Skip to main content

A toolkit for building composable interactive data driven applications.

Project description

Weave by Weights & Biases

Open in Colab Stable Version Download Stats Github Checks

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases.


You can use Weave to:

  • Log and debug language model inputs, outputs, and traces
  • Build rigorous, apples-to-apples evaluations for language model use cases
  • Organize all the information generated across the LLM workflow, from experimentation to evaluations to production

Our goal is to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

Documentation

Our documentation site can be found here.

Installation

pip install weave

Usage

Tracing

You can trace any function using weave.op() - from api calls to OpenAI, Anthropic, Google AI Studio etc to generation calls from Hugging Face and other open source models to any other validation functions or data transformations in your code you'd like to keep track of.

Decorate all the functions you want to trace, this will generate a trace tree of the inputs and outputs of all your functions:

import weave
weave.init("weave-example")

@weave.op()
def sum_nine(value_one: int):
    return value_one + 9

@weave.op()
def multiply_two(value_two: int):
    return value_two * 2

@weave.op()
def main():
    output = sum_nine(3)
    final_output = multiply_two(output)
    return final_output

main()

Fuller Example

import weave
import json
from openai import OpenAI

@weave.op()
def extract_fruit(sentence: str) -> dict:
    client = OpenAI()

    response = client.chat.completions.create(
    model="gpt-3.5-turbo-1106",
    messages=[
        {
            "role": "system",
            "content": "You will be provided with unstructured data, and your task is to parse it one JSON dictionary with fruit, color and flavor as keys."
        },
        {
            "role": "user",
            "content": sentence
        }
        ],
        temperature=0.7,
        response_format={ "type": "json_object" }
    )
    extracted = response.choices[0].message.content
    return json.loads(extracted)

weave.init('intro-example')

sentence = "There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy."

extract_fruit(sentence)

Contributing

Interested in pulling back the hood or contributing? Awesome, before you dive in, here's what you need to know.

We're in the process of 🧹 cleaning up 🧹. This codebase contains a large amount code for the "Weave engine" and "Weave boards", which we've put on pause as we focus on Tracing and Evaluations.

The Weave Tracing code is mostly in: weave/trace and weave/trace_server.

The Weave Evaluations code is mostly in weave/flow.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

weave-0.51.51.tar.gz (415.5 kB view details)

Uploaded Source

Built Distribution

weave-0.51.51-py3-none-any.whl (530.0 kB view details)

Uploaded Python 3

File details

Details for the file weave-0.51.51.tar.gz.

File metadata

  • Download URL: weave-0.51.51.tar.gz
  • Upload date:
  • Size: 415.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for weave-0.51.51.tar.gz
Algorithm Hash digest
SHA256 a984b118951f333f101245f2a9b6e95111f04bf637d8858cab2b8afdb7b32d20
MD5 8275a5959f5d61f59795d8206c2718e9
BLAKE2b-256 d5f545cc4ef85841a3ed964b20193a7133affb071d72a856945c504dcda20661

See more details on using hashes here.

Provenance

The following attestation bundles were made for weave-0.51.51.tar.gz:

Publisher: release.yaml on wandb/weave

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file weave-0.51.51-py3-none-any.whl.

File metadata

  • Download URL: weave-0.51.51-py3-none-any.whl
  • Upload date:
  • Size: 530.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for weave-0.51.51-py3-none-any.whl
Algorithm Hash digest
SHA256 0b0d8b02f1a47e19dce2a1388ea2a69254d4a2f43b37240ee05000f8cdcf05a5
MD5 dbb3c2553eecc7d5784250bc33ebb64d
BLAKE2b-256 9b2b8eb9943f4f1c4171c116dae0d21fefb53c138a40161a9b6fd8dd9a3c2e4a

See more details on using hashes here.

Provenance

The following attestation bundles were made for weave-0.51.51-py3-none-any.whl:

Publisher: release.yaml on wandb/weave

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page