gpt-rag-orchestrator

(★ 100)

The GPT-RAG Orchestrator service is an agentic orchestration layer built on Microsoft Foundry Agent Service and the Microsoft Agent framework. It enables agent-based RAG workflows by coordinating multiple specialized agents to collaboratively generate accurate, context-aware responses for complex user queries.

File Explorer

Download Latest Version (.zip)

- deployment-plan.md
- devcontainer.json
- - architecture.agent.md
  - implementation.agent.md
- - api-fastapi.instructions.md
  - connectors-security.instructions.md
  - contracts.instructions.md
  - deployment.instructions.md
  - frontend.instructions.md
  - release.instructions.md
  - runtime-strategies.instructions.md
  - tests.instructions.md
- - config.yml
- - requirements.txt
  - validate-agentic-assets.py
- - block-pr-to-main.yml
  - cicd_pipeline.yaml
  - pr_pipeline.yaml
  - validate-agentic-assets.yml
- copilot-instructions.md
- dependabot.yml
- settings.json
- audit-event-v1.application-insights.schema.json
- audit-event-v1.schema.json
- audit-event-v1.sha256
- golden-dataset.jsonl
- pull_request_template.md
- README.md
- - logo.png
  - vite.svg
- - App.tsx
  - index.css
  - main.tsx
  - vite-env.d.ts
- .gitignore
- eslint.config.js
- index.html
- package-lock.json
- package.json
- postcss.config.js
- tailwind.config.js
- tsconfig.app.json
- tsconfig.json
- tsconfig.node.json
- vite.config.ts
- main.bicep
- README.md
- admin-guide-datasource-configuration.png
- nl2sql_ingestion_pipeline.png
- semantic-model-configuration.png
- semantic-model-configuration02.png
- sql-database-configuration-role-assignment.png
- testing.ipynb
- - datasources.json
- - datasources.json
- benchmark_audit.py
- deploy.ps1
- deploy.sh
- preProvision.ps1
- preProvision.sh
- - __init__.py
  - config_settings.py
  - dashboard.py
  - dashboard_config.py
  - hosted_entrypoint.py
  - responses_adapter.py
  - turn_sse.py
- - __init__.py
  - aifoundry.py
  - appconfig.py
  - cosmosdb.py
  - cosmosdb_admin.py
  - fabric.py
  - foundry_iq.py
  - foundry_iq_mcp.py
  - identity_manager.py
  - keyvault.py
  - mcp_client.py
  - multimodal_chat_client.py
  - openai_chat_client.py
  - search.py
  - sqldbs.py
  - types.py
- - __init__.py
  - agent_events.py
  - conversation_compaction.py
  - orchestrator.py
  - turn.py
- - __init__.py
  - agent_provider_v2.py
  - agent_strategies.py
  - agent_strategy_factory.py
  - base_agent_strategy.py
  - composite_context_provider.py
  - context_shaping.py
  - foundry_iq_context_provider.py
  - hosted_strategies.py
  - intent_utils.py
  - maf_agent_service_strategy.py
  - maf_lite_strategy.py
  - mcp_strategy.py
  - multimodal_search_context_provider.py
  - multimodal_strategy.py
  - nl2sql_strategy.py
  - retrieval_intent.py
  - search_context_provider.py
  - single_agent_rag_strategy_v2.py
- - __init__.py
  - audit.py
  - audit_contract.py
  - audit_sanitizer.py
  - telemetry.py
- - __init__.py
  - citations.py
  - foundry_platform.py
  - jwt_utils.py
  - metadata.py
  - retrieval_backend.py
  - test_stream.py
  - tools.py
- __init__.py
- constants.py
- dependencies.py
- main.py
- schemas.py
- startup_warmup.py
- upload_prompts.py
- - foundry_iq_mcp_canonical_source.json
- - audit_event_v1.json
  - audit_event_v1_ingestion_document.json
  - audit_event_v1_ingestion_run.json
  - audit_event_v1_root.json
- conftest.py
- rbac.ps1
- test_agent_strategies.py
- test_agent_strategy_factory.py
- test_audit_contract.py
- test_audit_emitter.py
- test_audit_foundry_source_types.py
- test_audit_http_correlation.py
- test_audit_lifecycle.py
- test_audit_propagation.py
- test_audit_telemetry.py
- test_base_agent_strategy.py
- test_build_conversation_filter.py
- test_citations.py
- test_container_contract.py
- test_conversation_compaction.py
- test_conversation_history.py
- test_copilot_release_skill.py
- test_dashboard.py
- test_dashboard_config.py
- test_foundry_iq.py
- test_foundry_iq_fabric_data_agent.py
- test_foundry_iq_fabric_iq.py
- test_foundry_iq_mcp.py
- test_foundry_iq_onelake.py
- test_foundry_iq_sharepoint_indexed.py
- test_foundry_iq_sharepoint_remote.py
- test_foundry_iq_web_grounding.py
- test_foundry_iq_work_iq.py
- test_foundry_platform.py
- test_hosted_entrypoint_import.py
- test_hosted_responses.py
- test_hosted_strategies.py
- test_maf_agent_service_strategy.py
- test_maf_lite_strategy.py
- test_mcp_client.py
- test_mcp_strategy.py
- test_metadata_context.py
- test_multimodal_strategy.py
- test_nl2sql_sql_validation.py
- test_nl2sql_strategy.py
- test_openai_chat_client.py
- test_orchestration_turn.py
- test_retrieval_backend.py
- test_retrieval_intent.py
- test_retrieval_logging.py
- test_single_agent_rag_v2_conversation_scope.py
- test_single_agent_rag_v2_direct_llm_history.py
- test_single_agent_rag_v2_thread_conversation.py
- test_startup_warmup.py
.dockerignore
.env.sample
.gitattributes
.gitignore
.image-tag.txt
.pr-body.md
.release-notes.md
AGENTS.md
azure.yaml
CHANGELOG.md
Dockerfile
launch.json
LICENSE.md
pyproject.toml
README.md
requirements.txt
SECURITY.md
VERSION

# Installation Guide

1. Get the code

git clone https://github.com/Azure/gpt-rag-orchestrator

Downloads the entire project code from GitHub to your computer.

cd gpt-rag-orchestrator

Moves into the project folder you just downloaded.

2. Docker

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Docker Desktop Needed to build and run containers. Install it and keep it running in the background.

docker build -t gpt-rag-orchestrator .

Builds a runnable image based on the Dockerfile.

docker run -p 8080:80 gpt-rag-orchestrator

Runs the built image as an actual container.

✅ Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.

3. Node.js

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Node.js Node.js must be installed to use npm. The LTS version is recommended.

cd frontend

This project's files live in a subfolder, so move into it first.

npm install

Downloads and installs the libraries listed in package.json.

npm start

Starts the development/run server.

✅ After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.

4. Python

Easy

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install -r requirements.txt

Installs the Python libraries listed in requirements.txt (or similar).

jupyter notebook

Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.

✅ If it runs without errors and prints output in the terminal, it worked.