fix(preprocess): harden S3 and real Compose jobs

This commit is contained in:
2026-07-12 06:01:06 +02:00
parent 950f88f23e
commit c6966f3d15
10 changed files with 222 additions and 43 deletions
+16 -4
View File
@@ -5,10 +5,14 @@ services:
build:
context: .
dockerfile: docker/core.Dockerfile
entrypoint: [/app/docker/core-entrypoint.sh, preprocess]
command: [evidence, --json, -c, "/app/harness/workspaces/${THT_PREPROCESS_WORKSPACE:-tht.example}.yaml"]
entrypoint: [sh, -ec]
command: ["mkdir -p /data/workspaces/preprocess-evidence && exec /app/docker/core-entrypoint.sh preprocess evidence --json -c /app/harness/workspaces/preprocess-evidence.yaml"]
environment:
THT_DATA_ROOT: /data
THT_OLLAMA_URL: "${THT_OLLAMA_URL:-http://host.docker.internal:11434}"
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
THT_VECTOR_WRITER_PASSWORD_FILE: /run/secrets/vector_writer_password
secrets: [vector_reader_password, vector_writer_password]
volumes:
- thoth_data:/data
- ./deploy/workspaces:/app/harness/workspaces:ro
@@ -20,11 +24,19 @@ services:
build:
context: .
dockerfile: docker/core.Dockerfile
entrypoint: [/app/docker/core-entrypoint.sh, preprocess]
command: [dwh, --json, -c, "/app/harness/workspaces/${THT_PREPROCESS_WORKSPACE:-tht.example}.yaml"]
entrypoint: [sh, -ec]
command: ["mkdir -p /data/workspaces/preprocess-dwh && exec /app/docker/core-entrypoint.sh preprocess dwh --steps introspect --json -c /app/harness/workspaces/preprocess-dwh.yaml"]
environment:
THT_DATA_ROOT: /data
THT_VECTOR_READER_PASSWORD_FILE: /run/secrets/vector_reader_password
secrets: [vector_reader_password]
volumes:
- thoth_data:/data
- ./deploy/workspaces:/app/harness/workspaces:ro
restart: "no"
secrets:
vector_reader_password:
file: ${THT_VECTOR_READER_PASSWORD_SECRET_FILE:?set THT_VECTOR_READER_PASSWORD_SECRET_FILE}
vector_writer_password:
file: ${THT_VECTOR_WRITER_PASSWORD_SECRET_FILE:?set THT_VECTOR_WRITER_PASSWORD_SECRET_FILE}
+7
View File
@@ -0,0 +1,7 @@
language: en
dwh:
type: postgres_direct
connection:
{host: vector-db, database: thoth, schema: vectors, user: thoth_vector_reader,
password_file: "${THT_VECTOR_READER_PASSWORD_FILE}"}
roots: {artifacts: artifacts, indexes: indexes, sessions: sessions}
@@ -0,0 +1,15 @@
language: en
dwh:
type: postgres_direct
connection: {host: unused, database: unused, schema: public, user: unused, password: unused}
vectors:
type: pgvector_direct
reader:
{host: vector-db, database: thoth, schema: vectors, user: thoth_vector_reader,
password_file: "${THT_VECTOR_READER_PASSWORD_FILE}"}
writer:
{host: vector-db, database: thoth, schema: vectors, user: thoth_vector_writer,
password_file: "${THT_VECTOR_WRITER_PASSWORD_FILE}"}
roots: {artifacts: artifacts, indexes: indexes, sessions: sessions}
evidence: {source_root: /data/source, evidence_dir: evidence}
embeddings: {base_url: "${THT_OLLAMA_URL}", model: smoke, dim: 768, batch_size: 32}