Skip to main content

A library that wraps multiple LLM providers into a consistent API while using each provider's native SDK internally, supporting multimodal I/O, file processing, and stream output.

Project description

LLM Bridge

LLM Bridge is a Python library that wraps multiple LLM providers into a consistent API while using each provider's native SDK internally, supporting multimodal I/O, file processing, and stream output.

GitHub: https://github.com/windsnow1025/LLM-Bridge

PyPI: https://pypi.org/project/LLM-Bridge/

Workflow and Features

  1. Chat Client Factory: creates a client for the specific LLM API with model parameters
    1. Model Message Converter: converts general messages to model messages
      1. Media Processor: converts general media to model compatible formats.
  2. Chat Client: generate stream or non-stream responses

Supported Features for API Types

The features listed represent the maximum capabilities of each API type supported by LLM Bridge.

API Type Input Format Capabilities Output Format
OpenAI Completion API Text, Image, PDF, Audio Thinking, Structured Output Text, Audio
OpenAI Responses API Text, Image, PDF Thinking, Web Search, Code Execution, Structured Output Text, Image
Google GenAI Text, Image, PDF, Audio, Video Thinking, Web Search, Web Fetch, Code Execution, Structured Output Text, Image, File
Anthropic Text, Image, PDF Thinking, Web Search, Web Fetch, Code Execution, Structured Output Text, File
xAI Text, Image, PDF, Audio, Video, docx, xlsx, pptx Thinking, Web Search, Code Execution, Structured Output Text

Development

Python uv

  1. Install uv: powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
  2. Install Python in uv: uv python install 3.12; upgrade Python in uv: uv python upgrade 3.12
  3. Configure requirements:
uv sync --refresh

PyCharm

Add New Interpreter >> Add Local Interpreter

  • Environment: Select existing
  • Type: uv

Usage

Copy ./usage/.env.example and rename it to ./usage/.env, then fill in the environment variables.

Build

uv build

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

llm_bridge-2.1.0.tar.gz (132.0 kB view details)

Uploaded Source

Built Distribution

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

llm_bridge-2.1.0-py3-none-any.whl (49.5 kB view details)

Uploaded Python 3

File details

Details for the file llm_bridge-2.1.0.tar.gz.

File metadata

  • Download URL: llm_bridge-2.1.0.tar.gz
  • Upload date:
  • Size: 132.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for llm_bridge-2.1.0.tar.gz
Algorithm Hash digest
SHA256 8539caa96401c9d6fddf3075fb48f07b83687357aee3db4fc28eac0e5d1131fb
MD5 16a0546dbe29c1b0f7f5e3d227fe9fe4
BLAKE2b-256 fa5533a1692e953f32c38e45c138611f5d35b81a28864d419c8b47f863c0e430

See more details on using hashes here.

File details

Details for the file llm_bridge-2.1.0-py3-none-any.whl.

File metadata

  • Download URL: llm_bridge-2.1.0-py3-none-any.whl
  • Upload date:
  • Size: 49.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for llm_bridge-2.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5a1306d1e0c2312bdce2d849390ff68c817f6ff6d077d4f438ccbcc7468065e6
MD5 3d6978a01e56ee5dcad77995fc32c50f
BLAKE2b-256 5aeb70176d4dd01df1e75799fb2f6d553c76663d4b66e46f612e8498e3db4ae8

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