Multi-Tenant Index Routing with Moss#230
Open
CoderOMaster wants to merge 2 commits into
Open
Conversation
CoderOMaster
requested review from
HarshaNalluru,
r4ghu and
yatharthk2
as code owners
CoderOMaster
force-pushed
the
keshav/multi-index-demo
branch
from
4d96bb1 to
4dd494c
Compare
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new Python cookbook demonstrating multi-tenant index routing in Moss by exposing one LangChain tool per tenant index and letting the LLM choose which index(es) to query at runtime.
Changes:
- Adds
examples/cookbook/multi-tenant/cookbook with an asyncbind_toolsagent, lazy per-index loading, and sample tenant datasets. - Updates
ROADMAP.mdto reflect shipped/in-progress items and reorganizes sections.
Reviewed changes
Copilot reviewed 10 out of 10 changed files in this pull request and generated 8 comments.
Show a summary per file
| File | Description |
|---|---|
| ROADMAP.md | Reorganizes roadmap sections and updates shipped/in-progress items. |
| examples/cookbook/multi-tenant/README.md | Cookbook documentation: setup, running, and routing explanation. |
| examples/cookbook/multi-tenant/pyproject.toml | Defines cookbook packaging + dependencies. |
| examples/cookbook/multi-tenant/moss_multitenant.py | Implements lazy index store + tool factory for per-tenant search tools. |
| examples/cookbook/multi-tenant/agent.py | Demo agent: tool-calling loop, index creation from JSON, CLI. |
| examples/cookbook/multi-tenant/.env.example | Example env vars for Moss + OpenAI credentials. |
| examples/cookbook/multi-tenant/data/saas_company.json | Sample tenant knowledge base (Stackbase). |
| examples/cookbook/multi-tenant/data/retail_urban_threads.json | Sample tenant knowledge base (Urban Threads). |
| examples/cookbook/multi-tenant/data/pizza_shop.json | Sample tenant knowledge base (Luigi’s Pizzeria). |
| examples/cookbook/multi-tenant/data/law_firm.json | Sample tenant knowledge base (Harrison & Cole LLP). |
| examples/cookbook/multi-tenant/data/health_vitacare.json | Sample tenant knowledge base (VitaCare Clinic). |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+42
to
+45
| if index_name not in self._loaded: | ||
| await self._client.load_index(index_name) | ||
| self._loaded.add(index_name) | ||
|
|
yatharthk2
reviewed
May 12, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Pull Request Checklist
Please ensure that your PR meets the following requirements:
Description
Adds a new cookbook: Multi-Tenant Index Routing with Moss (
examples/cookbook/multi-tenant/).Each business gets its own named Moss index (
food-luigis-pizzeria,law-harrison-cole,tech-stackbase,health-vitacare,retail-urban-threads). The agent exposes oneStructuredToolper index viallm.bind_tools(). GPT-4.1-mini selects which index(es) to query based purely on tool name and description — no hard-coded routing logic. Ambiguous questions trigger parallel Moss queries viaasyncio.gatherand the model synthesises a merged answer.This demonstrates a key Moss use case: dynamically injecting the right business-specific context at runtime without system prompt bloat or context leakage across tenants.
Fixes # (issue number)
Type of Change