Fixed #996: added comprehensive error handling for GenAI pipeline operations#1035
Open
GauravSRC wants to merge 1 commit intoopenvinotoolkit:masterfrom
Open
Fixed #996: added comprehensive error handling for GenAI pipeline operations#1035GauravSRC wants to merge 1 commit intoopenvinotoolkit:masterfrom
GauravSRC wants to merge 1 commit intoopenvinotoolkit:masterfrom
Conversation
…enAI pipeline operations - Add error checking to all OpenVINO GenAI C API calls - Validate device availability before pipeline creation - Return descriptive errors instead of silent failures - Log available devices at startup for debugging - Add proper error responses in HTTP API This fixes the issue where models would fail to generate output when using unavailable devices (like NPU on systems without NPU hardware).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR addresses issue #996 where the GenAI Ollama integration fails silently when using unavailable devices (like NPU on systems without NPU hardware), resulting in zero token generation and no error messages.
Root Cause
The original implementation lacked error checking on OpenVINO GenAI C API calls. When operations failed, the code continued execution and returned empty results with all metrics showing 0.00 values.
Changes
genai.go:
CreatePipeline()to validate device availability and return errorsGenerateTextWithMetrics()to check all C API status codesIsDeviceAvailable()andGetAvailableDeviceNames()runner.go:
loadModel()with error handling and device availability loggingprocessBatch()to propagate generation errorsImpact
Testing