feat(vision): add GCP Vision API integration #4231
Conversation
| aden_supported=False, | ||
| aden_provider_name="", | ||
| direct_api_key_supported=True, | ||
| api_key_instructions="""To get a Google Cloud Vision API key: |
There was a problem hiding this comment.
add API key instructions in readme file instead of here
There was a problem hiding this comment.
Thanks for suggestion!, I noticed @RichardTang-Aden deleted the integrations.py and added .py files to each tool, following the same pattern-I created gcp_vision.py file .
Hope, this will resolve ur concerns.
ThankYou.
Trinath052004
force-pushed
the
feat/gcp-vision-tool
branch
from
d963974 to
4310b89
Compare
|
Initially added the Vision integration credential to older integration.py structure. |
Hundao
left a comment
Hundao
left a comment
There was a problem hiding this comment.
Left some comments inline. Can you also share some e2e test output showing a couple tools working? Thanks!
| **LLM_CREDENTIALS, | ||
| **SEARCH_CREDENTIALS, | ||
| **EMAIL_CREDENTIALS, | ||
| **INTEGRATION_CREDENTIALS, |
There was a problem hiding this comment.
INTEGRATION_CREDENTIALS is never imported or defined anywhere. This will crash at runtime.
| """ | ||
|
|
||
| from .base import CredentialError, CredentialSpec | ||
| from .browser import get_aden_auth_url, get_aden_setup_url, open_browser |
There was a problem hiding this comment.
These imports already exist a few lines below, remove the duplicates.
.gitignore
Outdated
| docs/github-issues/* | ||
| core/tests/*dumps/* | ||
| screenshots/* No newline at end of file | ||
| agent_logs/ |
There was a problem hiding this comment.
This is unrelated to the Vision tool, please revert.
There was a problem hiding this comment.
Hey @Trinath052004 please check the lint test they are failing you can check it out here - https://github.com/adenhq/hive/actions/runs/21870639828/job/63208638027?pr=4231
Also please do the changes suggested by @Hundao
Hi @Hundao i have made suggested changes and ran e2e tests, the results are as follows: Test 1: Test2: btw , i apologize for creating quite a number of commits( i jus wanted to make sure everything works perfect!)
Thankyou @prakharsingh-74 for the review and suggestion( i have updated accordingly!) @Hundao , i am open to make further changes if necessary, Thankyou for trusting me by assigning this issue to me :) |
3 participants
Description
Added Google Cloud Vision API integration with 9 detection capabilities including label detection, OCR, face detection, object localization, and more
Type of Change
Related Issues
Closes #3616
Changes Made
vision_toolmodule with 9 Google Cloud Vision API detection functionsintegrations.pyto support GCP Vision API credentialsTesting
Describe the tests you ran to verify your changes:
cd core && pytest tests/)cd core && ruff check .)Checklist
Screenshots (if applicable)
N/A -Backend tool integration