Update ingest.py

ingest.py

@@ -1 +1,26 @@
-import os
    texts,
    embeddings,
    url=url,
    prefer_grpc=False,
    collection_name="vector_db"
+import os
+from langchain_community.embeddings import SentenceTransformerEmbeddings
+from langchain_community.document_loaders import UnstructuredFileLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Qdrant
+
+embeddings = SentenceTransformerEmbeddings(model_name="NeuML/pubmedbert-base-embeddings")
+
+
+loader = DirectoryLoader('data/', glob="**/*.pdf", show_progress=True, loader_cls=UnstructuredFileLoader)
+documents = loader.load()
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=700, chunk_overlap=70)
+texts = text_splitter.split_documents(documents)
+
+url = "http://0.0.0.0:6333" # This is the same URL that must match Step 4d
+qdrant = Qdrant.from_documents(
+    texts,
+    embeddings,
+    url=url,
+    prefer_grpc=False,
+    collection_name="vector_db"
+)
+
+print("Vector DB Successfully Created!")
+