Modify VisionAgent to fetch and send image bytes #3045
Conversation
Updated image handling in VisionAgent to use byte array. System.Net.Http.HttpRequestException: 'Response status code does not indicate success: 403 (Forbidden).'
There was a problem hiding this comment.
Pull request overview
This PR modifies the VisionAgent sample to fetch image bytes using HttpClient instead of passing a URI directly to the API. This change resolves a 403 Forbidden error that occurs when some image hosting services (like Wikipedia) block direct URI access from automated requests.
- Changed image handling from URI-based (
UriContent) to byte array-based (DataContent) - Added HttpClient with User-Agent header to download image bytes before sending to the agent
- Maintains the same functional behavior while working around external service restrictions
|
|
||
|
|
||
| using HttpClient httpClient = new(); | ||
| httpClient.DefaultRequestHeaders.UserAgent.ParseAdd("Mozilla/5.0 (Windows NT 10.0; Win64; x64)"); |
There was a problem hiding this comment.
The User-Agent header is added to work around the 403 Forbidden error, but there's no comment explaining why this is necessary. According to the coding guidelines, sample code should be well-documented with comments explaining the purpose of each step. Consider adding a comment above line 22 explaining that some image hosting services (like Wikipedia) require a User-Agent header to prevent automated scraping.
| name: "VisionAgent", | ||
| instructions: "You are a helpful agent that can analyze images"); | ||
|
|
||
|
|
There was a problem hiding this comment.
There's an extra blank line here that should be removed to maintain consistency with the coding style in other samples.
1 participant
Updated image handling in VisionAgent to use byte array.
System.Net.Http.HttpRequestException: 'Response status code does not indicate success: 403 (Forbidden).'
Motivation and Context
Description
Contribution Checklist