Skip to main content

AI development SDK for LLM-based workflows (Python)

Project description

LangFn (Python)

Comprehensive AI Development SDK for LLM-based workflows.

Features

  • Model Abstraction: Unified interface for OpenAI, Anthropic, Ollama, and more.
  • Orchestration: Sequential, Parallel, and Map-Reduce chains.
  • Graph Workflows: Stateful workflows with StateGraph.
  • Agents: Functional ToolAgent and ReActAgent.
  • Structured Output: Type-safe output parsing with Pydantic.
  • RAG: Embeddings and Vector Store support.
  • Observability: Built-in tracing with watchfn integration.

Usage

from langfn import LangFn
from langfn.models.openai import OpenAIChatModel

lang = LangFn(
    model=OpenAIChatModel(api_key="your-api-key")
)

response = await lang.complete("Hello world")
print(response.content)

Documentation

See the main documentation for more details.

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

langfn-0.0.1.tar.gz (28.8 kB view details)

Uploaded Source

Built Distribution

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

langfn-0.0.1-py3-none-any.whl (45.8 kB view details)

Uploaded Python 3

File details

Details for the file langfn-0.0.1.tar.gz.

File metadata

  • Download URL: langfn-0.0.1.tar.gz
  • Upload date:
  • Size: 28.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for langfn-0.0.1.tar.gz
Algorithm Hash digest
SHA256 d07db20d319cd99702fa2d356cfee38f6c40f2580961d3aad4df5877d80062b7
MD5 491467695dcd199cc1ebcaf7ead3d933
BLAKE2b-256 83dc9a3d740fdbde987fe042d16ddb4ee5e5b1d42ce824928d5d4310a585d72d

See more details on using hashes here.

File details

Details for the file langfn-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: langfn-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 45.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for langfn-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a079d1db7844508f76fdd6bcc93ff0abd4f9c7876746c3f1c24a1325e2b359c6
MD5 1dabaa61e4c7c6a218bfa484457d9b08
BLAKE2b-256 8ca8c0b513a98b3fb8e243b2222a307e2163f607b2e6a806b248a5ef517c04e6

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