⚡ Unified LLM data management to drive accuracy at scale ⚡
pip install log10-io
A one-line Python integration to manage your LLM data.
import openai
from log10.load import log10
log10(openai)
# all your openai calls are now logged - including 3rd party libs using openai
For OpenAI v1, use from log10.load import OpenAI instead of from openai import OpenAI
from log10.load import OpenAI
client = OpenAI()
Access your LLM data at log10.io
Use Log10 to log both closed and open-source LLM calls, e.g. OpenAI, Anthropic, Google Gemini, Llama, Mistral, etc. It helps you:
Log10 offers various integration methods, including a python LLM library wrapper, the Log10 LLM abstraction, and callbacks, to facilitate its use in both existing production environments and new projects. Pick the one that works best for you.
| log10 ver | openai v0 | openai v1 |
|---|---|---|
| 0.4 | log10(openai) ✅ | ❌ |
| 0.5+ | log10(openai) ✅ | from log10.load import OpenAI ✅ |
OpenAI v0 - Use library wrapper log10(openai). Check out examples/logging in log10 version 0.4.6.
import openai
from log10.load import log10
log10(openai)
# openai calls are now logged - including 3rd party libs using openai such as magentic or langchain
OpenAI v1
NOTE: We added OpenAI v1 API support in log10
0.5.0release.load.log10(openai)still works for openai v1. This also enables logging LLM completions from providers which support OpenAI API, such as Ollama.
from log10.load import OpenAI
# from openai import OpenAI
client = OpenAI()
completion = client.completions.create(model="gpt-3.5-turbo-instruct", prompt="Once upon a time")
# All completions.create and chat.completions.create calls will be logged
Full script here.
Use Log10 LLM abstraction
from log10.openai import OpenAI
llm = OpenAI({"model": "gpt-3.5-turbo"}, log10_config=Log10Config())
openai v1+ lib required. Full script here.
Use library wrapper log10(anthropic).
Full script here.
import anthropic
from log10.load import log10
log10(anthropic)
# anthropic calls are now logged
Use Log10 LLM abstraction. Full script here.
from log10.anthropic import Anthropic
llm = Anthropic({"model": "claude-2"}, log10_config=Log10Config())
We support OpenAI and Anthropic Async-client (e.g. AsyncOpenAI and AsyncAnthropic client) in their Python SDK
You could use the same code log10(openai) or log10(anthropic) and then call the async-client to start logging asynchronous mode (including streaming).
Release 0.9.0 includes significant improvements in how we handle concurrency while using LLM in asynchronous streaming mode.
This update is designed to ensure that logging at steady state incurs no overhead (previously up to 1-2 seconds), providing a smoother and more efficient experience in latency critical settings.
Important Considerations for Short-Lived Scripts:
💡For short-lived scripts using asynchronous streaming, it's important to note that you may need to wait until all logging requests have been completed before terminating your script. We have provided a convenient method called
finalize()to handle this. Here's how you can implement this in your code:
from log10._httpx_utils import finalize
...
await finalize()
Ensure finalize() is called once, at the very end of your event loop to guarantee that all pending logging requests are processed before the script exits.
For more details, check async logging examples.
Log open-source LLM calls, e.g. Llama, Mistral, etc from providers. Currently we support inference endpoints on Together.AI and MosaicML (ranked on the top based on our benchmarking on Llama-2 inference providers). Adding other providers is on the roadmap.
If the providers support OpenAI API (e.g. Groq, vLLM, Together), you can easily starting logging using log10(openai).
MosaicML with LLM abstraction. Full script here.
from log10.mosaicml import MosaicML
llm = MosaicML({"model": "llama2-70b-chat/v1"}, log10_config=Log10Config())
Together with LLM abstraction. Full script here.
from log10.together import Together
llm = Together({"model": "togethercomputer/llama-2-70b-chat"}, log10_config=Log10Config())
Use Log10 callbacks if you use LangChain's LLM abstraction. Full script here.
from langchain.chat_models import ChatOpenAI
from langchain.schema import HumanMessage
from log10.langchain import Log10Callback
from log10.llm import Log10Config
log10_callback = Log10Callback(log10_config=Log10Config())
messages = [
HumanMessage(content="You are a ping pong machine"),
HumanMessage(content="Ping?"),
]
llm = ChatOpenAI(model_name="gpt-3.5-turbo", callbacks=[log10_callback])
Read more here for options for logging using library wrapper, langchain callback logger and how to apply log10 tags here.
Optimizing prompts requires a lot of manual effort. Log10 provides a copilot that can help you with suggestions on how to optimize your prompt.
Add feedback to your completions. Checkout the Python example
or use CLI log10 feedback-task create and log10 feedback create. Please check our doc for more details.
Leverage your current feedback and AI by using our AutoFeedback feature to generate feedback automatically. Here’s a quick guide:
log10 feedback predict --task_id $FEEDBACK_TASK_ID --content '{"prompt": "this is article", "response": "summary of the article."}'.
--file or pass a completion from your Log10 logs with --completion_id.log10 feedback predict --help.Feel free to integrate AutoFeedback into your workflow to enhance the feedback and evaluation process.
Easily benchmark your logged completions using LLM models from OpenAI, Anthropic, Mistral, Meta, etc., by using the log10 completions benchmark_models command in the log10 CLI.
Generate detailed reports and gain insights to enhance your model's performance and cost.
Please refer to the cli doc or the demo video for details.
Prompt chains such as those in Langchain can be difficult to debug. Log10 provides prompt provenance, session tracking and call stack functionality to help debug chains.
Use your data and feedback from users to fine-tune custom models with RLHF with the option of building and deploying more reliable, accurate and efficient self-hosted models.
Create flexible groups to share and collaborate over all of the above features
LOG10_URL=https://log10.ioLOG10_TOKEN: From the Settings tab in log10.ioLOG10_ORG_ID: From the Organization tab in log10.ioOPENAI_API_KEY: OpenAI API keyANTHROPIC_API_KEY: Anthropic API keyYou can find and run examples under folder examples, e.g. run a logging example:
python examples/logging/chatcompletion.py
Also you can run some end-to-end tests with xdocttest installed (pip install xdoctest).
# list all tests
python -m xdoctest log10 list
# run all tests
python -m xdoctest log10 all
# run a single test, e.g.
python -m xdoctest /Users/wenzhe/dev/log10/log10/load.py log10:0
Few options to enable debug logging:
export LOG10_DEBUG=1log10.load.log10(DEBUG_=True) when using log10.loadlog10_config(DEBUG=True) when using llm abstraction classes or callback.log10 provides a managed data store, but if you'd prefer to manage data in your own environment, you can use data stores like google big query.
Install the big query client library with:
pip install log10-io[bigquery]
And provide the following configuration in either a .env file, or as environment variables:
| Name | Description |
|---|---|
LOG10_DATA_STORE | Either log10 or bigquery |
LOG10_BQ_PROJECT_ID | Your google cloud project id |
LOG10_BQ_DATASET_ID | The big query dataset id |
LOG10_BQ_COMPLETIONS_TABLE_ID | The name of the table to store completions in |
Note that your environment should have been setup with google cloud credentials. Read more here about authenticating.
We add CLI to manage your completions and feedback. Read more here.
We welcome community participation and feedback. Please leave an issue, submit a PR or join our Discord. For enterprise use cases, please contact us to set up a shared slack channel.
FAQs
Unified LLM data management
We found that log10-io demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 2 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
Security News
Attackers used a malicious npm package typosquatting a popular ESLint plugin to steal sensitive data, execute commands, and exploit developer systems.
Security News
The Ultralytics' PyPI Package was compromised four times in one weekend through GitHub Actions cache poisoning and failure to rotate previously compromised API tokens.
Security News
Research
Socket researchers found a malicious Maven package impersonating the legitimate ‘XZ for Java’ library, introducing a backdoor for remote code execution.