Context vs Knowledge
PraisonAI provides two systems for providing information to agents: Context (runtime data flow) and Knowledge (pre-loaded reference data). Understanding when to use each is crucial for building efficient agents.Quick Comparison
| Aspect | Context | Knowledge |
|---|---|---|
| When Loaded | Runtime (during execution) | Pre-loaded (before execution) |
| Source | Agent outputs, tool results | Files, URLs, documents |
| Storage | In-memory (ephemeral) | Vector DB (persistent) |
| Search | Sequential flow | Semantic search (RAG) |
| Use Case | Passing data between agents | Reference information |
| Dependencies | None | chromadb, mem0 |
Context: Runtime Data Flow
Context is how agents share information during a single workflow execution. Data flows from one agent to the next and is lost when the session ends.Context Code Example
Knowledge: Pre-loaded Reference Data
Knowledge provides agents with pre-loaded reference information from files, URLs, or documents. It uses RAG (Retrieval Augmented Generation) to find relevant information.Knowledge Code Example
Supported File Types
Documents
PDF, DOC, DOCX, PPT, PPTX, XLS, XLSX
Text
TXT, CSV, JSON, XML, MD, HTML
Media
JPG, PNG, GIF, MP3, WAV (with transcription)
How Knowledge Works
1
Load Documents
Files are read and converted to text using MarkItDown.
2
Chunk Content
Text is split into smaller chunks (default: 512 tokens, 50 overlap).
3
Generate Embeddings
Each chunk is converted to a vector embedding.
4
Store in Vector DB
Embeddings are stored in ChromaDB for fast similarity search.
5
Query at Runtime
When agent needs info, query is embedded and similar chunks are retrieved.
When to Use Each
Use Context When:
- Agent-to-agent data flow - Passing results between sequential agents
- Tool results - Using output from tool calls
- Simple workflows - No external reference data needed
- Zero dependencies - Want to avoid extra packages
Use Knowledge When:
- Reference documents - Manuals, FAQs, documentation
- Large content - Too much to fit in prompt
- Semantic search - Need to find relevant sections
- RAG applications - Question answering over documents
Using Both Together
The most powerful pattern combines both: Knowledge for reference data + Context for workflow data.Knowledge Configuration
Basic Configuration
Advanced Configuration
Performance Comparison
| Operation | Context | Knowledge |
|---|---|---|
| Setup | Instant | ~1-5s per document |
| Query | ~0ms | ~50-200ms |
| Dependencies | None | chromadb |
| Storage | Memory | Disk (persistent) |
Knowledge has higher setup cost but enables semantic search over large document collections that wouldn’t fit in context.
Summary
Context
Runtime data flow between agents. Fast, zero dependencies, ephemeral. Use for passing agent outputs.
Knowledge
Pre-loaded reference data with semantic search. Persistent, RAG-enabled. Use for documents and FAQs.

