> ## Documentation Index > Fetch the complete documentation index at: https://docs.qodo.ai/llms.txt > Use this file to discover all available pages before exploring further. # Set up Context Engine > Follow this guide to set up, install, and begin using the Context Engine in on-prem environments. **Context Engine documentation** [See the full Context Engine documentation](/core-concepts/context-engine) for more details on the Context Engine. ## Prerequisites ### Infrastructure requirements The machine running the Context Engine components should have at least: * **vCPU:** 8 * 16 **GB RAM** **PostgreSQL Instance (Recommended Size):** * **vCPU**: 4 * **Memory**: 32 GB * **Disk**: 100 GB > You may opt for smaller instances if working with a relatively small codebase. **PostgreSQL Version**: 17 **Required Configuration:** * `pg_vector` extension installed *Note: This is pre-installed in managed cloud deployments.* * TCP port `5432` must be accessible from the Kubernetes cluster where the Context Engine will be deployed * Two separate databases: * `rag-indexer` * `metadata` * Two PostgreSQL users with full access to their respective databases #### Supported Git providers: * GitHub (Cloud or Enterprise) * GitLab * Bitbucket Data Center ### Models supported These models are used by the Context Engine and must be available for the Context Engine to be used: * `gpt-5` * `claude-4.1-opus` Contact Qodo support if **none of these AI models are supported by your system**. Contact Qodo support If you're using a **custom LLM gateway**. ## 1. Context Engine installation The Context Engine consists of a few components. Install them **in the following order**: 1. `metadata-service` 2. `rag-indexer` 3. `context-retriever` 4. `context-retriever-mcp` (only if you'd like to connect your codebase understanding capabilities to tools that are not Qodo Gen or Qodo Merge). We recommend deploying all components in the **same Kubernetes namespace**. Each component requires its own `values.yaml` file with configuration like the following. ### 1. metadata-service **Example** `metadata-values.yaml`**:** ```yaml expandable theme={null} image: repository: artif-reg-self-hosted.codium.ai/proxy/codium-stack/us-central1-docker.pkg.dev/codium-production/codium-repo-self-hosted/qodo-engine-metadata tag: 1.33.1 deployments: enabled: true resources: requests: cpu: "500m" memory: "2Gi" ports: - containerPort: 8000 name: http probes: liveness: httpGet: path: /api/v1/health port: http initialDelaySeconds: 15 failureThreshold: 5 periodSeconds: 30 successThreshold: 1 service: enabled: true type: NodePort port: 8000 ports: http: targetPort: http # add externalSecrets block here if needed volumes: qodo-aware-secrets: secret: secretName: qodo-aware-secrets volumeMounts: qodo-aware-secrets: mountPath: /workspace/app/config_prod ``` **Install with Helm:** ```bash theme={null} helm upgrade --install metadata-service oci://artifacts-self-hosted.qodo.ai/codium-stack/stable/module -f ./metadata-values.yaml ``` ### 2. rag-indexer ```bash expandable theme={null} image: repository: artif-reg-self-hosted.codium.ai/proxy/codium-stack/us-central1-docker.pkg.dev/codium-production/codium-repo-self-hosted/qodo-engine-indexer tag: 1.33.1 deployments: enabled: true resources: requests: cpu: "500m" memory: "2Gi" ports: - containerPort: 3000 name: http probes: liveness: httpGet: path: /api/v1/indexer/health port: http initialDelaySeconds: 15 failureThreshold: 5 periodSeconds: 30 successThreshold: 1 service: enabled: true type: NodePort port: 3000 ports: http: targetPort: http # add externalSecrets block here if needed volumes: qodo-aware-secrets: secret: secretName: qodo-aware-secrets volumeMounts: qodo-aware-secrets: mountPath: /workspace/qodo_engine/shared_settings/secrets cronJobs: reindex: schedule: "0 3 * * *" concurrencyPolicy: "Allow" suspend: false image: repository: curlimages/curl tag: 8.11.1 pullPolicy: IfNotPresent command: - "/bin/sh" - "-c" - "curl -X POST -H 'Content-Type: application/json' -d '{}' http://indexer:3000/api/v1/indexer/reindex" configMaps: main: REINDEX_CRONJOB_SCHEDULE: "0 3 * * *" ENVIRONMENT_TYPE: "ON_PREM" ``` **Install with Helm:** ```bash theme={null} helm upgrade --install rag-indexer oci://artifacts-self-hosted.qodo.ai/codium-stack/stable/module -f ./rag-indexer-values.yaml ``` ### 3. context-retriever ```yaml expandable theme={null} image: repository: artif-reg-self-hosted.codium.ai/proxy/codium-stack/us-central1-docker.pkg.dev/codium-production/codium-repo-self-hosted/qodo-engine-context-retriever tag: 1.33.1 deployments: enabled: true resources: requests: cpu: "500m" memory: "2Gi" ports: - containerPort: 8001 name: http probes: liveness: httpGet: path: /v1/context/health port: http initialDelaySeconds: 15 failureThreshold: 5 periodSeconds: 30 successThreshold: 1 service: enabled: true type: NodePort port: 8001 ports: http: targetPort: http volumes: qodo-aware-secrets: secret: secretName: qodo-aware-secrets # add externalSecrets block here if needed volumeMounts: qodo-aware-secrets: mountPath: /app/qodo_engine/shared_settings/secrets envFrom: configMapRefs: - name: main configMaps: main: SERVICE_CONFIG__AUTH_BACKEND_PROVIDER: "noauth" ENVIRONMENT_TYPE: "ON_PREM" test: "TEsts" ``` **Install with Helm:** ```bash theme={null} helm upgrade --install context-retriever oci://artifacts-self-hosted.qodo.ai/codium-stack/stable/module -f ./context-retriever-values.yaml ``` 4. Trigger initial indexing (if you prefer to not wait until the cronjob is triggered): `kubectl create job indexer-reindex-manual --from=cronjob/indexer-reindex` 5. Verify `indexer` pod (that is part of the deployment, not the job) logs, to confirm indexing has completed (can take anywhere from minutes to up to a day, depends on how many repositories are configured and how big they are). ### 4. context-retriever-mcp **Note**: Set `context-retriever-mcp` only if you'd like to connect your codebase understanding capabilities to tools that are not Qodo Gen or Qodo Merge. ```yaml expandable theme={null} image: repository: artif-reg-self-hosted.codium.ai/proxy/codium-stack/us-central1-docker.pkg.dev/codium-production/codium-repo-self-hosted/qodo-engine-context-retriever tag: 1.5.0 deployments: enabled: true resources: requests: cpu: "500m" memory: "2Gi" ports: - containerPort: 8001 name: http probes: liveness: httpGet: path: /health port: http initialDelaySeconds: 15 failureThreshold: 5 periodSeconds: 30 successThreshold: 1 ingress: enabled: true host: "" # add client host here annotations: # add relevant annotations here hosts: - paths: - path: /mcp pathType: Prefix replicaCount: 1 service: enabled: true type: NodePort port: 8001 ports: http: targetPort: http volumes: qodo-aware-secrets: secret: secretName: qodo-aware-secrets # add externalSecrets block here if needed volumeMounts: qodo-aware-secrets: mountPath: /app/qodo_engine/shared_settings/secrets envFrom: configMapRefs: - name: main configMaps: main: SERVICE_CONFIG__EXPOSE_MCP_SERVER: "true" ENVIRONMENT_TYPE: "ON_PREM" SERVICE_CONFIG__AUTH_BACKEND_PROVIDER: "local" ``` ## 2. Finish setup on your version control Finish setting up Qodo Aware on your version control: ### Bitbucket Data Center ### 2.1 Custom CA If you are using an on-prem git provider with HTTPS connection from qodo-engine you will need to configure the custom CA like this: ```yaml hoghlight= [{1-2}] theme={null} configMaps: main: CONFIG__CERTIFICATE_BUNDLE: "/etc/ssl/custom/ca.pem" volumeMounts: custom-ca: mountPath: /etc/ssl/custom/ca.pem subPath: ca.pem volumes: custom-ca: secret: secretName: customer-ca-secret ``` ## Enabling Context Engine functionality in the Git integration #### Git Integration 1. Update qodo-merge secret, append the following ```bash theme={null} [rag_arguments] enable_rag=true [context_retrieval_service] url = "." # set this to context-retriever service address ``` 1. Restart pods to pick up the new secret.