Migrate to pgvector — remove ChromaDB from api.py, ingest scripts, dream.py

scripts/ingest_claude.py

@@ -2,7 +2,9 @@ import json
 import sys
 from pathlib import Path
 from sentence_transformers import SentenceTransformer
-import chromadb
+import psycopg2
+import psycopg2.extras
+import json as json_module
 
 # Paths
 db_path = str(Path.home() / "aaronai" / "db")
@@ -102,12 +104,26 @@ def ingest_conversations(path):
             continue
 
         embeddings = embedder.encode([n[1] for n in new]).tolist()
-        collection.upsert(
-            ids=[n[0] for n in new],
-            documents=[n[1] for n in new],
-            metadatas=[n[2] for n in new],
-            embeddings=embeddings,
-        )
+        pg = get_pg()
+        cur = pg.cursor()
+        for (chunk_id, chunk_text, meta), embedding in zip(new, embeddings):
+            cur.execute("""
+                INSERT INTO embeddings (id, document, embedding, source, type, created_at, metadata)
+                VALUES (%s, %s, %s::vector, %s, %s, %s, %s)
+                ON CONFLICT (id) DO UPDATE SET
+                    document = EXCLUDED.document,
+                    embedding = EXCLUDED.embedding,
+                    source = EXCLUDED.source,
+                    type = EXCLUDED.type,
+                    created_at = EXCLUDED.created_at,
+                    metadata = EXCLUDED.metadata
+            """, (
+                chunk_id, chunk_text, embedding,
+                meta.get('source'), meta.get('type'), meta.get('created_at'),
+                json_module.dumps(meta)
+            ))
+        pg.commit()
+        pg.close()
         total += len(new)
 
     print(f"Conversations: {total} chunks added, {skipped} skipped")