Skip to main content

Lightweight multi-provider LLM SDK with streaming and tools

Project description

Dobby SDK

Lightweight multi-provider LLM SDK with streaming and tool support.

Installation

pip install dobby-sdk

# Or from GitHub
pip install git+https://github.com/TYNYBAY/dobby-sdk.git

# With uv
uv add dobby-sdk

Quick Start

from dobby import AgentExecutor, OpenAIProvider
from dobby.types import UserMessagePart, TextPart, TextDeltaEvent

provider = OpenAIProvider(model="gpt-4o", api_key="sk-...")
executor = AgentExecutor(provider="openai", llm=provider)

messages = [UserMessagePart(parts=[TextPart(text="Hello!")])]

async for event in executor.run_stream(messages):
    match event:
        case TextDeltaEvent(delta=delta):
            print(delta, end="")

Features

  • Multi-provider: OpenAI, Azure OpenAI, Anthropic
  • Streaming: Real-time token streaming with typed events
  • Tools: Dataclass-based tools with auto-generated schemas
  • Context injection: Pass runtime context to tools via Injected[T]
  • Structured output: Pydantic model validation for agent responses

Documentation

See docs/ for detailed documentation:

License

MIT

Project details


Download files

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

Source Distribution

dobby_sdk-0.2.15.tar.gz (161.2 kB view details)

Uploaded Source

Built Distribution

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

dobby_sdk-0.2.15-py3-none-any.whl (54.4 kB view details)

Uploaded Python 3

File details

Details for the file dobby_sdk-0.2.15.tar.gz.

File metadata

  • Download URL: dobby_sdk-0.2.15.tar.gz
  • Upload date:
  • Size: 161.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.11 {"installer":{"name":"uv","version":"0.11.11","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for dobby_sdk-0.2.15.tar.gz
Algorithm Hash digest
SHA256 d55ab6492958a869c5798edbe6a75eac95b09da8435c2726e61f2becaa40a95b
MD5 f5e54894e87e2e10d017afd332d44688
BLAKE2b-256 e174cd0d482017aba8ee48f7d3dedd16bc7ab34552a41dd26a649e2b6a340c9b

See more details on using hashes here.

File details

Details for the file dobby_sdk-0.2.15-py3-none-any.whl.

File metadata

  • Download URL: dobby_sdk-0.2.15-py3-none-any.whl
  • Upload date:
  • Size: 54.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.11.11 {"installer":{"name":"uv","version":"0.11.11","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for dobby_sdk-0.2.15-py3-none-any.whl
Algorithm Hash digest
SHA256 a9de92c87d6534964656cbd0e8453ad70a763de68a5f6ce51e8f5931bdf72556
MD5 bcb2ba6719decd9a8337909562aa400a
BLAKE2b-256 9eefeb5d758d13d407aafa8b73ff2cebb32db3c2b0621fe6e9d77e60e4967e4d

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