Upload 3 files

.env

@@ -0,0 +1 @@
+HUGGINGFACEHUB_API_TOKEN = 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

app.py

@@ -0,0 +1,86 @@
+import streamlit as st
+from dotenv import load_dotenv
+from streamlit_extras.add_vertical_space import add_vertical_space
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+import pickle
+# from sentence_transformers import SentenceTransformer
+from langchain import HuggingFaceHub
+from langchain.chains.question_answering import load_qa_chain
+
+import os
+
+# model = SentenceTransformer('all-MiniLM-L6-v2')
+
+with st.sidebar:
+    st.title('LLM PDF Chats')
+    st.markdown('''
+                ## about
+                - This is LLM power chatbot
+                - By [Prathamesh Shete]('https://www.linkedin.com/in/prathameshshete')
+                
+                
+                ''')
+    add_vertical_space(5)
+    st.write('Made By Prathamesh')
+    
+load_dotenv()  
+def main():
+    st.header('Chat With PDF')
+    
+    pdf = st.file_uploader('Upload Your PDF',type='pdf')
+    
+    if pdf is not None:
+        pdf_reader = PdfReader(pdf)
+        # st.write(pdf_reader)
+
+        text = ''
+        for page in pdf_reader.pages:
+            text = page.extract_text()
+            
+            text_splitter = RecursiveCharacterTextSplitter(
+                chunk_size = 1000,
+                chunk_overlap = 200,
+                length_function = len
+            )
+            
+            chunks = text_splitter.split_text(text=text)
+            
+            # st.write(chunks)
+            
+            # embeddings
+            
+            store_name = pdf.name[:-4]
+            
+            if os.path.exists(f'{store_name}.pkl'):
+                with open(f'{store_name}.pkl','rb') as f:
+                    VectorStore = pickle.load(f)
+            else:
+                embeddings = HuggingFaceEmbeddings()
+                VectorStore = FAISS.from_texts(chunks,embedding=embeddings)
+                with open(f'{store_name}.pkl','wb') as f:
+                    pickle.dump(VectorStore,f)
+                    
+                    
+            # accept user query's
+            
+            ask_query = st.text_input('Ask question about PDF : ')
+            
+            
+            if ask_query:
+                docs = VectorStore.similarity_search(query=ask_query, k=3)
+                # st.write(docs)
+                llm = HuggingFaceHub(repo_id="google/flan-t5-xl", model_kwargs={"temperature": 0, "max_length": 64})
+                chain = load_qa_chain(llm=llm, chain_type='stuff')
+                response = chain.run(input_documents=docs, question=ask_query)
+                st.write(response)
+            # st.write(text)
+    
+    
+    
+    
+    
+if __name__ == "__main__":
+    main()

requirement.txt

@@ -0,0 +1,94 @@
+aiohttp==3.8.4
+aiosignal==1.3.1
+altair==5.0.1
+async-timeout==4.0.2
+attrs==23.1.0
+beautifulsoup4==4.12.2
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+contourpy==1.1.0
+cycler==0.11.0
+dataclasses-json==0.5.9
+decorator==5.1.1
+faiss-cpu==1.7.4
+Faker==18.11.2
+favicon==0.7.0
+fonttools==4.40.0
+frozenlist==1.3.3
+gitdb==4.0.10
+GitPython==3.1.31
+greenlet==2.0.2
+htbuilder==0.6.1
+idna==3.4
+importlib-metadata==6.7.0
+Jinja2==3.1.2
+jsonschema==4.17.3
+kiwisolver==1.4.4
+langchain==0.0.224
+langchainplus-sdk==0.0.20
+lxml==4.9.3
+Markdown==3.4.3
+markdown-it-py==3.0.0
+markdownlit==0.0.7
+MarkupSafe==2.1.3
+marshmallow==3.19.0
+marshmallow-enum==1.5.1
+matplotlib==3.7.1
+mdurl==0.1.2
+more-itertools==9.1.0
+multidict==6.0.4
+mypy-extensions==1.0.0
+numexpr==2.8.4
+numpy==1.25.0
+openapi-schema-pydantic==1.2.4
+packaging==23.1
+pandas==2.0.3
+Pillow==9.5.0
+protobuf==4.23.3
+pyarrow==12.0.1
+pydantic==1.10.11
+pydeck==0.8.1b0
+Pygments==2.15.1
+pymdown-extensions==10.0.1
+Pympler==1.0.1
+pyparsing==3.1.0
+PyPDF2==3.0.1
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+pytz==2023.3
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+requests==2.31.0
+rich==13.4.2
+six==1.16.0
+smmap==5.0.0
+soupsieve==2.4.1
+SQLAlchemy==2.0.17
+st-annotated-text==4.0.0
+streamlit==1.24.0
+streamlit-camera-input-live==0.2.0
+streamlit-card==0.0.61
+streamlit-embedcode==0.1.2
+streamlit-extras==0.2.7
+streamlit-faker==0.0.2
+streamlit-image-coordinates==0.1.5
+streamlit-keyup==0.2.0
+streamlit-toggle-switch==1.0.2
+streamlit-vertical-slider==1.0.2
+tenacity==8.2.2
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.2
+typing-inspect==0.9.0
+typing_extensions==4.7.1
+tzdata==2023.3
+tzlocal==4.3.1
+urllib3==2.0.3
+validators==0.20.0
+watchdog==3.0.0
+yarl==1.9.2
+zipp==3.15.0