feat: add Compass catalog manifests for all agentic packs #133
There are no files selected for viewing
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,26 @@ | ||
| apiVersion: backstage.io/v1alpha1 | ||
| kind: Location | ||
| metadata: | ||
| name: agentic-plugins | ||
| title: Agentic Plugins | ||
| description: > | ||
| Root catalog entry point for the agentic-plugins repository. | ||
| Points to all agentic pack locations and MCP server manifests | ||
| for Compass ingestion. | ||
| annotations: | ||
| agentic-plugins.redhat.com/version: "1.0" | ||
| agentic-plugins.redhat.com/repo: "agentic-plugins" | ||
| spec: | ||
| targets: | ||
| # Repository-level system | ||
| - ./system.yaml | ||
| # Agentic Pack Locations | ||
| - ./ocp-admin/catalog-info.yaml | ||
| - ./rh-sre/catalog-info.yaml | ||
| - ./rh-virt/catalog-info.yaml | ||
| - ./rh-developer/catalog-info.yaml | ||
| - ./rh-basic/catalog-info.yaml | ||
| - ./rh-ai-engineer/catalog-info.yaml | ||
| - ./rh-automation/catalog-info.yaml | ||
| # MCP Servers Location | ||
| - ./mcps/catalog-info.yaml |
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,181 @@ | ||
| apiVersion: mcp/v1beta1 | ||
| kind: MCPServer | ||
| metadata: | ||
| namespace: agentic-plugins | ||
| name: ai-observability | ||
| title: AI Observability MCP Server | ||
| description: > | ||
| AI observability MCP server for monitoring and debugging AI/ML model | ||
| inference, performance metrics, and serving runtime health on | ||
| Red Hat OpenShift AI. | ||
| labels: | ||
| distribution: external | ||
| annotations: | ||
| backstage.io/source-location: >- | ||
| url:https://github.com/RHEcosystemAppEng/agentic-plugins/blob/main/rh-ai-engineer/mcps.json | ||
| tags: | ||
| - ai | ||
| - observability | ||
| - machine-learning | ||
| - monitoring | ||
| - mcp-server | ||
| links: | ||
| - url: https://github.com/rh-ai-quickstart/ai-observability-summarizer | ||
| title: Upstream Repository | ||
| icon: github | ||
| spec: | ||
| type: remote | ||
| lifecycle: beta | ||
| owner: group:redhat/ai5-marketplace | ||
| system: default/agentic-plugins | ||
| primitives: | ||
| - type: tool | ||
| name: list_models | ||
| description: List all available AI models for analysis. | ||
| - type: tool | ||
| name: list_vllm_namespaces | ||
| description: Get list of monitored vLLM Kubernetes namespaces with observability data. | ||
| - type: tool | ||
| name: get_model_config | ||
| description: Get available LLM models configured for summarization and analysis. | ||
| - type: tool | ||
| name: get_vllm_metrics_tool | ||
| description: Get available vLLM metrics with friendly names and PromQL queries. | ||
| - type: tool | ||
| name: fetch_vllm_metrics_data | ||
| description: Fetch vLLM metrics data with time-series for dashboard display. | ||
| - type: tool | ||
| name: analyze_vllm | ||
| description: Analyze vLLM metrics and generate an AI summary using an LLM. | ||
| - type: tool | ||
| name: calculate_metrics | ||
| description: Calculate statistics (avg, min, max, latest) for provided metrics data. | ||
| - type: tool | ||
| name: list_summarization_models | ||
| description: List all configured summarization models with metadata from runtime configuration. | ||
| - type: tool | ||
| name: get_gpu_info | ||
| description: Get cluster GPU information from Prometheus DCGM metrics. | ||
| - type: tool | ||
| name: get_deployment_info | ||
| description: Get model deployment details for a model in a namespace. | ||
| - type: tool | ||
| name: chat_vllm | ||
| description: Chat about vLLM metrics by asking follow-up questions on analyzed data. | ||
| - type: tool | ||
| name: analyze_openshift | ||
| description: Analyze OpenShift metrics for a category and scope with LLM-generated summary. | ||
| - type: tool | ||
| name: fetch_openshift_metrics_data | ||
| description: Fetch OpenShift metrics data for dashboard visualization without LLM analysis. | ||
| - type: tool | ||
| name: list_openshift_namespaces | ||
| description: Get list of all OpenShift namespaces observed in Prometheus. | ||
| - type: tool | ||
| name: list_openshift_metric_groups | ||
| description: Return available OpenShift metric group categories for cluster-wide analysis. | ||
| - type: tool | ||
| name: list_openshift_namespace_metric_groups | ||
| description: Return OpenShift metric groups that support namespace-scoped analysis. | ||
| - type: tool | ||
| name: chat_openshift | ||
| description: Chat about OpenShift metrics for a specific category and scope. | ||
| - type: tool | ||
| name: search_metrics | ||
| description: Search for Prometheus metrics by pattern using semantic understanding. | ||
| - type: tool | ||
| name: get_metric_metadata | ||
| description: Get detailed metadata for a specific Prometheus metric. | ||
| - type: tool | ||
| name: get_label_values | ||
| description: Get all possible values for a specific label of a Prometheus metric. | ||
| - type: tool | ||
| name: execute_promql | ||
| description: Execute a PromQL query and return structured results. | ||
| - type: tool | ||
| name: explain_results | ||
| description: Explain PromQL query results in natural language. | ||
| - type: tool | ||
| name: suggest_queries | ||
| description: Suggest related PromQL queries based on user intent. | ||
| - type: tool | ||
| name: select_best_metric | ||
| description: Select the best metric for a user question using semantic analysis. | ||
| - type: tool | ||
| name: find_best_metric_with_metadata_v2 | ||
| description: Enhanced metric selection with improved semantic analysis and query suggestions. | ||
| - type: tool | ||
| name: find_best_metric_with_metadata | ||
| description: Find the best metric for a user question using comprehensive metadata analysis. | ||
| - type: tool | ||
| name: get_metrics_categories | ||
| description: Get all metric categories with summary counts, priorities, and example queries. | ||
| - type: tool | ||
| name: search_metrics_by_category | ||
| description: Search metrics filtered by category IDs and priority levels. | ||
| - type: tool | ||
| name: get_category_metrics_detail | ||
| description: Get category summaries or detailed metrics catalog for a single category. | ||
| - type: tool | ||
| name: convert_time_to_promql_duration | ||
| description: Convert decimal hours to Prometheus duration format for use in PromQL queries. | ||
| - type: tool | ||
| name: query_tempo_tool | ||
| description: Search Tempo traces by TraceQL query, service, operation, and time range. | ||
| - type: tool | ||
| name: get_trace_details_tool | ||
| description: Get detailed trace information including spans by trace ID. | ||
| - type: tool | ||
| name: chat_tempo_tool | ||
| description: Conversational interface for Tempo trace analysis using natural language questions. | ||
| - type: tool | ||
| name: korrel8r_query_objects | ||
| description: Execute a Korrel8r domain query and return correlated objects. | ||
| - type: tool | ||
| name: korrel8r_get_correlated | ||
| description: Return correlated objects (alerts, logs, traces, metrics) for a Korrel8r query. | ||
| - type: tool | ||
| name: get_correlated_logs | ||
| description: Fetch application and infrastructure logs for a namespace or pod via Korrel8r. | ||
| - type: tool | ||
| name: chat | ||
| description: Chat with AI models using observability tools with progress tracking. | ||
| - type: tool | ||
| name: validate_api_key | ||
| description: Validate an API key for a given provider by making a minimal server-side request. | ||
| - type: tool | ||
| name: save_api_key | ||
| description: Save or update a provider API key in a Kubernetes Secret. | ||
| - type: tool | ||
| name: check_provider_secret | ||
| description: Check if a provider API key secret exists in the cluster. | ||
| - type: tool | ||
| name: delete_provider_secret | ||
| description: Delete a provider API key secret from the cluster. | ||
| - type: tool | ||
| name: list_provider_models | ||
| description: Query a provider API to list available models for configuration. | ||
| - type: tool | ||
| name: add_model_to_config | ||
| description: Add a new model to the model configuration by updating the Kubernetes ConfigMap. | ||
| - type: tool | ||
| name: update_maas_model_api_key | ||
| description: Update API key and optionally endpoint for an existing MaaS model. | ||
| packages: [] | ||
| remotes: | ||
| - url: https://ai-observability.example.com/mcp | ||
| dependsOn: | ||
| - system:default/agentic-plugins | ||
| dependencyOf: | ||
|
r2dedios marked this conversation as resolved.
|
||
| - airesource:rh-ai-engineer/ai-observability | ||
| - airesource:rh-ai-engineer/debug-inference | ||
| - airesource:rh-ai-engineer/ds-project-setup | ||
| - airesource:rh-ai-engineer/guardrails-config | ||
| - airesource:rh-ai-engineer/model-deploy | ||
| - airesource:rh-ai-engineer/model-monitor | ||
| - airesource:rh-ai-engineer/model-registry | ||
| - airesource:rh-ai-engineer/nim-setup | ||
| - airesource:rh-ai-engineer/pipeline-manage | ||
| - airesource:rh-ai-engineer/rh-ai-engineer | ||
| - airesource:rh-ai-engineer/serving-runtime-config | ||
| - airesource:rh-ai-engineer/workbench-manage | ||
Oops, something went wrong.
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.