refactor: retire external vector deployment

docker-compose.dev.yml

@@ -32,10 +32,11 @@ services:
       THT_SECRETS_FILE: /run/secrets/thothii.secrets
       THT_DB_NAME: ${THT_DB_NAME:-}
       THT_DWH_REST_URL: ${THT_DWH_REST_URL:-}
-      THT_VEC_REST_URL: ${THT_VEC_REST_URL:-}
-      THT_VEC_WRITE_REST_URL: ${THT_VEC_WRITE_REST_URL:-}
-      THT_OLLAMA_URL: ${THT_OLLAMA_URL:-}
       THT_LLM_URL: ${THT_LLM_URL:-}
+      THT_INTERNAL_QDRANT_URL: http://qdrant:6333
+      THT_INTERNAL_EMBEDDING_URL: http://embedding:11434
+      THT_INTERNAL_EMBEDDING_MODEL: qwen3-embedding:0.6b
+      THT_INTERNAL_EMBEDDING_DIMENSIONS: "1024"
       MAX_PI_PROCESSES: ${MAX_PI_PROCESSES:-4}
     extra_hosts:
       - "host.docker.internal:host-gateway"
@@ -59,6 +60,11 @@ services:
       retries: 5
       start_period: 30s
     restart: "no"
+    depends_on:
+      qdrant:
+        condition: service_healthy
+      embedding-model-init:
+        condition: service_completed_successfully
     networks: [thothii-net]
 
   frontend:
@@ -77,6 +83,60 @@ services:
     restart: "no"
     networks: [thothii-net]
 
+  qdrant:
+    image: qdrant/qdrant:v1.18.2@sha256:75eab8c4ba42096724fdcfde8b4de0b5713d529dde32f285a1f86fdcb2c9e50c
+    expose:
+      - "6333"
+    volumes:
+      - qdrant-data:/qdrant/storage
+    healthcheck:
+      test:
+        - CMD-SHELL
+        - >
+          /usr/bin/bash -lc "exec 3<>/dev/tcp/127.0.0.1/6333 &&
+          printf 'GET /healthz HTTP/1.1\r\nHost: 127.0.0.1\r\nConnection: close\r\n\r\n' >&3 &&
+          grep -q '200 OK' <&3"
+      interval: 15s
+      timeout: 3s
+      retries: 10
+      start_period: 10s
+    networks: [thothii-net]
+
+  embedding:
+    image: ollama/ollama:0.32.0@sha256:57f573b47f1f71ebb445789f279fe3e596a8beab182f7cf486db9205bad87c5a
+    command: ["serve"]
+    expose:
+      - "11434"
+    volumes:
+      - embedding-models:/root/.ollama
+    healthcheck:
+      test:
+        - CMD-SHELL
+        - >
+          /usr/bin/bash -lc "exec 3<>/dev/tcp/127.0.0.1/11434 &&
+          printf 'GET /api/tags HTTP/1.1\r\nHost: 127.0.0.1\r\nConnection: close\r\n\r\n' >&3 &&
+          grep -q '200 OK' <&3"
+      interval: 15s
+      timeout: 5s
+      retries: 20
+      start_period: 10s
+    networks: [thothii-net]
+
+  embedding-model-init:
+    image: ollama/ollama:0.32.0@sha256:57f573b47f1f71ebb445789f279fe3e596a8beab182f7cf486db9205bad87c5a
+    entrypoint: ["/usr/bin/bash", "/opt/thoth/embedding-model-init.sh"]
+    environment:
+      OLLAMA_BASE_URL: http://embedding:11434
+      OLLAMA_MODEL: qwen3-embedding:0.6b
+      OLLAMA_WAIT_TIMEOUT_SEC: "180"
+    volumes:
+      - embedding-models:/root/.ollama
+      - ./docker/embedding-model-init.sh:/opt/thoth/embedding-model-init.sh:ro
+    depends_on:
+      embedding:
+        condition: service_healthy
+    networks: [thothii-net]
+
 networks:
   thothii-net:
     driver: bridge
@@ -85,6 +145,8 @@ volumes:
   dev-data:
   dev-pi-state:
   workspace-registry:
+  qdrant-data:
+  embedding-models:
 
 secrets:
   thothii_secrets: