Create transcript_handler.py

transcript_handler.py

@@ -0,0 +1,19 @@
+import faiss
+import numpy as np
+
+def chunk_text(text, chunk_size=300, overlap=50):
+    words = text.split()
+    chunks = []
+    for i in range(0, len(words), chunk_size - overlap):
+        chunk = ' '.join(words[i:i+chunk_size])
+        chunks.append(chunk)
+    return chunks
+
+def embed_chunks(chunks, embedder):
+    embeddings = embedder.encode(chunks)
+    return np.array(embeddings), chunks
+
+def create_faiss_index(embeddings):
+    index = faiss.IndexFlatL2(embeddings.shape[1])
+    index.add(embeddings)
+    return index