opik
opik copied to clipboard
Open-source end-to-end LLM Development Platform
Open-source end-to-end LLM Development Platform
Confidently evaluate, test and monitor LLM applications.
Website • Slack community • Twitter • Documentation
🚀 What is Opik?
Opik is an open-source platform for evaluating, testing and monitoring LLM applications. Built by Comet.
You can use Opik for:
-
Development:
- Tracing: Track all LLM calls and traces during development and production (Quickstart, Integrations
- Annotations: Annotate your LLM calls by logging feedback scores using the Python SDK or the UI.
-
Evaluation: Automate the evaluation process of your LLM application:
-
Datasets and Experiments: Store test cases and run experiments (Datasets, Evaluate your LLM Application)
-
LLM as a judge metrics: Use Opik's LLM as a judge metric for complex issues like hallucination detection, moderation and RAG evaluation (Answer Relevance, Context Precision
-
CI/CD integration: Run evaluations as part of your CI/CD pipeline using our PyTest integration
-
-
Production Monitoring: Monitor your LLM application in production and easily close the feedback loop by adding error traces to your evaluation datasets.
[!TIP]
If you are looking for features that Opik doesn't have today, please raise a new Github discussion topic 🚀
🛠️ Installation
Opik is available as a fully open source local installation or using Comet.com as a hosted solution. The easiest way to get started with Opik is by creating a free Comet account at comet.com.
If you'd like to self-host Opik, you can do so by cloning the repository and starting the platform using Docker Compose:
# Clone the Opik repository
git clone https://github.com/comet-ml/opik.git
# Navigate to the opik/deployment/docker-compose directory
cd opik/deployment/docker-compose
# Start the Opik platform
docker compose up --detach
# You can now visit http://localhost:5173 on your browser!
For more information about the different deployment options, please see our deployment guides:
Installation methods | Docs link |
---|---|
Local instance | |
Kubernetes |
🏁 Get Started
To get started, you will need to first install the Python SDK:
pip install opik
Once the SDK is installed, you can configure it by running the opik configure
command:
opik configure
This will allow you to configure Opik locally by setting the correct local server address or if you're using the Cloud platform by setting the API Key
[!TIP]
You can also call theopik.configure(use_local=True)
method from your Python code to configure the SDK to run on the local installation.
You are now ready to start logging traces using the Python SDK.
📝 Logging Traces
The easiest way to get started is to use one of our integrations. Opik supports:
Integration | Description | Documentation | Try in Colab |
---|---|---|---|
OpenAI | Log traces for all OpenAI LLM calls | Documentation | |
LiteLLM | Call any LLM model using the OpenAI format | Documentation | |
LangChain | Log traces for all LangChain LLM calls | Documentation | |
Bedrock | Log traces for all Bedrock LLM calls | Documentation | |
Anthropic | Log traces for all Anthropic LLM calls | Documentation | |
Gemini | Log traces for all Gemini LLM calls | Documentation | |
Groq | Log traces for all Groq LLM calls | Documentation | |
LangGraph | Log traces for all LangGraph executions | Documentation | |
LlamaIndex | Log traces for all LlamaIndex LLM calls | Documentation | |
Ollama | Log traces for all Ollama LLM calls | Documentation | |
Predibase | Fine-tune and serve open-source Large Language Models | Documentation | |
Ragas | Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines | Documentation | |
watsonx | Log traces for all watsonx LLM calls | Documentation |
[!TIP]
If the framework you are using is not listed above, feel free to open an issue or submit a PR with the integration.
If you are not using any of the frameworks above, you can also use the track
function decorator to log traces:
import opik
opik.configure(use_local=True) # Run locally
@opik.track
def my_llm_function(user_question: str) -> str:
# Your LLM code here
return "Hello"
[!TIP]
The track decorator can be used in conjunction with any of our integrations and can also be used to track nested function calls.
🧑⚖️ LLM as a Judge metrics
The Python Opik SDK includes a number of LLM as a judge metrics to help you evaluate your LLM application. Learn more about it in the metrics documentation.
To use them, simply import the relevant metric and use the score
function:
from opik.evaluation.metrics import Hallucination
metric = Hallucination()
score = metric.score(
input="What is the capital of France?",
output="Paris",
context=["France is a country in Europe."]
)
print(score)
Opik also includes a number of pre-built heuristic metrics as well as the ability to create your own. Learn more about it in the metrics documentation.
🔍 Evaluating your LLM Application
Opik allows you to evaluate your LLM application during development through Datasets and Experiments.
You can also run evaluations as part of your CI/CD pipeline using our PyTest integration.
🤝 Contributing
There are many ways to contribute to Opik:
- Submit bug reports and feature requests
- Review the documentation and submit Pull Requests to improve it
- Speaking or writing about Opik and letting us know
- Upvoting popular feature requests to show your support
To learn more about how to contribute to Opik, please see our contributing guidelines.