Upload 3 files

src/helper.py

@@ -0,0 +1,30 @@
+from langchain.document_loaders import PyPDFLoader, DirectoryLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+
+
+# Extract data from the PDF
+def load_pdf(data):
+    loader = DirectoryLoader(data,
+                             glob="*.pdf",
+                             loader_cls=PyPDFLoader)
+
+    documents = loader.load()
+
+    return documents
+
+
+# Create text chunks
+def text_split(extracted_data):
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500, chunk_overlap=20)
+    text_chunks = text_splitter.split_documents(extracted_data)
+
+    return text_chunks
+
+
+# download embedding model
+def download_hugging_face_embeddings():
+    embeddings = HuggingFaceEmbeddings(
+        model_name='sentence-transformers/all-MiniLM-L6-v2')
+    return embeddings

src/prompt.py

@@ -0,0 +1,12 @@
+
+
+prompt_template = """
+Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
+"""