Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.praison.ai/llms.txt

Use this file to discover all available pages before exploring further.

Uses embeddings to split text at semantic boundaries. Groups related content together for better retrieval.

​
Quick Start

from praisonaiagents import Agent

agent = Agent(
    instructions="Answer questions from research papers.",
    knowledge={
        "sources": ["papers/"],
        "chunker": {
            "type": "semantic",
            "chunk_size": 512,
            "embedding_model": "all-MiniLM-L6-v2"
        }
    }
)

response = agent.start("What methodology did they use?")

​
When to Use

Good For

  • Research papers
  • Topic-dense content
  • Multi-subject documents
  • Quality over speed

Consider Alternatives

  • Speed-critical pipelines
  • Uniform chunk sizes needed
  • Simple structured content
  • Very short documents

​
Parameters

ParameterTypeDefaultDescription
chunk_sizeint512Max tokens per chunk
embedding_modelstrautoModel for semantic similarity

​
Examples

​
Research Analysis

agent = Agent(
    instructions="Analyze academic papers.",
    knowledge={
        "sources": ["research/"],
        "chunker": {
            "type": "semantic",
            "chunk_size": 512,
            "embedding_model": "all-MiniLM-L6-v2"
        }
    }
)

​
Knowledge Base

agent = Agent(
    instructions="Answer from knowledge base.",
    knowledge={
        "sources": ["wiki/", "faq.txt"],
        "chunker": {
            "type": "semantic",
            "chunk_size": 256  # Smaller for precise retrieval
        }
    }
)

​
How It Works

Semantic chunking:
  1. Splits document into sentences
  2. Generates embeddings for each sentence
  3. Groups consecutive similar sentences
  4. Creates new chunk when topic changes

​
Performance Note

Semantic chunking requires computing embeddings and is slower than token/sentence chunking. Use for quality-sensitive applications where retrieval accuracy matters more than speed.

​
Embedding Models

The default embedding model is all-MiniLM-L6-v2. You can use any model supported by the chonkie library: 
knowledge={
    "sources": ["docs/"],
    "chunker": {
        "type": "semantic",
        "embedding_model": "all-MiniLM-L6-v2"  # Default
        # Or: "text-embedding-3-small", etc.
    }
}