Chat with GitHub specifications using RAG search
Workflow Description
An intelligent conversation automation that connects OpenAI's language model to a Pinecone vector database to answer questions about GitHub project specifications. Users can query technical documentation and receive accurate responses grounded in the actual source materials.
How it works
- 1.Trigger chat interface and submit a question about project specifications
- 2.Parse and chunk specification documents, then generate embeddings and store in Pinecone
- 3.Search the vector database for content most relevant to the user's query
- 4.Pass retrieved context and question to the AI agent connected to OpenAI
- 5.Maintain conversation history to support multi-turn dialogue and context awareness
- 6.Return the answer with references to source documentation back to the user
Use cases
- Answer technical questions about APIs, requirements, and design specifications in GitHub repos
- Enable rapid full-text search across documentation without manual file review
- Provide developers instant clarification on project specifications and architectural decisions
Requirements
- Active OpenAI API key and configured Pinecone account
- GitHub specification documents or URLs prepared for ingestion and processing
- User-facing chat interface deployed and accessible
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (17)
When clicking ‘Test workflow’
Manual Trigger
HTTP Request
HTTP Request
Pinecone Vector Store
Vector Store Pinecone
Default Data Loader
Document Default Data Loader
Recursive Character Text Splitter
Text Splitter Recursive Character Text Splitter
When chat message received
Chat Trigger
AI Agent
Agent
OpenAI Chat Model
OpenAI
Window Buffer Memory
Memory Buffer Window
Vector Store Tool
Tool Vector Store
OpenAI Chat Model1
OpenAI
Sticky Note
Sticky Note
Sticky Note1
Sticky Note
Generate User Query Embedding
OpenAI
Pinecone Vector Store (Querying)
Vector Store Pinecone
Generate Embeddings
OpenAI
Sticky Note2
Sticky Note