news research tool that processes and analyzes news articles from given URLs. It leverages LangChain, Cohere embeddings, and Streamlit to provide insights and answers based on the content of the articles.
FinGuru is a news research tool that processes and analyzes news articles from given URLs and PDF. It leverages LangChain, Google embeddings, and Streamlit to provide insights and answers based on the content of the articles.
google gemini-pro
- Issue 1 : Copy pasting article in ChatGPt is tedious
- Issue 2 : We need an aggregate knowledge base
Semantic search
Wikipedia
Google Search
Google Finance
duckduckGo search
git clone https://github.com/mihirh19/news_research_tool_Equity-Research-Analysis-.git
cd news_research_tool_Equity-Research-Analysis-
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt
First, you need to set up the proper API keys and environment variables. To set it up, create the GOOGLE_API_KEY in the Google Cloud credential console (https://console.cloud.google.com/apis/credentials) and a GOOGLE_CSE_ID using the Programmable Search Engine (https://programmablesearchengine.google.com/controlpanel/create). Next, it is good to follow the instructions found here.
create api key on https://serpapi.com/
secrets.toml
in the .streamlit
directory with the following content:GOOGLE_API_KEY = "your-google-api-key"
GOOGLE_CSE_ID = "your-cse-id"
SERP_API_KEY ="your-"
streamlit run app.py
what is the target price of tata motors ?
and click Submit
to get the answer.AnnualReport202223.pdf Upload the Given PDF
Click "Process PDF" to start processing.
Enter a query like what is the yoy change of revenue of tata motors ?
and click Submit
to get answer.
👤 Mihir Hadavani
Give a ⭐️ if this project helped you!