Upload 4 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY = 'AIzaSyAAUSqm46KolD0515tMAsgJuCR_oPI-FKw'

faiss_store_openai.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
+size 0

main.py

@@ -0,0 +1,72 @@
+import os
+import streamlit as st
+import pickle
+import time
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import UnstructuredURLLoader
+import google.generativeai as palm
+from langchain.embeddings import GooglePalmEmbeddings
+from langchain.llms import GooglePalm
+from langchain.vectorstores import FAISS
+
+from dotenv import load_dotenv
+load_dotenv()  # take environment variables from .env (especially openai api key)
+
+st.title("RockyBot: News Research Tool 📈")
+st.sidebar.title("News Article URLs")
+
+urls = []
+for i in range(3):
+    url = st.sidebar.text_input(f"URL {i+1}")
+    urls.append(url)
+
+process_url_clicked = st.sidebar.button("Process URLs")
+file_path = "faiss_store_openai.pkl"
+
+main_placeholder = st.empty()
+llm = GooglePalm()
+
+if process_url_clicked:
+    # load data
+    loader = UnstructuredURLLoader(urls=urls)
+    main_placeholder.text("Data Loading...Started...✅✅✅")
+    data = loader.load()
+    # split data
+    text_splitter = RecursiveCharacterTextSplitter(
+        separators=['\n\n', '\n', '.', ','],
+        chunk_size=1000
+    )
+    main_placeholder.text("Text Splitter...Started...✅✅✅")
+    docs = text_splitter.split_documents(data)
+    # create embeddings and save it to FAISS index
+    embeddings = GooglePalmEmbeddings()
+    vectorstore_openai = FAISS.from_documents(docs, embeddings)
+    main_placeholder.text("Embedding Vector Started Building...✅✅✅")
+    time.sleep(2)
+
+    # Save the FAISS index to a pickle file
+    with open(file_path, "wb") as f:
+        pickle.dumps(vectorstore_openai, f)
+
+query = main_placeholder.text_input("Question: ")
+if query:
+    if os.path.exists(file_path):
+        with open(file_path, "rb") as f:
+            vectorstore = pickle.load(f)
+            chain = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=vectorstore.as_retriever())
+            result = chain({"question": query}, return_only_outputs=True)
+            # result will be a dictionary of this format --> {"answer": "", "sources": [] }
+            st.header("Answer")
+            st.write(result["answer"])
+
+            # Display sources, if available
+            sources = result.get("sources", "")
+            if sources:
+                st.subheader("Sources:")
+                sources_list = sources.split("\n")  # Split the sources by newline
+                for source in sources_list:
+                    st.write(source)
+
+
+

requirements.txt

@@ -0,0 +1,100 @@
+aiohttp==3.8.5
+aiosignal==1.3.1
+altair==5.1.2
+annotated-types==0.5.0
+anyio==3.7.1
+async-timeout==4.0.3
+attrs==23.1.0
+backports.zoneinfo==0.2.1
+beautifulsoup4==4.12.2
+blinker==1.6.2
+cachetools==5.3.1
+certifi==2023.7.22
+chardet==5.2.0
+charset-normalizer==3.3.0
+click==8.1.7
+dataclasses-json==0.6.1
+emoji==2.8.0
+exceptiongroup==1.1.3
+faiss-cpu==1.7.4
+filetype==1.2.0
+frozenlist==1.4.0
+gitdb==4.0.10
+GitPython==3.1.37
+google-ai-generativelanguage==0.1.0
+google-api-core==2.12.0
+google-auth==2.23.2
+google-generativeai==0.1.0rc1
+googleapis-common-protos==1.60.0
+greenlet==3.0.0
+grpcio==1.59.0
+grpcio-status==1.59.0
+idna==3.4
+importlib-metadata==6.8.0
+importlib-resources==6.1.0
+Jinja2==3.1.2
+joblib==1.3.2
+jsonpatch==1.33
+jsonpointer==2.4
+jsonschema==4.19.1
+jsonschema-specifications==2023.7.1
+langchain==0.0.309
+langdetect==1.0.9
+langsmith==0.0.42
+lxml==4.9.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.3
+marshmallow==3.20.1
+mdurl==0.1.2
+multidict==6.0.4
+mypy-extensions==1.0.0
+nltk==3.8.1
+numpy==1.24.4
+packaging==23.2
+pandas==2.0.3
+pickle5==0.0.11
+Pillow==10.0.1
+pkgutil_resolve_name==1.3.10
+proto-plus==1.22.3
+protobuf==4.24.4
+pyarrow==13.0.0
+pyasn1==0.5.0
+pyasn1-modules==0.3.0
+pydantic==2.4.2
+pydantic_core==2.10.1
+pydeck==0.8.1b0
+Pygments==2.16.1
+python-dateutil==2.8.2
+python-dotenv==1.0.0
+python-iso639==2023.6.15
+python-magic==0.4.27
+pytz==2023.3.post1
+PyYAML==6.0.1
+referencing==0.30.2
+regex==2023.10.3
+requests==2.31.0
+rich==13.6.0
+rpds-py==0.10.4
+rsa==4.9
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+SQLAlchemy==2.0.21
+streamlit==1.27.2
+tabulate==0.9.0
+tenacity==8.2.3
+toml==0.10.2
+toolz==0.12.0
+tornado==6.3.3
+tqdm==4.66.1
+typing-inspect==0.9.0
+typing_extensions==4.8.0
+tzdata==2023.3
+tzlocal==5.1
+unstructured==0.10.19
+urllib3==2.0.6
+validators==0.22.0
+watchdog==3.0.0
+yarl==1.9.2
+zipp==3.17.0