feat: add Gemini embedContent tracking#3369
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Prompt To Fix All With AIThis is a comment left during a code review.
Path: packages/ai/tests/gemini.test.ts
Line: 970-993
Comment:
**Prefer parametrised tests for token-count scenarios**
These two test cases exercise the same `extractEmbeddingTokenCount` path with different mock responses and expected values. Per the project's preference, they could be expressed as a single `test.each`:
```ts
test.each([
['with Vertex AI statistics', mockEmbedResponseWithStats, 13],
['without statistics', mockEmbedResponse, 0],
])('token count %s', async (_, mockResponse, expectedTokens) => {
;(client as any).client.models.embedContent = jest.fn().mockResolvedValue(mockResponse)
await client.models.embedContent({
model: 'gemini-embedding-001',
contents: 'Hello',
posthogDistinctId: 'test-id',
})
const [captureArgs] = (mockPostHogClient.capture as jest.Mock).mock.calls
expect(captureArgs[0].properties['$ai_input_tokens']).toBe(expectedTokens)
})
```
How can I resolve this? If you propose a fix, please make it concise.Reviews (1): Last reviewed commit: "feat: add gemini embedContent tracking s..." | Re-trigger Greptile |
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Comment on lines
+970
to
+993
| test('extracts token counts from Vertex AI statistics', async () => { | ||
| ;(client as any).client.models.embedContent = jest.fn().mockResolvedValue(mockEmbedResponseWithStats) | ||
|
|
||
| await client.models.embedContent({ | ||
| model: 'gemini-embedding-001', | ||
| contents: ['Hello', 'World'], | ||
| posthogDistinctId: 'test-id', | ||
| }) | ||
|
|
||
| const [captureArgs] = (mockPostHogClient.capture as jest.Mock).mock.calls | ||
| expect(captureArgs[0].properties['$ai_input_tokens']).toBe(13) // 5 + 8 | ||
| }) | ||
|
|
||
| test('returns 0 tokens when no statistics available', async () => { | ||
| ;(client as any).client.models.embedContent = jest.fn().mockResolvedValue(mockEmbedResponse) | ||
|
|
||
| await client.models.embedContent({ | ||
| model: 'gemini-embedding-001', | ||
| contents: 'Hello', | ||
| posthogDistinctId: 'test-id', | ||
| }) | ||
|
|
||
| const [captureArgs] = (mockPostHogClient.capture as jest.Mock).mock.calls | ||
| expect(captureArgs[0].properties['$ai_input_tokens']).toBe(0) |
Contributor
There was a problem hiding this comment.
These two test cases exercise the same extractEmbeddingTokenCount path with different mock responses and expected values. Per the project's preference, they could be expressed as a single test.each:
test.each([
['with Vertex AI statistics', mockEmbedResponseWithStats, 13],
['without statistics', mockEmbedResponse, 0],
])('token count %s', async (_, mockResponse, expectedTokens) => {
;(client as any).client.models.embedContent = jest.fn().mockResolvedValue(mockResponse)
await client.models.embedContent({
model: 'gemini-embedding-001',
contents: 'Hello',
posthogDistinctId: 'test-id',
})
const [captureArgs] = (mockPostHogClient.capture as jest.Mock).mock.calls
expect(captureArgs[0].properties['$ai_input_tokens']).toBe(expectedTokens)
})Prompt To Fix With AI
This is a comment left during a code review.
Path: packages/ai/tests/gemini.test.ts
Line: 970-993
Comment:
**Prefer parametrised tests for token-count scenarios**
These two test cases exercise the same `extractEmbeddingTokenCount` path with different mock responses and expected values. Per the project's preference, they could be expressed as a single `test.each`:
```ts
test.each([
['with Vertex AI statistics', mockEmbedResponseWithStats, 13],
['without statistics', mockEmbedResponse, 0],
])('token count %s', async (_, mockResponse, expectedTokens) => {
;(client as any).client.models.embedContent = jest.fn().mockResolvedValue(mockResponse)
await client.models.embedContent({
model: 'gemini-embedding-001',
contents: 'Hello',
posthogDistinctId: 'test-id',
})
const [captureArgs] = (mockPostHogClient.capture as jest.Mock).mock.calls
expect(captureArgs[0].properties['$ai_input_tokens']).toBe(expectedTokens)
})
```
How can I resolve this? If you propose a fix, please make it concise.Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
andrewm4894
approved these changes
Apr 10, 2026
Contributor
Contributor
|
Size Change: +1.75 kB (+0.03%) Total Size: 6.59 MB
ℹ️ View Unchanged
|
3 tasks
Contributor
Author
|
This PR adds Gemini Python SDK PR (addresses community request): PostHog/posthog-python#498 |
…ed-content # Conflicts: # packages/ai/src/gemini/index.ts # packages/ai/tests/gemini.test.ts
carlos-marchal-ph
temporarily deployed
to
NPM Release
GitHub Actions
Inactive
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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
Users want to track Gemini embedding calls via the PostHog wrapper. Currently only
generateContentandgenerateContentStreamare wrapped.Changes
embedContent()toWrappedModelsinpackages/ai/src/gemini/index.ts$ai_embeddingevents with provider, model, input, latency, token counts (Vertex AI)WrappedEmbeddingspatternCompanion PR for Python SDK: PostHog/posthog-python
Release info Sub-libraries affected
Libraries affected
Checklist
If releasing new changes
pnpm changesetto generate a changeset file