Create seed_supabase.py

seed_supabase.py

@@ -0,0 +1,35 @@
+import os
+from datasets import load_dataset
+from langchain.schema import Document
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import SupabaseVectorStore
+from supabase import create_client
+
+# 1. Load GAIA train split
+dataset = load_dataset("gaia-benchmark/GAIA", split="train")
+
+# 2. Build Documents: "Q: …\nA: …"
+docs = []
+for ex in dataset:
+    q, a = ex["question"], ex["answer"]
+    docs.append(Document(
+        page_content=f"Q: {q}\nA: {a}",
+        metadata={"task_id": ex.get("task_id"), "split": "train"}
+    ))
+
+# 3. Initialize embedding & Supabase client
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+supabase_url = os.environ["SUPABASE_URL"]
+supabase_key = os.environ["SUPABASE_SERVICE_KEY"]
+supabase = create_client(supabase_url, supabase_key)
+
+# 4. Upload to Supabase
+vectorstore = SupabaseVectorStore.from_documents(
+    docs,
+    embedding=embeddings,
+    client=supabase,
+    table_name="documents",
+    query_name="match_documents_langchain"
+)
+
+print(f"Seeded {len(docs)} GAIA examples into Supabase.")