modified: app.py

app.py

@@ -1,26 +1,27 @@
 import gradio as gr
-import yaml, json, uuid, os
+import json
+import uuid
 from pathlib import Path
 from src.reader import read_file
 from src.chunker import chunk_text
 from src.embeddings import embed_texts
 
 def run_pipeline(files, vertical, language):
-    recs = []
+    records = []
     for file_path in files:
         meta, body = read_file(Path(file_path))
         base_meta = {"vertical": vertical, "language": language, "source": Path(file_path).name, **meta}
         chunks = chunk_text(body)
-        vecs = embed_texts(chunks)
-        for i, (chunk, vec) in enumerate(zip(chunks, vecs), 1):
-            recs.append({
+        vectors = embed_texts(chunks)
+        for i, (chunk, vec) in enumerate(zip(chunks, vectors), 1):
+            records.append({
                 "id": f"{Path(file_path).stem}-chunk-{i:04d}",
                 "vector": vec,
                 "metadata": {**base_meta, "chunk_index": i}
             })
     out_path = f"/tmp/{uuid.uuid4().hex}.jsonl"
     with open(out_path, "w", encoding="utf-8") as f:
-        for r in recs:
+        for r in records:
             json.dump(r, f, ensure_ascii=False)
             f.write("\n")
     return out_path