Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[inference] Partial revert of #1199, cleaner implem #1201

Merged
merged 3 commits into from
Feb 14, 2025
Merged

[inference] Partial revert of #1199, cleaner implem #1201

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1af3e00
Partial revert of #1199, cleaner implem
julien-c Feb 13, 2025
a282e0a
Update tapes.json
julien-c Feb 13, 2025
32a99cb
re-add test
julien-c Feb 13, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions packages/inference/src/lib/makeRequestOptions.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,10 @@ function makeUrl(params: {
}
default: {
const baseUrl = HF_HUB_INFERENCE_PROXY_TEMPLATE.replaceAll("{{PROVIDER}}", "hf-inference");
if (params.taskHint && ["feature-extraction", "sentence-similarity"].includes(params.taskHint)) {
/// when deployed on hf-inference, those two tasks are automatically compatible with one another.
return `${baseUrl}/pipeline/${params.taskHint}/${params.model}`;
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

would be cleaner if it was /{model}/pipeline/{task}, probably (also simpler to route)

}
if (params.taskHint === "text-generation" && params.chatCompletion) {
return `${baseUrl}/models/${params.model}/v1/chat/completions`;
}
Expand Down
9 changes: 9 additions & 0 deletions packages/inference/test/HfInference.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -351,6 +351,15 @@ describe.concurrent("HfInference", () => {
});
expect(response).toEqual(expect.arrayContaining([expect.any(Number)]));
});
it("FeatureExtraction - auto-compatibility sentence similarity", async () => {
const response = await hf.featureExtraction({
model: "sentence-transformers/paraphrase-xlm-r-multilingual-v1",
inputs: "That is a happy person",
});

expect(response.length).toBeGreaterThan(10);
expect(response).toEqual(expect.arrayContaining([expect.any(Number)]));
});
it("FeatureExtraction - facebook/bart-base", async () => {
const response = await hf.featureExtraction({
model: "facebook/bart-base",
Expand Down
112 changes: 110 additions & 2 deletions packages/inference/test/tapes.json
View file
Open in desktop

Large diffs are not rendered by default.