Skip to main content

Python client for Autoblocks

Project description

📚 Documentation   •   🖥️ Application   •   🏠 Home

Installation

poetry add autoblocksai
pip install autoblocksai

Examples

See our Python examples.

Quickstart

import os
import uuid
import traceback
import time

import openai
from autoblocks.tracer import AutoblocksTracer

openai.api_key = os.environ["OPENAI_API_KEY"]
messages = [
  {
    "role": "system",
    "content": "You are a helpful assistant. You answer questions about a software product named Acme.",
  },
  {
    "role": "user",
    "content": "How do I sign up?",
  },
]
request_params = dict(
  model="gpt-3.5-turbo",
  messages=messages,
  temperature=0.7,
  top_p=1,
  frequency_penalty=0,
  presence_penalty=0,
  n=1,
)

tracer = AutoblocksTracer(
  os.environ["AUTOBLOCKS_INGESTION_KEY"],
  # All events sent below will have this trace ID
  trace_id=str(uuid.uuid4()),
  # All events sent below will include this property
  # alongside any other properties set in the send_event call
  properties=dict(
    provider="openai",
  ),
)

tracer.send_event(
  "ai.request",
  properties=request_params,
)

try:
  start_time = time.time()
  response = openai.ChatCompletion.create(**request_params)
  tracer.send_event(
    "ai.response",
    properties=dict(
      response=response,
      latency_ms=(time.time() - start_time) * 1000,
    ),
  )
except Exception as error:
  tracer.send_event(
    "ai.error",
    properties=dict(
      error_message=str(error),
      stacktrace=traceback.format_exc(),
    ),
  )

# Simulate user feedback
tracer.send_event(
  "user.feedback",
  properties=dict(
    feedback="good",
  ),
)

Documentation

See the full documentation.

Issues / Questions

Please open an issue if you encounter any bugs, have any questions, or have any feature requests.

Contributing

See CONTRIBUTING.md.

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

autoblocksai-0.0.33.tar.gz (19.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

autoblocksai-0.0.33-py3-none-any.whl (27.7 kB view details)

Uploaded Python 3

File details

Details for the file autoblocksai-0.0.33.tar.gz.

File metadata

  • Download URL: autoblocksai-0.0.33.tar.gz
  • Upload date:
  • Size: 19.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.11.8 Linux/6.5.0-1015-azure

File hashes

Hashes for autoblocksai-0.0.33.tar.gz
Algorithm Hash digest
SHA256 e00bc69cf876d4ec9ba2b9a07b579002989a3ac61bbb5c76515fd2ca3c246446
MD5 54acdfdda8af800c353c13b7213eb5d9
BLAKE2b-256 5127db719a196d7ba1371513d62df8b429a915b6e34509946ca093ab4e60e33a

See more details on using hashes here.

File details

Details for the file autoblocksai-0.0.33-py3-none-any.whl.

File metadata

  • Download URL: autoblocksai-0.0.33-py3-none-any.whl
  • Upload date:
  • Size: 27.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.7.1 CPython/3.11.8 Linux/6.5.0-1015-azure

File hashes

Hashes for autoblocksai-0.0.33-py3-none-any.whl
Algorithm Hash digest
SHA256 26f0f7877d9cf6ee1071b73d6bd86001f199ce27c552b52058a71699aa5a2ef6
MD5 ce3c400cb5513a2f46f5506d76a4a9ea
BLAKE2b-256 0ede7d5842ad97dec89b13a9c874027f77b658584b9b3b4df6a1ed5c24bedcac

See more details on using hashes here.

Supported by

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