observers 0.1.2

🤗 Observers: A lightweight library for (generative) AI observability, enabling insights into model interactions and everything that comes with it.

🤗🔭 Observers 🔭🤗

A lightweight library for (generative) AI observability.

Installation

First things first! You can install the SDK with pip as follows:

pip install observers

Usage

We differentiate between observers and stores. Observers wrap generative AI APIs (like OpenAI or llama-index) and track their interactions. Stores are classes that sync these observations to different storage backends (like duckdb or Hugging Face datasets).

import os

from observers.observers.models.openai import wrap_openai
from openai import OpenAI

api_key = os.environ["HF_TOKEN"]
openai_client = OpenAI(
    base_url="https://api-inference.huggingface.co/v1/", api_key=api_key
)

client = wrap_openai(openai_client)

response = client.chat.completions.create(
    model="Qwen/Qwen2.5-Coder-32B-Instruct",
    messages=[{"role": "user", "content": "Tell me a joke."}],
)

Observers

Supported Observers

• OpenAI and every other LLM provider that implements the OpenAI API message formate

Change OpenAI compliant LLM provider

The wrap_openai function allows you to wrap any OpenAI compliant LLM provider. Take a look at the example doing this for Ollama for more details.

Stores

Supported Stores

Store	Example	Annotate	Local	Free	UI filters	SQL filters
Hugging Face Datasets	example	❌	❌	✅	✅	✅
DuckDB	example	❌	✅	✅	❌	✅
Argilla	example	✅	❌	✅	✅	❌

Viewing / Querying

Hugging Face Datasets Store

To view and query Hugging Face Datasets, you can use the Hugging Face Datasets Viewer. From within here, you can query the dataset using SQL or using your own UI. Take a look at the example for more details.

DuckDB Store

The default store is DuckDB and can be viewed and queried using the DuckDB CLI. Take a look at the example for more details.

> duckdb store.db
> from openai_records limit 10;
┌──────────────────────┬──────────────────────┬──────────────────────┬──────────────────────┬───┬─────────┬──────────────────────┬───────────┐
│          id          │        model         │      timestamp       │       messages       │ … │  error  │     raw_response     │ synced_at │
│       varchar        │       varchar        │      timestamp       │ struct("role" varc…  │   │ varchar │         json         │ timestamp │
├──────────────────────┼──────────────────────┼──────────────────────┼──────────────────────┼───┼─────────┼──────────────────────┼───────────┤
│ 89cb15f1-d902-4586…  │ Qwen/Qwen2.5-Coder…  │ 2024-11-19 17:12:3…  │ [{'role': user, 'c…  │ … │         │ {"id": "", "choice…  │           │
│ 415dd081-5000-4d1a…  │ Qwen/Qwen2.5-Coder…  │ 2024-11-19 17:28:5…  │ [{'role': user, 'c…  │ … │         │ {"id": "", "choice…  │           │
│ chatcmpl-926         │ llama3.1             │ 2024-11-19 17:31:5…  │ [{'role': user, 'c…  │ … │         │ {"id": "chatcmpl-9…  │           │
├──────────────────────┴──────────────────────┴──────────────────────┴──────────────────────┴───┴─────────┴──────────────────────┴───────────┤
│ 3 rows                                                                                                                16 columns (7 shown) │
└────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘

Argilla Store

The Argilla Store allows you to sync your observations to Argilla. To use it, you first need to create a free Argilla deployment on Hugging Face. Take a look at the example for more details.

Contributing

See CONTRIBUTING.md