Community-maintained integration. This service is built and maintained by usemoss. Pipecat does not test or officially support it. Please report issues and request changes on the source repository. Learn more about community integrations.
Overview
MossRetrievalService performs low-latency semantic retrieval against
Moss vector indexes and injects the relevant
passages into your Pipecat agent’s LLM context. Its query() method returns a
MossIndexProcessor that you place in the pipeline to augment each user turn
with context-aware search results.
Source Repository
Source code, examples, and issues for the Moss integration
PyPI Package
The
pipecat-moss package on PyPIMoss
Learn more about Moss semantic retrieval
Moss Portal
Create a project and get your project ID and key
Installation
This is a community-maintained package distributed separately frompipecat-ai:
Prerequisites
Moss Project Setup
Before using the Moss retrieval service, you need:- Moss Project: Create a project in the Moss Portal
- Project Credentials: Get your project ID and project key from the portal
- A Moss Index: Create and populate an index before running your pipeline (see the source repository for the index-creation example)
Required Environment Variables
MOSS_PROJECT_ID: Your Moss project IDMOSS_PROJECT_KEY: Your Moss project key
Configuration
MossRetrievalService
Load an index before the pipeline runs with the awaitableload_index(index_name) method, then create a pipeline processor with
query(index_name, *, top_k=5, alpha=0.8).
query() parameters
Blends semantic vs. keyword scoring.
0.0 is keyword-only and 1.0 is
semantic-only.Usage
setup_indexes() must be awaited before the pipeline starts so the service
can load the Moss index. See the source
repository for a complete working
example.