giving user ability to upload PDF

app.py

@@ -1,4 +1,5 @@
 import gradio as gr
+from gradio_pdf import PDF
 from qdrant_client import models, QdrantClient
 from sentence_transformers import SentenceTransformer
 from PyPDF2 import PdfReader
@@ -45,7 +46,75 @@ llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF",
 print("LLM loaded........................................")
 print("################################################################")
 
-def get_chunks(text):
+# def get_chunks(text):
+# text_splitter = RecursiveCharacterTextSplitter(
+# # seperator = "\n",
+# chunk_size = 250,
+# chunk_overlap = 50,
+# length_function = len,
+# )
+
+# chunks = text_splitter.split_text(text)
+# return chunks
+
+
+# pdf_path = './100 Weird Facts About the Human Body.pdf'
+
+
+# reader = PdfReader(pdf_path)
+# text = ""
+# num_of_pages = len(reader.pages)
+
+# for page in range(num_of_pages):
+# current_page = reader.pages[page]
+# text += current_page.extract_text()
+
+
+# chunks = get_chunks(text)
+# print(chunks)
+# print("Chunks are ready.....................................")
+# print("######################################################")
+
+# client = QdrantClient(path = "./db")
+# print("db created................................................")
+# print("#####################################################################")
+
+# client.recreate_collection(
+# collection_name="my_facts",
+# vectors_config=models.VectorParams(
+# size=encoder.get_sentence_embedding_dimension(), # Vector size is defined by used model
+# distance=models.Distance.COSINE,
+# ),
+# )
+
+# print("Collection created........................................")
+# print("#########################################################")
+
+
+
+# li = []
+# for i in range(len(chunks)):
+# li.append(i)
+ 
+# dic = zip(li, chunks)
+# dic= dict(dic)
+
+# client.upload_records(
+# collection_name="my_facts",
+# records=[
+# models.Record(
+# id=idx,
+# vector=encoder.encode(dic[idx]).tolist(),
+# payload= {dic[idx][:5] : dic[idx]}
+# ) for idx in dic.keys()
+# ],
+# )
+
+# print("Records uploaded........................................")
+# print("###########################################################")
+
+def chat(file, question):
+ def get_chunks(text):
  text_splitter = RecursiveCharacterTextSplitter(
  # seperator = "\n",
  chunk_size = 250,
@@ -57,62 +126,61 @@ def get_chunks(text):
  return chunks
 
 
-pdf_path = './100 Weird Facts About the Human Body.pdf'
+ pdf_path = './100 Weird Facts About the Human Body.pdf'
 
 
-reader = PdfReader(pdf_path)
-text = ""
-num_of_pages = len(reader.pages)
+ reader = PdfReader(pdf_path)
+ text = ""
+ num_of_pages = len(reader.pages)
 
-for page in range(num_of_pages):
- current_page = reader.pages[page]
- text += current_page.extract_text()
+ for page in range(num_of_pages):
+ current_page = reader.pages[page]
+ text += current_page.extract_text()
 
 
-chunks = get_chunks(text)
-print(chunks)
-print("Chunks are ready.....................................")
-print("######################################################")
+ chunks = get_chunks(text)
+ # print(chunks)
+# print("Chunks are ready.....................................")
+# print("######################################################")
 
-client = QdrantClient(path = "./db")
-print("db created................................................")
-print("#####################################################################")
+ client = QdrantClient(path = "./db")
+# print("db created................................................")
+# print("#####################################################################")
 
-client.recreate_collection(
- collection_name="my_facts",
- vectors_config=models.VectorParams(
- size=encoder.get_sentence_embedding_dimension(), # Vector size is defined by used model
- distance=models.Distance.COSINE,
- ),
-)
+ client.recreate_collection(
+ collection_name="my_facts",
+ vectors_config=models.VectorParams(
+ size=encoder.get_sentence_embedding_dimension(), # Vector size is defined by used model
+ distance=models.Distance.COSINE,
+ ),
+ )
 
-print("Collection created........................................")
-print("#########################################################")
+# print("Collection created........................................")
+# print("#########################################################")
 
 
 
-li = []
-for i in range(len(chunks)):
- li.append(i)
+ li = []
+ for i in range(len(chunks)):
+ li.append(i)
  
-dic = zip(li, chunks)
-dic= dict(dic)
-
-client.upload_records(
- collection_name="my_facts",
- records=[
- models.Record(
- id=idx,
- vector=encoder.encode(dic[idx]).tolist(),
- payload= {dic[idx][:5] : dic[idx]}
- ) for idx in dic.keys()
- ],
-)
+ dic = zip(li, chunks)
+ dic= dict(dic)
+
+ client.upload_records(
+ collection_name="my_facts",
+ records=[
+ models.Record(
+ id=idx,
+ vector=encoder.encode(dic[idx]).tolist(),
+ payload= {dic[idx][:5] : dic[idx]}
+ ) for idx in dic.keys()
+ ],
+ )
 
-print("Records uploaded........................................")
-print("###########################################################")
+# print("Records uploaded........................................")
+# print("###########################################################")
 
-def chat(question):
 
  hits = client.search(
  collection_name="my_facts",
@@ -148,7 +216,7 @@ def chat(question):
 
 screen = gr.Interface(
  fn = chat,
- inputs = gr.Textbox(lines = 10, placeholder = "Enter your question here 👉"),
+ inputs = [PDF(label="Upload a PDF", interactive=True), gr.Textbox(lines = 10, placeholder = "Enter your question here 👉")],
  outputs = gr.Textbox(lines = 10, placeholder = "Your answer will be here soon 🚀"),
  title="Q&A with PDF 👩🏻‍💻📓✍🏻💡",
 description="This app facilitates a conversation with PDFs available on https://www.delo.si/assets/media/other/20110728/100%20Weird%20Facts%20About%20the%20Human%20Body.pdf💡",