# srinikraman/rag-llama_index-pinecone architecture

> Architecture diagram of the GitHub repository srinikraman/rag-llama_index-pinecone, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/srinikraman/rag-llama_index-pinecone
- Repository: https://github.com/srinikraman/rag-llama_index-pinecone

## Overview

This is a compact command-line RAG application. On startup, main.py loads PDFs, configures OpenAI models, ensures a dimension-compatible Pinecone index, and builds a vector index. It then accepts questions, queries the index with hybrid top-6 retrieval and a context-restricted prompt, and prints answers. The README documents these capabilities; implementation details are concentrated in main.py, so the graph keeps stages distinct without implying separate modules. Edges are supported by the main.py excerpt or explicit README statements.

Main entry points: [`main.py`](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py) (Vector index builder), [`input`](https://github.com/srinikraman/rag-llama_index-pinecone/tree/main/input) (PDF documents)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ingestion["PDF ingestion"]
  node_pdfs["PDF documents"]
  node_loader["PDF loader<br/>[main.py]"]
  node_documents["Document objects<br/>[main.py]"]
end

subgraph group_indexing["Index and storage"]
  node_index_manager["Index management<br/>[main.py]"]
  node_pinecone[("Pinecone vector DB")]
  node_vector_index["Vector index builder<br/>[main.py]"]
  node_embedder["OpenAI embeddings<br/>[main.py]"]
end

subgraph group_query["Query and response"]
  node_query_loop["Interactive query loop<br/>[main.py]"]
  node_retriever["Hybrid retriever<br/>[main.py]"]
  node_prompt["Context-only prompt<br/>[main.py]"]
  node_llm["OpenAI answer model<br/>[main.py]"]
  node_answer["Printed answer<br/>[main.py]"]
end

node_operator(("CLI user"))

node_pdfs -->|"loads from"| node_loader
node_loader -->|"produces"| node_documents
node_documents -->|"indexes"| node_vector_index
node_index_manager -->|"checks and configures"| node_pinecone
node_vector_index -->|"stores vectors"| node_pinecone
node_vector_index -->|"embeds documents"| node_embedder
node_operator -->|"enters question"| node_query_loop
node_query_loop -->|"queries index"| node_retriever
node_retriever -->|"searches vectors"| node_pinecone
node_retriever -->|"provides context"| node_llm
node_prompt -->|"constrains answer"| node_llm
node_llm -->|"generates"| node_answer
node_query_loop -->|"prints"| node_answer

click node_pdfs "https://github.com/srinikraman/rag-llama_index-pinecone/tree/main/input"
click node_loader "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_documents "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_index_manager "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_vector_index "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_embedder "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_query_loop "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_retriever "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_prompt "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_llm "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"
click node_answer "https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_pdfs,node_loader,node_documents,node_operator toneBlue
class node_index_manager,node_pinecone,node_vector_index,node_embedder toneAmber
class node_query_loop,node_retriever,node_prompt,node_llm,node_answer toneMint
```

## Components

### PDF ingestion

- [PDF documents](https://github.com/srinikraman/rag-llama_index-pinecone/tree/main/input): `input`
- [PDF loader](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [Document objects](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`

### Index and storage

- [Index management](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- **Pinecone vector DB**
- [Vector index builder](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [OpenAI embeddings](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`

### Query and response

- [Interactive query loop](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [Hybrid retriever](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [Context-only prompt](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [OpenAI answer model](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`
- [Printed answer](https://github.com/srinikraman/rag-llama_index-pinecone/blob/main/main.py): `main.py`

### Other components

- **CLI user**

## Connections

- PDF documents → PDF loader: loads from (evidence: `main.py`)
- PDF loader → Document objects: produces (evidence: `main.py`)
- Document objects → Vector index builder: indexes (evidence: `main.py`)
- Index management → Pinecone vector DB: checks and configures (evidence: `main.py`)
- Vector index builder → Pinecone vector DB: stores vectors (evidence: `main.py`)
- Vector index builder → OpenAI embeddings: embeds documents (evidence: `README.md`)
- CLI user → Interactive query loop: enters question (evidence: `main.py`)
- Interactive query loop → Hybrid retriever: queries index (evidence: `main.py`)
- Hybrid retriever → Pinecone vector DB: searches vectors (evidence: `README.md`)
- Hybrid retriever → OpenAI answer model: provides context (evidence: `README.md`)
- Context-only prompt → OpenAI answer model: constrains answer (evidence: `main.py`)
- OpenAI answer model → Printed answer: generates (evidence: `main.py`)
- Interactive query loop → Printed answer: prints (evidence: `main.py`)
