Upload backend/main.py

backend/main.py

@@ -0,0 +1,28 @@
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from dotenv import load_dotenv
+
+load_dotenv()
+
+def ingest_pdf(pdf_path: str):
+    loader = PyPDFLoader(pdf_path)
+    documents = loader.load()
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500,
+        chunk_overlap=50
+    )
+    chunks = splitter.split_documents(documents)
+    embeddings = HuggingFaceEmbeddings(
+        model_name="all-MiniLM-L6-v2"
+    )
+    vectorstore = Chroma.from_documents(
+        chunks,
+        embeddings,
+        persist_directory="chroma_db"
+    )
+    print(f"✅ Ingested {len(chunks)} chunks from {pdf_path}")
+
+if __name__ == "__main__":
+    ingest_pdf("../docs/test.pdf")