fix(preprocess): harden S3 and real Compose jobs

2026-07-12 06:01:06 +02:00
parent 950f88f23e
commit c6966f3d15
10 changed files with 222 additions and 43 deletions
@@ -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}