/0/0/1209828518477622
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.
Problem
Inference has new APIs which were made available in
2025-04. These allow for listing and describing available models hosted by Pinecone.Solution
Inferenceclass to better align with other classes used in a similar way such asIndexandPinecone. I broke out all inference actions into individual files / functions:embed.tsandrerank.ts. I think a lot of this was implemented rather quickly initially, so I've done a bunch of cleanup while I was in here adding new methods.getModel.tsandlistModels.tsfiles/functions. These are called and documented insideInference.embedandrerank. Basically just standardized to how we do mocking / testing elsewhere. They were a bit awkward.getModel,listModels, along with an integration test file.Type of Change
Test Plan
CI - external test, unit tests, integration tests
To test this you can pull this branch down, and run the repl locally:
from
pinecone-ts-clientroot: