GML-1991 Update Document

[chengbiao-jin]

PR Type

Documentation, Enhancement

---

Description

• Add GraphRAG quickstart scripts and configs

• Provide Docker Compose and Kubernetes deployment manifests

• Add tutorial notebooks and Python usage examples

• Revamp README with setup and LLM configuration

---

Diagram Walkthrough

flowchart LR
  readme["Updated README with quickstart and configs"]
  scripts["Setup and demo shell scripts"]
  compose["Docker Compose and Nginx configs"]
  k8s["Kubernetes deployment manifest"]
  examples["Python examples and tutorial notebook"]
  data["Sample tutorials dataset"]

  readme -- "guides" --> scripts
  readme -- "references" --> compose
  readme -- "references" --> k8s
  scripts -- "drives" --> examples
  compose -- "runs" --> examples
  examples -- "uses" --> data

Loading

File Walkthrough

	Relevant files
Documentation	6 files answer_question.py Example script to query GraphRAG answers                                  +49/-0    init_graphrag.py Initialize graph, ingest data, update GraphRAG                      +38/-0    README.md Overhaul docs with quickstart and configuration                    +281/-109 GraphRAGDemo.ipynb End-to-end GraphRAG document QA notebook                                  +471/-0  GraphRAGDemo.ipynb Adjust dataset path in existing notebook                                  +1/-1      tg_tutorials.jsonl Add sample tutorials JSONL dataset                                              [link]
Enhancement	3 files setup_graphrag_tg.sh Setup GraphRAG against existing TigerGraph instance            +73/-0    setup_graphrag.sh One-step local GraphRAG deployment with TigerGraph              +64/-0    graphrag_demo.sh Demo driver initializes GraphRAG and queries                          +31/-0
Configuration changes	5 files graphrag-k8s.yml Kubernetes manifests for GraphRAG stack                                    +322/-0  docker-compose.yml Docker Compose stack including TigerGraph                                +86/-0    docker-compose-tg.yml Compose stack for external TigerGraph deployments                +74/-0    server_config.json Sample server configuration with LLM settings                        +47/-0    nginx.conf Nginx reverse proxy for UI and API                                              +32/-0
Miscellaneous	1 files data Reference to shared tutorials data directory                          +1/-0

---

[tg-pr-agent]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪

🧪 No relevant tests

🔒 Security concerns Remote code execution and credential handling: The README recommends piping curl to sh and uses -k (TLS verification disabled): curl -k ... | sh. This pattern is vulnerable to MITM and remote code execution. Suggest using a pinned tag/commit with curl -fsSL and explicitly executing a downloaded, verified script. setup_graphrag_tg.sh writes plaintext database credentials into configs/server_config.json. Consider environment variables, Docker/K8s secrets, or prompting the user to supply them securely. K8s manifests use hostPath volumes for configs, which is risky in multi-tenant clusters. Prefer ConfigMaps/Secrets and avoid hostPath unless necessary. Images are pinned to :latest in Compose/K8s, which can lead to supply-chain drift. Recommend pinning immutable digests or versioned tags.

⚡ Recommended focus areas for review Possible Issue The script references an undefined variable (tg_version) when templating the Docker Compose file and contains an early exit that prevents services from starting. This will break the quickstart path. curl -s https://raw.githubusercontent.com/tigergraph/graphrag/refs/heads/main/docs/tutorials/docker-compose-tg.yml | sed "s/community:4.2.1/community:${tg_version}/g" > docker-compose.yml curl -s https://raw.githubusercontent.com/tigergraph/graphrag/refs/heads/main/docs/tutorials/nginx.conf -o configs/nginx.conf curl -s https://raw.githubusercontent.com/tigergraph/graphrag/refs/heads/main/docs/tutorials/server_config.json | sed '/"gsPort": "14240"/a\ "username": "'${tg_username}'",\ "password": "'${tg_password}'", ' | sed "s#http://tigergraph#${tg_host}#g; s/14240/${tg_port}/g"> configs/server_config.json exit echo "Starting GraphRAG sevices.." docker compose up -d sleep 5 Logic Error The Python version check regex is too strict and likely fails on valid versions, and the log polling looks for "Done" while the grep pattern is "DONE", causing a loop that may never exit. These issues will break the demo flow. if ! python --version 2>&1 | grep "Python 3\.1.\." >/dev/null; then echo "Python 3.11+ is needed, please check Python version or use virutal environment" exit 1 fi if ! pip freeze 2>&1 | grep pyTigerGraph >/dev/null; then echo "pyTigerGraph is needed, please install it by running: pip install pyTigerGraph" exit 2 fi echo "Initializing GraphRAG. It may take 5 to 10 minutes." python ./init_graphrag.py current_stage= while :; do stage=$(docker logs graphrag-ecc 2>&1 | grep "Processing Start\|DONE. graphrag.run" | tail -1) if [[ -n "$stage" && ! "$stage" == "$current_stage" ]]; then if [[ "$stage" =~ Processing ]]; then echo $stage | cut -d ' ' -f5-7 elif [[ "$stage" =~ Done ]]; then echo "GraphRAG initialization is done." break fi fi current_stage=$stage sleep 5 done Misconfigured Namespace The tigergraph Deployment/Service and the PVC are created without the graphrag namespace, while the rest of the stack uses it. This cross-namespace mismatch will prevent service discovery (e.g., http://tigergraph) from working. apiVersion: v1 kind: PersistentVolumeClaim metadata: name: tigergraph-data spec: accessModes: - ReadWriteOnce resources: requests: storage: 20Gi --- apiVersion: apps/v1 kind: Deployment metadata: name: tigergraph spec: replicas: 1 selector: matchLabels: app: tigergraph template: metadata: labels: app: tigergraph spec: containers: - name: tigergraph image: tigergraph/community:4.2.2 imagePullPolicy: IfNotPresent ports: - containerPort: 14240 volumeMounts: - mountPath: /home/tigergraph/tigergraph/data name: tigergraph-storage volumes: - name: tigergraph-storage persistentVolumeClaim: claimName: tigergraph-data --- apiVersion: v1 kind: Service metadata: name: tigergraph spec: selector: app: tigergraph ports: - protocol: TCP port: 14240 targetPort: 14240 type: ClusterIP