Langtrace is an open source observability software which lets you capture, debug and analyze traces and metrics from all your applications that leverages LLM APIs, Vector Databases and LLM based Frameworks.
The traces generated by Langtrace adhere to Open Telemetry Standards(OTEL). We are developing semantic conventions for the traces generated by this project. You can checkout the current definitions in this repository. Note: This is an ongoing development and we encourage you to get involved and welcome your feedback.
To use the managed SaaS version of Langtrace, follow the steps below:
- Sign up by going to this link.
- Create a new Project after signing up. Projects are containers for storing traces and metrics generated by your application. If you have only one application, creating 1 project will do.
- Generate an API key by going inside the project.
- In your application, install the Langtrace SDK and initialize it with the API key you generated in the step 3.
- The code for installing and setting up the SDK is shown below
Get started by adding simply three lines to your code!
pipinstalllangtrace-python-sdkfromlangtrace_python_sdkimportlangtrace# Must precede any llm module importslangtrace.init(api_key=<your_api_key>)OR
fromlangtrace_python_sdkimportlangtrace# Must precede any llm module importslangtrace.init() # LANGTRACE_API_KEY as an ENVIRONMENT variableGet started by adding simply two lines to your code and see traces being logged to the console!
pipinstalllangtrace-python-sdkfromlangtrace_python_sdkimportlangtrace# Must precede any llm module importslangtrace.init(write_to_langtrace_cloud=False, batch=False)Get started by adding simply three lines to your code and see traces being exported to your remote location!
pipinstalllangtrace-python-sdkfromlangtrace_python_sdkimportlangtrace# Must precede any llm module importslangtrace.init(custom_remote_exporter=<your_exporter>, batch=<TrueorFalse>)@with_langtrace_root_span- this decorator is designed to organize and relate different spans, in a hierarchical manner. When you're performing multiple operations that you want to monitor together as a unit, this function helps by establishing a "parent" (LangtraceRootSpanor whatever is passed toname) span. Then, any calls to the LLM APIs made within the given function (fn) will be considered "children" of this parent span. This setup is especially useful for tracking the performance or behavior of a group of operations collectively, rather than individually.
fromlangtrace_python_sdk.utils.with_root_spanimportwith_langtrace_root_span@with_langtrace_root_span()defexample():
response=client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Say this is a test three times"}],
stream=False,
)
returnresponsewith_additional_attributes- this function is designed to enhance the traces by adding custom attributes to the current context. These custom attributes provide extra details about the operations being performed, making it easier to analyze and understand their behavior.
fromlangtrace_python_sdk.utils.with_root_spanimport (
with_langtrace_root_span,
with_additional_attributes,
)
@with_additional_attributes({"user.id": "1234", "user.feedback.rating": 1})defapi_call1():
response=client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Say this is a test three times"}],
stream=False,
)
returnresponse@with_additional_attributes({"user.id": "5678", "user.feedback.rating": -1})defapi_call2():
response=client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Say this is a test three times"}],
stream=False,
)
returnresponse@with_langtrace_root_span()defchat_completion():
api_call1()
api_call2()Langtrace automatically captures traces from the following vendors:
| Vendor | Type | Typescript SDK | Python SDK |
|---|---|---|---|
| OpenAI | LLM | ✅ | ✅ |
| Anthropic | LLM | ✅ | ✅ |
| Azure OpenAI | LLM | ✅ | ✅ |
| Langchain | Framework | ❌ | ✅ |
| LlamaIndex | Framework | ✅ | ✅ |
| Pinecone | Vector Database | ✅ | ✅ |
| ChromaDB | Vector Database | ✅ | ✅ |
- To request for features, head over here to start a discussion.
- To raise an issue, head over here and create an issue.
We welcome contributions to this project. To get started, fork this repository and start developing. To get involved, join our Discord workspace.
To report security vulnerabilites, email us at security@scale3labs.com. You can read more on security here.