Create upload_pdf.py

upload_pdf.py

@@ -0,0 +1,41 @@
+import chromadb
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from uuid import uuid4
+
+
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size=800,
+    chunk_overlap=50
+)
+client = chromadb.PersistentClient("test")
+collection = client.create_collection("test_data")
+
+def upload_pdf(file_path):
+    loader = PyPDFLoader(file_path)
+    pages = loader.load()
+    documents = []
+    for page in pages:
+        docs = text_splitter.split_text(page.page_content)
+        for doc in docs:
+            documents.append({
+                "text": docs, "meta_data": page.metadata,
+            })
+    collection.add(
+        ids=[str(uuid4()) for _ in range(len(documents))],
+        documents=[doc['text'][0] for doc in documents],
+        metadatas=[doc['meta_data'] for doc in documents]
+    )
+    return f"PDF Uploaded Successfully. {collection.count()} chunks stored in ChromaDB"
+
+# Define the Gradio interface
+iface = gr.Interface(
+    fn=upload_pdf,
+    inputs=["file"],  # Specify a file input component
+    outputs="textbox",  # Display the output text in a textbox
+    title="Upload PDF to ChromaDB",
+    description="Upload a PDF file and store its text chunks in ChromaDB.",
+)
+
+# Launch the Gradio app
+iface.launch(debug=True,share=True)