How dharun-cohere/rag_for_complex_data works
This is a single-script financial-document RAG prototype. Its implemented workflow parses the NVIDIA PDF into Markdown, chunks and indexes the content, retrieves and reranks relevant passages, then generates and prints an answer to a hard-coded question. The README describes broader analysis use cases, but the shown runtime does not implement separate forecasting, risk, or investment workflows. Edges reflect calls and data transfers visible in app.py; the vector store is configured as a local Qdrant database.
Main entry points: app.py RAG workflow · NVIDIAAn.pdf NVIDIA PDF · parsed_document.md Parsed Markdown
Components 14
Document ingestion
- RAG workflow
app.py - NVIDIA PDF
NVIDIAAn.pdf - PDF parser
app.py - Parsed Markdown
data/parsed_document.md - Markdown loader
app.py - Text splitter
app.py - Embedding encoder
app.py
Search and retrieval
- Qdrant index
app.py - Top-k retriever
app.py - Passage reranker
app.py
Answer generation
- Retrieval QA
app.py - Groq language model
- Sample question
app.py - Printed answer
app.py
Connections 19
- RAG workflow → NVIDIA PDF: parses
app.py - RAG workflow → PDF parser: calls
app.py - PDF parser → NVIDIA PDF: reads
app.py - RAG workflow → Parsed Markdown: writes
app.py - RAG workflow → Markdown loader: loads
app.py - Markdown loader → Parsed Markdown: reads
app.py - RAG workflow → Text splitter: chunks
app.py - RAG workflow → Embedding encoder: creates
app.py - RAG workflow → Qdrant index: indexes
app.py - RAG workflow → Top-k retriever: configures
app.py - RAG workflow → Passage reranker: configures
app.py - RAG workflow → Retrieval QA: builds and invokes
app.py - Retrieval QA → Top-k retriever: retrieves passages
app.py - Top-k retriever → Qdrant index: searches
app.py - Retrieval QA → Passage reranker: reranks passages
app.py - RAG workflow → Groq language model: configures
app.py - Retrieval QA → Groq language model: generates answer
app.py - RAG workflow → Sample question: submits
app.py - RAG workflow → Printed answer: prints response
app.py