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.
| What is LLava? | Do you know what the Memformer is? |
|---|---|
 |
 |
The bot is composed of three building blocks that work sequentially:
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.
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.
- 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.
