<div align="center">
<img src="https://github.com/openlit/.github/blob/main/profile/assets/wide-logo-no-bg.png?raw=true" alt="OpenLIT Logo" width="30%"><h1>
OpenTelemetry Auto-Instrumentation for GenAI & LLM Applications</h1>
**[Documentation](https://docs.openlit.io/) | [Quickstart](#-getting-started) | [Python SDK](https://github.com/openlit/openlit/tree/main/sdk/python)**
[](https://github.com/openlit/openlit)
[](https://github.com/openlit/openlit/blob/main/LICENSE)
[](https://pepy.tech/project/openlit)
[](https://github.com/openlit/openlit/pulse)
[](https://github.com/openlit/openlit/graphs/contributors)
[](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ)
[](https://discord.gg/rjvTm6zd)
[](https://twitter.com/openlit_io)
</div>
OpenLIT Python SDK is an **OpenTelemetry-native** Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects. Designed with simplicity and efficiency, OpenLIT offers the ability to embed observability into your GenAI-driven projects effortlessly using just **a single line of code**.
Whether you're directly using LLM Libraries like OpenAI, Anthropic or building complex RAG Agents using Langchain, OpenLIT seamlessly integrates observability into your applications, ensuring enhanced performance and reliability across diverse scenarios.
This project adheres to the [Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai) proposed by the OpenTelemetry community. You can check out the current definitions [here](src/openlit/semcov/__init__.py).
## Auto Instrumentation Capabilities
| LLMs | Vector DBs | Frameworks |
|-----------------------------------------------------------------|----------------------------------------------|----------------------------------------------|
| [✅ OpenAI](https://docs.openlit.io/latest/integrations/openai) | [✅ ChromaDB](https://docs.openlit.io/latest/integrations/chromadb) | [✅ Langchain](https://docs.openlit.io/latest/integrations/langchain) |
| [✅ Ollama](https://docs.openlit.io/latest/integrations/ollama) | [✅ Pinecone](https://docs.openlit.io/latest/integrations/pinecone) | [✅ LiteLLM](https://docs.openlit.io/latest/integrations/litellm) |
| [✅ Anthropic](https://docs.openlit.io/latest/integrations/anthropic) | [✅ Qdrant](https://docs.openlit.io/latest/integrations/qdrant) | [✅ LlamaIndex](https://docs.openlit.io/latest/integrations/llama-index) |
| [✅ GPT4All](https://docs.openlit.io/latest/integrations/gpt4all) | [✅ Milvus](https://docs.openlit.io/latest/integrations/milvus) | [✅ Haystack](https://docs.openlit.io/latest/integrations/haystack) |
| [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere) | | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain) |
| [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral) | |
| [✅ Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai) | |
| [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) | |
| [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock) | |
| [✅ Vertex AI](https://docs.openlit.io/latest/integrations/vertexai) | |
| [✅ Groq](https://docs.openlit.io/latest/integrations/groq) |
## Supported Destinations
- [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)
- [✅ Prometheus + Tempo](https://docs.openlit.io/latest/connections/prometheus-tempo)
- [✅ Prometheus + Jaeger](https://docs.openlit.io/latest/connections/prometheus-jaeger)
- [✅ Grafana Cloud](https://docs.openlit.io/latest/connections/grafanacloud)
- [✅ New Relic](https://docs.openlit.io/latest/connections/new-relic)
- [✅ Elastic](https://docs.openlit.io/latest/connections/elastic)
- [✅ DataDog](https://docs.openlit.io/latest/connections/datadog)
- [✅ SigNoz](https://docs.openlit.io/latest/connections/signoz)
- [✅ Dynatrace](https://docs.openlit.io/latest/connections/dynatrace)
- [✅ OpenObserve](https://docs.openlit.io/latest/connections/openobserve)
- [✅ Highlight.io](https://docs.openlit.io/latest/connections/highlight)
## 💿 Installation
```bash
pip install openlit
```
## 🚀 Getting Started
### Step 1: Install OpenLIT
Open your command line or terminal and run:
```bash
pip install openlit
```
### Step 2: Initialize OpenLIT in your Application
Integrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **two lines of code**:
```python
import openlit
openlit.init()
```
To forward telemetry data to an HTTP OTLP endpoint, such as the OpenTelemetry Collector, set the `otlp_endpoint` parameter with the desired endpoint. Alternatively, you can configure the endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` environment variable as recommended in the OpenTelemetry documentation.
> 💡 Info: If you dont provide `otlp_endpoint` function argument or set the `OTEL_EXPORTER_OTLP_ENDPOINT` environment variable, OpenLIT directs the trace directly to your console, which can be useful during development.
To send telemetry to OpenTelemetry backends requiring authentication, set the `otlp_headers` parameter with its desired value. Alternatively, you can configure the endpoint by setting the `OTEL_EXPORTER_OTLP_HEADERS` environment variable as recommended in the OpenTelemetry documentation.
#### Example
---
<details>
<summary>Initialize using Function Arguments</summary>
---
Add the following two lines to your application code:
```python
import openlit
openlit.init(
otlp_endpoint="YOUR_OTEL_ENDPOINT",
otlp_headers ="YOUR_OTEL_ENDPOINT_AUTH"
)
```
</details>
---
<details>
<summary>Initialize using Environment Variables</summary>
---
Add the following two lines to your application code:
```python
import openlit
openlit.init()
```
Then, configure the your OTLP endpoint using environment variable:
```env
export OTEL_EXPORTER_OTLP_ENDPOINT = "YOUR_OTEL_ENDPOINT"
export OTEL_EXPORTER_OTLP_HEADERS = "YOUR_OTEL_ENDPOINT_AUTH"
```
</details>
---
### Step 3: Visualize and Optimize!
With the LLM Observability data now being collected and sent to OpenLIT, the next step is to visualize and analyze this data to get insights into your LLM application’s performance, behavior, and identify areas of improvement.
To begin exploring your LLM Application's performance data within the OpenLIT UI, please see the [Quickstart Guide](https://docs.openlit.io/latest/quickstart).
If you want to integrate and send metrics and traces to your existing observability tools, refer to our [Connections Guide](https://docs.openlit.io/latest/connections/intro) for detailed instructions.
### Configuration
Below is a detailed overview of the configuration options available, allowing you to adjust OpenLIT's behavior and functionality to align with your specific observability needs:
| Argument | Description | Default Value | Required |
|-------------------------|-----------------------------------------------------------------------------------------------|----------------|----------|
| `environment` | The deployment environment of the application. | `"default"` | Yes |
| `application_name` | Identifies the name of your application. | `"default"` | Yes |
| `tracer` | An instance of OpenTelemetry Tracer for tracing operations. | `None` | No |
| `meter` | An OpenTelemetry Metrics instance for capturing metrics. | `None` | No |
| `otlp_endpoint` | Specifies the OTLP endpoint for transmitting telemetry data. | `None` | No |
| `otlp_headers` | Defines headers for the OTLP exporter, useful for backends requiring authentication. | `None` | No |
| `disable_batch` | A flag to disable batch span processing, favoring immediate dispatch. | `False` | No |
| `trace_content` | Enables tracing of content for deeper insights. | `True` | No |
| `disabled_instrumentors`| List of instrumentors to disable. | `None` | No |
| `disable_metrics` | If set, disables the collection of metrics. | `False` | No |
| `pricing_json` | URL or file path of the pricing JSON file. | `https://github.com/openlit/openlit/blob/main/assets/pricing.json` | No |
## 🌱 Contributing
Whether it's big or small, we love contributions 💚. Check out our [Contribution guide](../../CONTRIBUTING.md) to get started
Unsure where to start? Here are a few ways to get involved:
- Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/rjvTm6zd) community to discuss ideas, share feedback, and connect with both our team and the wider OpenLIT community.
Your input helps us grow and improve, and we're here to support you every step of the way.
## 💚 Community & Support
Connect with the OpenLIT community and maintainers for support, discussions, and updates:
- 🌟 If you like it, Leave a star on our [GitHub](https://github.com/openlit/openlit/)
- 🌍 Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/rjvTm6zd) community for live interactions and questions.
- 🐞 Report bugs on our [GitHub Issues](https://github.com/openlit/openlit/issues) to help us improve OpenLIT.
- 𝕏 Follow us on [X](https://x.com/openlit_io) for the latest updates and news.
Raw data
{
"_id": null,
"home_page": "https://github.com/openlit/openlit/tree/main/openlit/python",
"name": "openlit",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0.0,>=3.7.1",
"maintainer_email": null,
"keywords": "OpenTelemetry, otel, otlp, llm, tracing, openai, anthropic, claude, cohere, llm monitoring, observability, monitoring, gpt, Generative AI, chatGPT",
"author": "OpenLIT",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/82/ea/8adb4aae310c1e23d2e51022b6654c0e332701f83c696527f3216a7bfd86/openlit-1.13.0.tar.gz",
"platform": null,
"description": "<div align=\"center\">\n<img src=\"https://github.com/openlit/.github/blob/main/profile/assets/wide-logo-no-bg.png?raw=true\" alt=\"OpenLIT Logo\" width=\"30%\"><h1>\nOpenTelemetry Auto-Instrumentation for GenAI & LLM Applications</h1>\n\n**[Documentation](https://docs.openlit.io/) | [Quickstart](#-getting-started) | [Python SDK](https://github.com/openlit/openlit/tree/main/sdk/python)**\n\n[](https://github.com/openlit/openlit)\n[](https://github.com/openlit/openlit/blob/main/LICENSE)\n[](https://pepy.tech/project/openlit)\n[](https://github.com/openlit/openlit/pulse)\n[](https://github.com/openlit/openlit/graphs/contributors)\n\n[](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ)\n[](https://discord.gg/rjvTm6zd)\n[](https://twitter.com/openlit_io)\n\n\n\n\n</div>\n\nOpenLIT Python SDK is an **OpenTelemetry-native** Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects. Designed with simplicity and efficiency, OpenLIT offers the ability to embed observability into your GenAI-driven projects effortlessly using just **a single line of code**.\n\nWhether you're directly using LLM Libraries like OpenAI, Anthropic or building complex RAG Agents using Langchain, OpenLIT seamlessly integrates observability into your applications, ensuring enhanced performance and reliability across diverse scenarios.\n\nThis project adheres to the [Semantic Conventions](https://github.com/open-telemetry/semantic-conventions/tree/main/docs/gen-ai) proposed by the OpenTelemetry community. You can check out the current definitions [here](src/openlit/semcov/__init__.py).\n\n## Auto Instrumentation Capabilities\n\n| LLMs | Vector DBs | Frameworks |\n|-----------------------------------------------------------------|----------------------------------------------|----------------------------------------------|\n| [\u2705 OpenAI](https://docs.openlit.io/latest/integrations/openai) | [\u2705 ChromaDB](https://docs.openlit.io/latest/integrations/chromadb) | [\u2705 Langchain](https://docs.openlit.io/latest/integrations/langchain) |\n| [\u2705 Ollama](https://docs.openlit.io/latest/integrations/ollama) | [\u2705 Pinecone](https://docs.openlit.io/latest/integrations/pinecone) | [\u2705 LiteLLM](https://docs.openlit.io/latest/integrations/litellm) |\n| [\u2705 Anthropic](https://docs.openlit.io/latest/integrations/anthropic) | [\u2705 Qdrant](https://docs.openlit.io/latest/integrations/qdrant) | [\u2705 LlamaIndex](https://docs.openlit.io/latest/integrations/llama-index) |\n| [\u2705 GPT4All](https://docs.openlit.io/latest/integrations/gpt4all) | [\u2705 Milvus](https://docs.openlit.io/latest/integrations/milvus) | [\u2705 Haystack](https://docs.openlit.io/latest/integrations/haystack) |\n| [\u2705 Cohere](https://docs.openlit.io/latest/integrations/cohere) | | [\u2705 EmbedChain](https://docs.openlit.io/latest/integrations/embedchain) | \n| [\u2705 Mistral](https://docs.openlit.io/latest/integrations/mistral) | | \n| [\u2705 Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai) | | \n| [\u2705 HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) | | \n| [\u2705 Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock) | | \n| [\u2705 Vertex AI](https://docs.openlit.io/latest/integrations/vertexai) | | \n| [\u2705 Groq](https://docs.openlit.io/latest/integrations/groq) | \n\n## Supported Destinations\n- [\u2705 OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)\n- [\u2705 Prometheus + Tempo](https://docs.openlit.io/latest/connections/prometheus-tempo)\n- [\u2705 Prometheus + Jaeger](https://docs.openlit.io/latest/connections/prometheus-jaeger)\n- [\u2705 Grafana Cloud](https://docs.openlit.io/latest/connections/grafanacloud)\n- [\u2705 New Relic](https://docs.openlit.io/latest/connections/new-relic)\n- [\u2705 Elastic](https://docs.openlit.io/latest/connections/elastic)\n- [\u2705 DataDog](https://docs.openlit.io/latest/connections/datadog)\n- [\u2705 SigNoz](https://docs.openlit.io/latest/connections/signoz)\n- [\u2705 Dynatrace](https://docs.openlit.io/latest/connections/dynatrace)\n- [\u2705 OpenObserve](https://docs.openlit.io/latest/connections/openobserve)\n- [\u2705 Highlight.io](https://docs.openlit.io/latest/connections/highlight)\n\n## \ud83d\udcbf Installation\n\n```bash\npip install openlit\n```\n\n## \ud83d\ude80 Getting Started\n\n### Step 1: Install OpenLIT\n\nOpen your command line or terminal and run:\n\n```bash\npip install openlit\n```\n\n### Step 2: Initialize OpenLIT in your Application\nIntegrating the OpenLIT into LLM applications is straightforward. Start monitoring for your LLM Application with just **two lines of code**: \n\n```python\nimport openlit\n\nopenlit.init()\n```\n\nTo forward telemetry data to an HTTP OTLP endpoint, such as the OpenTelemetry Collector, set the `otlp_endpoint` parameter with the desired endpoint. Alternatively, you can configure the endpoint by setting the `OTEL_EXPORTER_OTLP_ENDPOINT` environment variable as recommended in the OpenTelemetry documentation.\n\n> \ud83d\udca1 Info: If you dont provide `otlp_endpoint` function argument or set the `OTEL_EXPORTER_OTLP_ENDPOINT` environment variable, OpenLIT directs the trace directly to your console, which can be useful during development.\n\nTo send telemetry to OpenTelemetry backends requiring authentication, set the `otlp_headers` parameter with its desired value. Alternatively, you can configure the endpoint by setting the `OTEL_EXPORTER_OTLP_HEADERS` environment variable as recommended in the OpenTelemetry documentation.\n\n#### Example\n\n---\n\n<details>\n <summary>Initialize using Function Arguments</summary>\n \n ---\n\n Add the following two lines to your application code:\n \n ```python\n import openlit\n \n openlit.init(\n otlp_endpoint=\"YOUR_OTEL_ENDPOINT\", \n otlp_headers =\"YOUR_OTEL_ENDPOINT_AUTH\"\n )\n ```\n\n</details>\n\n---\n\n<details>\n\n <summary>Initialize using Environment Variables</summary>\n\n ---\n\n Add the following two lines to your application code:\n\n ```python\n import openlit\n\n openlit.init()\n ```\n \n Then, configure the your OTLP endpoint using environment variable:\n\n ```env\n export OTEL_EXPORTER_OTLP_ENDPOINT = \"YOUR_OTEL_ENDPOINT\"\n export OTEL_EXPORTER_OTLP_HEADERS = \"YOUR_OTEL_ENDPOINT_AUTH\"\n ```\n</details>\n\n---\n\n### Step 3: Visualize and Optimize!\nWith the LLM Observability data now being collected and sent to OpenLIT, the next step is to visualize and analyze this data to get insights into your LLM application\u2019s performance, behavior, and identify areas of improvement.\n\nTo begin exploring your LLM Application's performance data within the OpenLIT UI, please see the [Quickstart Guide](https://docs.openlit.io/latest/quickstart).\n\nIf you want to integrate and send metrics and traces to your existing observability tools, refer to our [Connections Guide](https://docs.openlit.io/latest/connections/intro) for detailed instructions.\n\n\n\n\n### Configuration\n\nBelow is a detailed overview of the configuration options available, allowing you to adjust OpenLIT's behavior and functionality to align with your specific observability needs:\n\n| Argument | Description | Default Value | Required |\n|-------------------------|-----------------------------------------------------------------------------------------------|----------------|----------|\n| `environment` | The deployment environment of the application. | `\"default\"` | Yes |\n| `application_name` | Identifies the name of your application. | `\"default\"` | Yes |\n| `tracer` | An instance of OpenTelemetry Tracer for tracing operations. | `None` | No |\n| `meter` | An OpenTelemetry Metrics instance for capturing metrics. | `None` | No |\n| `otlp_endpoint` | Specifies the OTLP endpoint for transmitting telemetry data. | `None` | No |\n| `otlp_headers` | Defines headers for the OTLP exporter, useful for backends requiring authentication. | `None` | No |\n| `disable_batch` | A flag to disable batch span processing, favoring immediate dispatch. | `False` | No |\n| `trace_content` | Enables tracing of content for deeper insights. | `True` | No |\n| `disabled_instrumentors`| List of instrumentors to disable. | `None` | No |\n| `disable_metrics` | If set, disables the collection of metrics. | `False` | No |\n| `pricing_json` | URL or file path of the pricing JSON file. | `https://github.com/openlit/openlit/blob/main/assets/pricing.json` | No |\n\n## \ud83c\udf31 Contributing\n\nWhether it's big or small, we love contributions \ud83d\udc9a. Check out our [Contribution guide](../../CONTRIBUTING.md) to get started\n\nUnsure where to start? Here are a few ways to get involved:\n\n- Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/rjvTm6zd) community to discuss ideas, share feedback, and connect with both our team and the wider OpenLIT community.\n\nYour input helps us grow and improve, and we're here to support you every step of the way.\n\n## \ud83d\udc9a Community & Support\n\nConnect with the OpenLIT community and maintainers for support, discussions, and updates:\n\n- \ud83c\udf1f If you like it, Leave a star on our [GitHub](https://github.com/openlit/openlit/)\n- \ud83c\udf0d Join our [Slack](https://join.slack.com/t/openlit/shared_invite/zt-2etnfttwg-TjP_7BZXfYg84oAukY8QRQ) or [Discord](https://discord.gg/rjvTm6zd) community for live interactions and questions.\n- \ud83d\udc1e Report bugs on our [GitHub Issues](https://github.com/openlit/openlit/issues) to help us improve OpenLIT.\n- \ud835\udd4f Follow us on [X](https://x.com/openlit_io) for the latest updates and news.\n\n",
"bugtrack_url": null,
"license": null,
"summary": "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects",
"version": "1.13.0",
"project_urls": {
"Homepage": "https://github.com/openlit/openlit/tree/main/openlit/python",
"Repository": "https://github.com/openlit/openlit/tree/main/openlit/python"
},
"split_keywords": [
"opentelemetry",
" otel",
" otlp",
" llm",
" tracing",
" openai",
" anthropic",
" claude",
" cohere",
" llm monitoring",
" observability",
" monitoring",
" gpt",
" generative ai",
" chatgpt"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "7a0c1cb453c4b234ca1f9f355aaca185fc9b6f6aca69a50631c2d5a76a8c13ea",
"md5": "3e9557d5de8d8c95253bdba8827280f5",
"sha256": "8a27008b9c2fe59d62a4deac79e263d9edfbcb9dc7f61d6b70ebcd9a9b42b7cb"
},
"downloads": -1,
"filename": "openlit-1.13.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "3e9557d5de8d8c95253bdba8827280f5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0.0,>=3.7.1",
"size": 113695,
"upload_time": "2024-06-12T04:52:21",
"upload_time_iso_8601": "2024-06-12T04:52:21.660092Z",
"url": "https://files.pythonhosted.org/packages/7a/0c/1cb453c4b234ca1f9f355aaca185fc9b6f6aca69a50631c2d5a76a8c13ea/openlit-1.13.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "82ea8adb4aae310c1e23d2e51022b6654c0e332701f83c696527f3216a7bfd86",
"md5": "783b503ff53305b3d00e9a0b2ca4495a",
"sha256": "18770fae26945f3bae8f7f0186484c5134d686c22694b8bceea9ffa62861e8a9"
},
"downloads": -1,
"filename": "openlit-1.13.0.tar.gz",
"has_sig": false,
"md5_digest": "783b503ff53305b3d00e9a0b2ca4495a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0.0,>=3.7.1",
"size": 63707,
"upload_time": "2024-06-12T04:52:23",
"upload_time_iso_8601": "2024-06-12T04:52:23.391723Z",
"url": "https://files.pythonhosted.org/packages/82/ea/8adb4aae310c1e23d2e51022b6654c0e332701f83c696527f3216a7bfd86/openlit-1.13.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-12 04:52:23",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "openlit",
"github_project": "openlit",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "openlit"
}
JSON
