Skip to main content

Dify plugin for LiveKit Agents

Project description

LiveKit Plugins Dify

LLM inference implemention from Dify API

Usage:

    agent = VoicePipelineAgent(
        vad=ctx.proc.userdata["vad"],
        stt=deepgram.STT(model=dg_model),
        llm=dify.LLM(
            base_url="Your dify API",
            api_key="Your Dify App API Key",
        ),
        tts=openai.TTS(),
        chat_ctx=initial_ctx,
    )

Notes: Do not use initial_ctx = llm.ChatContext().append to add system prompt or context. Implement these in your Dify.

Only 'Chatflow' is supported.

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

livekit_plugins_dify-0.3.0.tar.gz (5.2 kB view details)

Uploaded Source

File details

Details for the file livekit_plugins_dify-0.3.0.tar.gz.

File metadata

  • Download URL: livekit_plugins_dify-0.3.0.tar.gz
  • Upload date:
  • Size: 5.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.5

File hashes

Hashes for livekit_plugins_dify-0.3.0.tar.gz
Algorithm Hash digest
SHA256 99590517828f2855c973ba423e530198d41e328982f77e30064d802a64f56fdd
MD5 c08443774125058ab2c759aca9165bfc
BLAKE2b-256 495a6012015f5d80df1ba7d4f5dc7cbb3413bddf74b42748af37bd1d2f61b60a

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