Comments (5)
flaviabeo
commented on August 29, 2024
1
Fixed by the PR #102!
from fms-guardrails-orchestrator.
gkumbhat
commented on August 29, 2024
Thanks @flaviabeo . This should have been fixed with: #47
from fms-guardrails-orchestrator.
evaline-ju
commented on August 29, 2024
What version of orchestrator is being used here? edit: was able to reproduce on latest (b3231a5)
The results are correct if a sentence chunker is not used, which points to an issue potentially still with the offsets...
from fms-guardrails-orchestrator.
evaline-ju
commented on August 29, 2024
Root cause was that the detectors used are not returning an output per input i.e. each text in contents did not necessarily return a result. Since the orchestrator does not know which "chunk" or text a result corresponds to, the offset is calculated incorrectly. This has to be fixed on the detector server side.
In the meantime it was noticed that with #76 we are doing unnecessary codepoint slicing again to determine text
from fms-guardrails-orchestrator.
evaline-ju
commented on August 29, 2024
With the merge of #102 , there will be a clear error message and 500 return until this is updated for the requested detector(s)
from fms-guardrails-orchestrator.
Related Issues (20)
- Standardize mask validation error
- Generation validation errors surface as 500s on streaming HOT 1
- Mask input validation off by 1
- Mask input validation off by 1
- Implementation of /api/v2/text/detection/generated HOT 1
- Make detector params more flexible to arbitrary parameters
- Update evidences in detector and orchestrator APIs
- Add evidence to context endpoint
- Integrate open telemetry metrics in orchestrator
- Perform client health checks on start-up to further validate configuration
- Add detector_type to configure different detector endpoints
- Make generation and chunker sections of configuration optional HOT 1
- Feature design: Support Chat API HOT 1
- Streaming with whole doc chunker seems to hang HOT 1
- Detector Params are not getting passed through to downstream context detectors
- Multiple detector models appear to interfere with streaming
- Make evidence value optional
- De-duplicate between detect and detect_content
- Add list detectors endpoint
- Add chunking processing for all standalone detection
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fms-guardrails-orchestrator.