Stock Trend Analyzer 📈

This project is a web-based research tool that leverages Large Language Models (LLMs) to analyze and answer questions about financial news articles. Built with Streamlit and LangChain, it allows users to input multiple URLs and perform conversational Q&A to extract key insights, summaries, and sentiment from the provided text.

This version is configured to run entirely on your local machine using Ollama and a small, efficient language model, making it completely free to use without needing any API keys.

📸 Screenshot

✨ Features

• Analyze Multiple Sources: Input up to three news article URLs for analysis.
• Conversational Q&A: Ask questions in natural language to get insights from the articles.
• Local & Private: Runs entirely on your local machine using Ollama, ensuring your data remains private.
• No API Keys Needed: Completely free to run, with no dependency on paid services like OpenAI.
• Simple UI: A clean and user-friendly web interface powered by Streamlit.

🛠️ Tech Stack

• Python
• Streamlit: For the web application interface.
• LangChain: The core framework for building LLM-powered applications.
• Ollama: For running open-source LLMs locally.
• FAISS: For efficient similarity search in the vector store.
• Transformers: For tokenization with local models.

⚙️ Setup and Installation

Follow these steps to get the project running on your local machine.

1. Clone the Repository

git clone https://github.com/JyotsnaGuntha/Stock_Trend_Analyzer.git
cd Stock_Trend_Analyzer

2. Install Dependencies

Make sure you have a requirements.txt file with the following content:

streamlit
langchain
langchain-openai
langchain-community
python-dotenv
unstructured
faiss-cpu
tiktoken
transformers

Then, install all the required packages:

pip install -r requirements.txt

3. Set Up Ollama

This project uses Ollama to run a language model locally.

• Download and install Ollama from the official website: https://ollama.com/
• Download the model: Open your terminal and run the following command to download tinyllama, a small model suitable for most computers.

  ollama run tinyllama

  This will start the Ollama server and make the model available for the application.

🚀 How to Run the Application

1. Ensure Ollama is Running: Make sure the Ollama application or background service is active.

2. Start the Streamlit App: Open a terminal in the project directory and run:

   streamlit run app.py

3. Use the App:

   • Your browser will open with the application running.
   • Enter the URLs of the news articles you want to analyze in the sidebar.
   • Click the "Process URLs" button.
   • Once the processing is complete, ask your questions in the main input box to get insights!