Project Links

Meta

Author: OpenLIT

Requires Python: >=3.9.0,<4.0.0

Classifiers

License

OSI Approved :: Apache Software License

Programming Language

Python :: 3
Python :: 3.9
Python :: 3.10
Python :: 3.11
Python :: 3.12
Python :: 3.13
Python :: 3.14

OpenTelemetry-native

AI Observability, Evaluation and Guardrails Framework

Documentation | Quickstart | Roadmap | Feature Request | Report a Bug

OpenLIT SDK is a monitoring framework built on top of OpenTelemetry that gives your complete Observability for your AI stack, from LLMs to vector databases and GPUs, with just one line of code with tracing and metrics. It also allows you to send the generated traces and metrics to your existing monitoring tools like Grafana, New Relic, and more.

This project proudly follows and maintains the Semantic Conventions with the OpenTelemetry community, consistently updating to align with the latest standards in Observability.

⚡ Features

🔎 Auto Instrumentation: Works with 50+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
🔭 OpenTelemetry-Native Observability SDKs: Vendor-neutral SDKs that can send traces and metrics to your existing observability tool like Prometheus and Jaeger.
💲 Cost Tracking for Custom and Fine-Tuned Models: Pass custom pricing files for accurate budgeting of custom and fine-tuned models.
🚀 Support for OpenLIT Features: Includes support for prompt management and secrets management features available in OpenLIT.

Auto Instrumentation Capabilities

LLMs	Vector DBs	Frameworks	GPUs
✅ OpenAI	✅ ChromaDB	✅ Langchain	✅ NVIDIA
✅ Ollama	✅ Pinecone	✅ LiteLLM	✅ AMD
✅ Anthropic	✅ Qdrant	✅ LlamaIndex
✅ GPT4All	✅ Milvus	✅ Haystack
✅ Cohere	✅ AstraDB	✅ EmbedChain
✅ Mistral		✅ Guardrails
✅ Azure OpenAI		✅ CrewAI
✅ Azure AI Inference		✅ DSPy
✅ GitHub AI Models		✅ AG2
✅ HuggingFace Transformers		✅ Dynamiq
✅ Amazon Bedrock		✅ Phidata
✅ AI21		✅ mem0
✅ Vertex AI		✅ MultiOn
✅ Groq		✅ Julep AI
✅ ElevenLabs		✅ ControlFlow
✅ vLLM		✅ Crawl4AI
✅ OLA Krutrim		✅ FireCrawl
✅ Google AI Studio		✅ Letta
✅ NVIDIA NIM		✅ SwarmZero
✅ Titan ML
✅ Reka AI
✅ xAI
✅ Prem AI
✅ Assembly AI
✅ Together
✅ DeepSeek
✅ DigitalOcean (pydo)
✅ DigitalOcean Gradient

Supported Destinations

💿 Installation

pip install openlit

🚀 Getting Started with LLM Observability

Step 1: Install OpenLIT SDK

Open your command line or terminal and run:

pip install openlit

Step 2: Initialize OpenLIT in your Application

Integrate OpenLIT into your AI applications by adding the following lines to your code.

import openlit

openlit.init()

Configure the telemetry data destination as follows:

Purpose	Parameter/Environment Variable	For Sending to OpenLIT
Send data to an HTTP OTLP endpoint	`otlp_endpoint` or `OTEL_EXPORTER_OTLP_ENDPOINT`	`"http://127.0.0.1:4318"`
Authenticate telemetry backends	`otlp_headers` or `OTEL_EXPORTER_OTLP_HEADERS`	Not required by default

💡 Info: If the otlp_endpoint or OTEL_EXPORTER_OTLP_ENDPOINT is not provided, the OpenLIT SDK will output traces directly to your console, which is recommended during the development phase.

Example

Initialize using Function Arguments

Add the following two lines to your application code:

import openlit

openlit.init(
  otlp_endpoint="YOUR_OTEL_ENDPOINT", 
  otlp_headers ="YOUR_OTEL_ENDPOINT_AUTH"
)

Initialize using Environment Variables

Add the following two lines to your application code:

import openlit

openlit.init()

Then, configure the your OTLP endpoint using environment variable:

export OTEL_EXPORTER_OTLP_ENDPOINT = "YOUR_OTEL_ENDPOINT"
export OTEL_EXPORTER_OTLP_HEADERS = "YOUR_OTEL_ENDPOINT_AUTH"

Step 3: Visualize and Optimize!

Now that your LLM observability data is being collected and sent to configured OpenTelemetry destination, the next step is to visualize and analyze this data. This will help you understand your LLM application's performance and behavior and identify where it can be improved.

If you want to use OpenLIT's Observability Dashboard to monitor LLM usage—like cost, tokens, and user interactions—please check out our Quickstart Guide.

If you're sending metrics and traces to other observability tools, take a look at our Connections Guide to start using a pre-built dashboard we have created for these tools.

Configuration

Observability - `openlit.init()`

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
`capture_message_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
`collect_gpu_stats`	Flag to enable or disable GPU metrics collection.	`False`	No
`custom_metrics_attributes`	Custom key-value attributes applied to every metric recording. Useful for grouping metrics by custom tags (e.g., client ID, team, project).	`None`	No

OpenLIT Prompt Hub - `openlit.get_prompt()`

Below are the parameters for use with the SDK for OpenLIT Prompt Hub for prompt management:

Parameter	Description
`url`	Sets the OpenLIT URL. Defaults to the `OPENLIT_URL` environment variable.
`api_key`	Sets the OpenLIT API Key. Can also be provided via the `OPENLIT_API_KEY` environment variable.
`name`	Sets the name to fetch a unique prompt. Use this or `prompt_id`.
`prompt_id`	Sets the ID to fetch a unique prompt. Use this or `name`. Optional
`version`	Set to `True` to get the prompt with variable substitution.. Optional
`shouldCompile`	Boolean value that compiles the prompt using the provided variables. Optional
`variables`	Sets the variables for prompt compilation. Optional
`meta_properties`	Sets the meta-properties for storing in the prompt's access history metadata. Optional

OpenLIT Vault - `openlit.get_secrets()`

Below are the parameters for use with the SDK for OpenLIT Vault for secret management:

Parameter	Description
`url`	Sets the Openlit URL. Defaults to the `OPENLIT_URL` environment variable.
`api_key`	Sets the OpenLIT API Key. Can also be provided via the `OPENLIT_API_KEY` environment variable.
`key`	Sets the key to fetch a specific secret. Optional
`should_set_env`	Boolean value that sets all the secrets as environment variables for the application. Optional
`tags`	Sets the tags for fetching only the secrets that have the mentioned tags assigned. Optional

OpenLIT Rule Engine - `openlit.evaluate_rule()`

Evaluate trace attributes against the OpenLIT Rule Engine to retrieve matching rules and associated entities (contexts, prompts, evaluation configurations).

Parameter	Description
`url`	Sets the OpenLIT URL. Defaults to the `OPENLIT_URL` environment variable.
`api_key`	Sets the OpenLIT API Key. Can also be provided via the `OPENLIT_API_KEY` environment variable.
`entity_type`	Type of entity to match: `"context"`, `"prompt"`, or `"evaluation"`.
`fields`	Dictionary of trace attributes to evaluate against rules. e.g. `{"gen_ai.system": "openai", "gen_ai.request.model": "gpt-4"}`
`include_entity_data`	If `True`, include full entity data in the response. Default: `False`. Optional
`entity_inputs`	Optional dictionary of inputs for entity resolution (e.g. prompt variables, version).

Example

import openlit

# Evaluate rules to get matching contexts
result = openlit.evaluate_rule(
    entity_type="context",
    fields={
        "gen_ai.system": "openai",
        "gen_ai.request.model": "gpt-4",
        "service.name": "my-app",
    },
    include_entity_data=True,
)

if result:
    print("Matching rules:", result["matchingRuleIds"])
    print("Entities:", result["entities"])
    # Use with evaluations:
    # contexts = result.get("entity_data", {})

🛣️ Roadmap

We are dedicated to continuously improving OpenLIT SDKs. Here's a look at what's been accomplished and what's on the horizon:

Feature	Status
OpenTelmetry auto-instrumentation for LLM Providers like OpenAI, Anthropic	✅ Completed
OpenTelmetry auto-instrumentation for Vector databases like Pinecone, Chroma	✅ Completed
OpenTelmetry auto-instrumentation for LLM Frameworks like LangChain, LlamaIndex	✅ Completed
OpenTelemetry-native auto-instrumentation for NVIDIA GPU Monitoring	✅ Completed
Real-Time Guardrails Implementation	✅ Completed
Programmatic Evaluation for LLM Response	✅ Completed
OpenTelemetry-native AI Agent Observability	✅ Completed