Comments (5)
penguine-ip
commented on June 24, 2024
1
@AndresPrez Agreed with the embedding + similarity bit. Have you tried using GEval for this with strict=true? I'm sure it will give good results.
from deepeval.
AndresPrez
commented on June 24, 2024
@penguine-ip g-eval is actually pretty nice! thanks for the advise ❤️
from deepeval.
penguine-ip
commented on June 24, 2024
@AndresPrez No problem! I'm actually going to push out more tutorials soon on the documentation page, I feel like the full capabilities of deepeval mostly go undiscovered 😅 Be including Answer Correctness for sure
from deepeval.
gtmtech
commented on June 24, 2024
@penguine-ip - thanks for the explanation on this - I too got a bit fooled just because the docs state that ragas metrics are supported, and AnswerCorrectness is one of ragas metrics - bit of internal translation to do to get there.
from deepeval.
penguine-ip
commented on June 24, 2024
@gtmtech Yes but we eventually deleted most of it except for the flagship ragas metrics since they weren't very good n well maintained
from deepeval.
Related Issues (20)
- Knowledge Retention metric discrepancy HOT 3
- No test cases found error HOT 4
- Is context recall and context precision returns categorical output? HOT 1
- Cant use HuggingFace Model for evaluation HOT 5
- Unable to disable telemetry HOT 2
- Crash with ContextualRelevancyVerdict HOT 3
- 'Did not find openai_api_key' When using azure openai HOT 4
- .generate_raw_response(prompt) gives an attribute error HOT 6
- Corrupted cache can make it impossible to run deepeval
- Remove unconditional, uncontrollable output statements
- deepeval should return non-zero exitCode on failure HOT 1
- Dramatically simpler and more reliable cache
- Synthesizer generates goldens but a dataset loads as test cases
- Synthesizer only takes one document in list of documents for some edge cases
- RagasMetric breaks when used with dataset HOT 1
- Suggestion for Future Improvement: Enable Function Calling for Consistent JSON Output
- No response after processing few prompts.
- ProxySchemeUnknown: Proxy URL had no scheme, should start with http:// or https://
- `check_for_update` should not happen on package load HOT 1
- Error in Faithfulness metric: KeyError: 'claims' in `a_generate_claims` HOT 3
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 deepeval.