Update embed_index.py

embed_index.py

@@ -1 +1,63 @@
-#
+import json
+import os
+import faiss
+import numpy as np
+from sentence_transformers import SentenceTransformer
+
+from config.settings import *
+
+CONDITIONS_DIR = "Conditions"
+INDEX_DIR = "index"
+
+def load_chunks():
+    texts = []
+    metadatas = []
+
+    for condition in os.listdir(CONDITIONS_DIR):
+        cond_path = os.path.join(CONDITIONS_DIR, condition)
+        if not os.path.isdir(cond_path):
+            continue
+
+        chunks_path = os.path.join(cond_path, "chunks.json")
+        if not os.path.exists(chunks_path):
+            continue
+
+        with open(chunks_path, "r", encoding="utf-8") as f:
+            chunks = json.load(f)
+
+        for chunk in chunks:
+            texts.append(chunk["text"])
+            metadatas.append({
+                "condition": chunk["condition"],
+                "section": chunk["section"],
+                "source_id": chunk["source_id"]
+            })
+
+    return texts, metadatas
+
+
+def main():
+    print("Loading embedding model...")
+    model = SentenceTransformer(EMBEDDING_MODEL)
+
+    texts, metadatas = load_chunks()
+    print(f"Loaded {len(texts)} chunks")
+
+    embeddings = model.encode(texts, show_progress_bar=True)
+    embeddings = np.array(embeddings).astype("float32")
+
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+
+    os.makedirs(INDEX_DIR, exist_ok=True)
+
+    faiss.write_index(index, FAISS_INDEX_PATH)
+
+    with open(METADATA_PATH, "w", encoding="utf-8") as f:
+        json.dump(metadatas, f, indent=2)
+
+    print("FAISS index built successfully")
+
+
+if __name__ == "__main__":
+    main()