Create ingest.py

ingest.py

@@ -0,0 +1,30 @@
+import streamlit as st
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma
+from constants import CHROMA_SETTINGS
+persist_directory = "db"
+
+
+def main():
+    st.title("PDF Processor")
+    uploaded_file = st.file_uploader("Upload a PDF file")
+    if uploaded_file is not None:
+        st.write("Processing PDF...")
+        loader = PyPDFLoader(uploaded_file.read())
+        documents = loader.load()
+        st.write("Splitting into chunks")
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+        texts = text_splitter.split_documents(documents)
+        st.write("Loading sentence transformers model")
+        embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
+        st.write("Creating embeddings. This may take some time...")
+        db = Chroma.from_documents(texts, embeddings, persist_directory=persist_directory, client_settings=CHROMA_SETTINGS)
+        db.persist()
+        db = None
+        st.success("Ingestion complete! You can now run privateGPT.py to query your documents")
+
+
+if __name__ == "__main__":
+    main()