Upload 5 files

.env

@@ -0,0 +1 @@
+OPENAI_API_KEY='enter your openapi key here'

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+FinSight.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,11 +1,17 @@
----
-title: FinSight
-emoji: 🏃
-colorFrom: pink
-colorTo: pink
-sdk: docker
-pinned: false
-short_description: FinSight Finance News Research Tool
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# FinSight- Finance News Research Tool
+FinSight is  user-friendly news research tool designed for effortless information retrieval. Users can input article URLs and ask questions to receive relevant insights from the stock market and financial domain.
+
+![](FinSight.jpg)
+
+## Features
+
+- Load URLs or upload text files containing URLs to fetch article content.
+- Process article content through LangChain's UnstructuredURL Loader
+- Construct an embedding vector using OpenAI's embeddings and leverage FAISS, a powerful similarity search library, to enable swift and effective retrieval of relevant information
+- Interact with the LLM's (Chatgpt) by inputting queries and receiving answers along with source URLs.
+
+## Project Structure
+
+- main.py: The main Streamlit application script.
+- requirements.txt: A list of required Python packages for the project.
+- .env: Configuration file for storing your OpenAI API key.

main.py

@@ -0,0 +1,72 @@
+import os
+import streamlit as st
+import pickle
+import time
+from langchain import OpenAI
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.document_loaders import UnstructuredURLLoader
+from langchain.embeddings import OpenAIEmbeddings
+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 = OpenAI(temperature=0.9, max_tokens=500)
+
+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 = OpenAIEmbeddings()
+    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.dump(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 +1,10 @@
+langchain==0.0.284
+python-dotenv==1.0.0
+streamlit==1.22.0
+unstructured==0.9.2
+tiktoken==0.4.0
+faiss-cpu==1.7.4
+libmagic==1.0
+python-magic==0.4.27
+python-magic-bin==0.4.14
+OpenAI == 0.28.0