feat: Allow searching solr by user defined queries (#738)

- Adds a new endpoint to query solr for renku entities
- The api is copied from the previous (scala) services
- Results are filtered based on authz using the relation `non_public_read`

Author: eikek

.devcontainer/docker-compose.yml

@@ -1,5 +1,3 @@
-version: '3.8'
-
 services:
   data_service:
     image: "mcr.microsoft.com/devcontainers/python:3.13-bookworm"
@@ -26,12 +24,13 @@ services:
       NB_SERVER_OPTIONS__DEFAULTS_PATH: /workspace/server_defaults.json
       NB_SERVER_OPTIONS__UI_CHOICES_PATH: /workspace/server_options.json
       KUBECONFIG: "/workspace/.k3d-config.yaml"
-      SOLR_URL: "http://127.0.0.1:8983"
+      SOLR_URL: "http://localhost:8983"
       SOLR_CORE: "renku-search-dev"
     network_mode: service:db
     depends_on:
       - db
       - authz
+      - solr
 
   db:
     image: postgres:latest
@@ -45,13 +44,18 @@ services:
       POSTGRES_USER: renku
       POSTGRES_DB: postgres
       POSTGRES_PASSWORD: renku
+    # All services is put into the network of this service, so
+    # everything is reachable via localhost. This is necessary,
+    # because authzed doesn't allow insecure connections from anything
+    # other than localhost….
     ports:
-      - "8000:8000"
-      - "5432:5432"
-      - "8080:8080"
-      - "5678:5678"
-      - "50051:50051"
+      - "8000:8000" # data-service api
+      - "5432:5432" # postgresql
+      - "8080:8080" # swagger
+      - "5678:5678" # python debugger (data_service)
+      - "50051:50051" # authzed grpc
       - "8888:80"
+      - "8983:8983" # solr
 
   swagger:
     image: swaggerapi/swagger-ui
@@ -75,6 +79,7 @@ services:
   solr:
     image: solr:9
     restart: unless-stopped
+    network_mode: service:db
     volumes:
       - solr_data:/var/solr
     command:

components/renku_data_services/search/api.spec.yaml

@@ -8,6 +8,54 @@ info:
 servers:
   - url: /api/data
 paths:
+  /search/query:
+    get:
+      summary: Run a search query.
+      parameters:
+        - in: query
+          description: query parameters
+          name: params
+          style: form
+          explode: true
+          schema:
+            $ref: "#/components/schemas/SearchQuery"
+      responses:
+        "422":
+          description: Failed to validate the query parameters
+        "500":
+          description: Internal server error.
+        "503":
+          description: Temporary internal error.
+        "200":
+          description: Search results according to the query.
+          #NOTE: This is not the standard way we do pagination, but to
+          #be compatible witht the current search API we make an
+          #exception for the search here
+          headers:
+            x-page:
+              required: true
+              schema:
+                type: integer
+                format: int32
+            x-per-page:
+              required: true
+              schema:
+                type: integer
+                format: int32
+            x-total:
+              required: true
+              schema:
+                type: integer
+                format: int64
+            x-total-pages:
+              required: true
+              schema:
+                type: integer
+                format: int32
+          content:
+            application/json:
+              schema:
+                $ref: "#/components/schemas/SearchResult"
   /search/reprovision:
     post:
       summary: Start a new reprovisioning
@@ -56,6 +104,261 @@ paths:
 
 components:
   schemas:
+    SearchQuery:
+      description: Query params for the search request
+      allOf:
+      - $ref: "#/components/schemas/PaginationRequest"
+      - properties:
+          q:
+            description: The search query.
+            type: string
+            default: ""
+    PaginationRequest:
+      type: object
+      additionalProperties: false
+      properties:
+        page:
+          description: Result's page number starting from 1
+          type: integer
+          minimum: 1
+          default: 1
+        per_page:
+          description: The number of results per page
+          type: integer
+          minimum: 1
+          maximum: 100
+          default: 20
+    FacetData:
+      title: FacetData
+      examples:
+        - entityType:
+            Project: 15
+            User: 3
+      type: object
+      required:
+        - entityType
+      properties:
+        entityType:
+          $ref: '#/components/schemas/Map_EntityType_Int'
+    Group:
+      title: Group
+      examples:
+        - type: Group
+          id: 2CAF4C73F50D4514A041C9EDDB025A36
+          name: SDSC
+          namespace: SDSC
+          description: SDSC group
+          score: 1.1
+      type: object
+      required:
+        - id
+        - name
+        - namespace
+        - type
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        namespace:
+          type: string
+        description:
+          type: string
+        score:
+          type: number
+          format: double
+        type:
+          type: string
+          const: Group
+    Map_EntityType_Int:
+      title: Map_EntityType_Int
+      type: object
+      additionalProperties:
+        type: integer
+        format: int32
+    PageDef:
+      title: PageDef
+      type: object
+      required:
+        - limit
+        - offset
+      properties:
+        limit:
+          type: integer
+          format: int32
+        offset:
+          type: integer
+          format: int32
+    PageWithTotals:
+      title: PageWithTotals
+      type: object
+      required:
+        - page
+        - totalResult
+        - totalPages
+      properties:
+        page:
+          $ref: '#/components/schemas/PageDef'
+        totalResult:
+          type: integer
+          format: int64
+        totalPages:
+          type: integer
+          format: int32
+        prevPage:
+          type: integer
+          format: int32
+        nextPage:
+          type: integer
+          format: int32
+    SearchProject:
+      title: Project
+      examples:
+        - type: Project
+          id: 01HRA7AZ2Q234CDQWGA052F8MK
+          name: renku
+          slug: renku
+          namespace:
+            type: Group
+            id: 2CAF4C73F50D4514A041C9EDDB025A36
+            name: SDSC
+            namespace: SDSC
+            description: SDSC group
+            score: 1.1
+          repositories:
+            - https://github.com/renku
+          visibility: public
+          description: Renku project
+          createdBy:
+            type: User
+            id: 1CAF4C73F50D4514A041C9EDDB025A36
+            namespace: renku/renku
+            firstName: Albert
+            lastName: Einstein
+            score: 2.1
+          creationDate: '2025-03-06T15:05:42.058323392Z'
+          keywords:
+            - data
+            - science
+          score: 1
+      type: object
+      required:
+        - id
+        - name
+        - slug
+        - visibility
+        - creationDate
+        - type
+      properties:
+        id:
+          type: string
+        name:
+          type: string
+        slug:
+          type: string
+        namespace:
+          $ref: '#/components/schemas/UserOrGroup'
+        repositories:
+          type: array
+          items:
+            type: string
+        visibility:
+          $ref: '#/components/schemas/Visibility'
+        description:
+          type: string
+        createdBy:
+          $ref: '#/components/schemas/User'
+        creationDate:
+          type: string
+          format: date-time
+        keywords:
+          type: array
+          items:
+            type: string
+        score:
+          type: number
+          format: double
+        type:
+          type: string
+          const: Project
+    SearchEntity:
+      title: SearchEntity
+      oneOf:
+        - $ref: '#/components/schemas/Group'
+        - $ref: '#/components/schemas/SearchProject'
+        - $ref: '#/components/schemas/User'
+      discriminator:
+        propertyName: type
+        mapping:
+          Group: '#/components/schemas/Group'
+          Project: '#/components/schemas/SearchProject'
+          User: '#/components/schemas/User'
+    SearchResult:
+      title: SearchResult
+      type: object
+      required:
+        - facets
+        - pagingInfo
+      properties:
+        items:
+          type: array
+          items:
+            $ref: '#/components/schemas/SearchEntity'
+        facets:
+          $ref: '#/components/schemas/FacetData'
+        pagingInfo:
+          $ref: '#/components/schemas/PageWithTotals'
+    User:
+      title: User
+      examples:
+        - type: User
+          id: 1CAF4C73F50D4514A041C9EDDB025A36
+          namespace: renku/renku
+          firstName: Albert
+          lastName: Einstein
+          score: 2.1
+      type: object
+      required:
+        - id
+        - type
+      properties:
+        id:
+          type: string
+        namespace:
+          type: string
+        firstName:
+          type: string
+        lastName:
+          type: string
+        score:
+          type: number
+          format: double
+        type:
+          type: string
+          const: User
+    UserOrGroup:
+      title: UserOrGroup
+      examples:
+        - type: Group
+          id: 2CAF4C73F50D4514A041C9EDDB025A36
+          name: SDSC
+          namespace: SDSC
+          description: SDSC group
+          score: 1.1
+      oneOf:
+        - $ref: '#/components/schemas/Group'
+        - $ref: '#/components/schemas/User'
+      discriminator:
+        propertyName: type
+        mapping:
+          Group: '#/components/schemas/Group'
+          User: '#/components/schemas/User'
+    Visibility:
+      description: Project's visibility levels
+      type: string
+      enum:
+        - private
+        - public
     Reprovisioning:
       description: A reprovisioning
       type: object