Comments (5)
@lmpratti You're probably using the DeepEvalBaseLLM wrapper in the ragas metric. Unforuntately the ragas metric only accept langhcain chat models, you can read the docs here: https://docs.confident-ai.com/docs/metrics-ragas#example
from deepeval.
Hey @haarisedhi102 where are you finding this?
self.llm.set_run_config(run_config)
Also what version of deepeval are you on?
from deepeval.
@penguine-ip This happens on the latest version of deepeval too (0.21.62
). I suspect it's due to the dependency on ragas
library.
It fails even after adding the below set_run_config
to the llm.
def set_run_config(self, run_config: RunConfig = RunConfig()):
self.run_config = run_config
from deepeval.
@penguine-ip Thanks a ton! Is there a plan to support DeepEvalBaseLLM
wrapped models for ragas metric?
from deepeval.
@lmpratti Unfortunately no because ragas does not have their own ecosystem to support custom models, so out of our control. But we have our own similar implementation of the ragas metrics for this reason
from deepeval.
Related Issues (20)
- Typo in bias metric (too many values to unpack (expected 2)) HOT 3
- AttributeError: 'str' object has no attribute 'content' HOT 1
- deepeval v0.21.71 - v 0.21.73 MMLU prediction results are wrong and the task scores and overall score are always 0 for Mistral7B and Gemma2B models HOT 5
- data.generate_goldens throw TypeError: Synthesizer.generate_goldens() got an unexpected keyword argument 'enable_breadth_evolve' HOT 2
- Suggestion to modify the "valid_gpt_models" list from gpt_model.py
- Why actual_output is required for Context Relevancy? HOT 1
- ValueError: Evaluation LLM outputted an invalid JSON. Please use a better evaluation model.
- Add jsonl file support in dataset HOT 2
- Recursion Error While Verbose_mode is set to True
- BiasMetric fails to return verdicts in release >=0.21.73 HOT 1
- SummarizationMetric changing score and reasoning methodology at random HOT 1
- Tool Correctness documentation page shows using ContextualRelevancyMetric instead of ToolCorrectnessMetric HOT 1
- Parameters mentioned in Conversation Relevancy Doc page is of Faithfulness HOT 3
- Example Colab notebook is failing. No module named 'deepeval.metrics.conversation_relevancy HOT 1
- Custom LLM Example do not Work HOT 1
- Incorrect pydantic schemas cause ValidationErrors when using a custom LLM for evaluation
- error HOT 1
- Error on dataset.pull: TypeError: Api.send_request() got an unexpected keyword argument 'params' HOT 1
- Synthesizer - generate from scratch returns only one golden HOT 1
- Deepeval does not work on AWS Lambda HOT 1
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.