RAG - Maestro (Now Live!)
RAG-Maestro is an up-to-date LLM assistant designed to provide clear and concise explanations of scientific concepts and relevant papers. As a Q&A bot, it does not keep track of your conversation and will treat each input independently.
RAG-Maestro is now Live!
Examples
| What is LLava? | Do you know what the Memformer is? |
|---|---|
 |
 |
Implementation Details
The bot is composed of three building blocks that work sequentially:
A Keywords extractor
RAG-Maestro first tasks is to extract from your request the keywords to browse for. the RAKE (Rapid Keyword Extraction Algorithm) from nltk is used.
A Paper browser
Once the keywords extracted, they are used to retrieve the 5 most relevant papers from arxiv.org. These papers are then downloaded and scrapped.
To build the scraper, I used the open-source arxiv API and PyPDF2 to ease the pdf reading.
A RAG Pipeline (Paper)
That retrieves the most relevant information from the scraped papers relatively to the query, and takes it as context to summarize. One of the main features I implemented (prompt engineering) is that the bot is citing its sources. Hence, it becomes possible to assess the veracity of the provided answer. The pipeline is using OpenAI LLMS (embedding-v3 and gpt-3.5-turbo) to process the retrieval and the generation steps. Like every LLM, RAG-Maestro can be subject to hallucinations. Making it citing the sources can help us to detect a hallucination.
I used llama_index to build the RAG pipeline, specifically picked a "tree_summarizer" form query engine to generate the answer. All the hyperparameters are stored in an editable config.yml file.
Commands
Running the app locally from this repository
- clone this repository
- Create a new Python environment provided with pip
- run
pip install -r requirements.txt - run
streamlit run src/app.py - Now open the 'External URL' in your browser. Enjoy the bot.
