KBRA Weave Onboarding Guide

pip install wandb weave

wandb login --host <YOUR W&B HOST URL> <YOUR API TOKEN>

wandb.login(host=os.getenv("WANDB_BASE_URL"), key=os.getenv("WANDB_API_KEY"))

import weave
weave.init('kbra/<project-name>') # this ensures the project is created in the kbra team that has been created for the PoC

import weave
from openai import OpenAI

client = OpenAI()

# Weave will track the inputs, outputs and code of this function
@weave.op()
def extract_dinos(sentence: str) -> dict:
    response = client.chat.completions.create(
        model="gpt-4o",
        messages=[
            {
                "role": "system",
                "content": """In JSON format extract a list of `dinosaurs`, with their `name`,
their `common_name`, and whether its `diet` is a herbivore or carnivore"""
            },
            {
                "role": "user",
                "content": sentence
            }
            ],
            response_format={ "type": "json_object" }
        )
    return response.choices[0].message.content


# Initialise the weave project
weave.init('kbra/jurassic-park')

sentence = """I watched as a Tyrannosaurus rex (T. rex) chased after a Triceratops (Trike), \
both carnivore and herbivore locked in an ancient dance. Meanwhile, a gentle giant \
Brachiosaurus (Brachi) calmly munched on treetops, blissfully unaware of the chaos below."""

result = extract_dinos(sentence)
print(result)

import weave
from llama_index.core.chat_engine import SimpleChatEngine

# Initialize Weave with your project name
weave.init("kbra/llamaindex_demo")

chat_engine = SimpleChatEngine.from_defaults()
response = chat_engine.chat(
    "Say something profound and romantic about fourth of July"
)
print(response)