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.

​
RetrievalConfig

Defined in the Retrieval Config module.
AI Agent Unified configuration for Agent retrieval behavior. This is the SINGLE configuration surface that replaces:
  • knowledge_config
  • rag_config
Attributes: enabled: Whether retrieval is enabled (default: True if knowledge provided) policy: When to retrieve (auto, always, never) top_k: Number of chunks to retrieve min_score: Minimum relevance score threshold (0.0-1.0) max_context_tokens: Maximum tokens for retrieved context rerank: Whether to rerank results for better relevance hybrid: Whether to use hybrid retrieval (dense + keyword) citations: Whether to include source citations citations_mode: How to include citations (append, inline, hidden)

​
Vector store configuration

vector_store_provider: Vector store provider (chroma, mongodb, etc.) vector_store_config: Provider-specific configuration collection_name: Collection/index name persist_path: Path for persistent storage

​
Embedding configuration

embedder_provider: Embedding provider embedder_model: Embedding model name

​
Advanced options

auto_keywords: Keywords that trigger retrieval in auto mode auto_min_length: Minimum query length for auto retrieval context_template: Template for formatting retrieved context system_separation: Whether to use system prompt separation for safety

​
Properties

​
enabled
bool
No description available.
​
policy
RetrievalPolicy
No description available.
​
top_k
int
No description available.
​
min_score
float
No description available.
​
max_context_tokens
int
No description available.
​
rerank
bool
No description available.
​
hybrid
bool
No description available.
​
citations
bool
No description available.
​
citations_mode
CitationsMode
No description available.
​
model_context_window
Optional
No description available.
​
reserved_response_tokens
int
No description available.
​
dynamic_budget
bool
No description available.
​
strategy
str
No description available.
​
compress
bool
No description available.
​
compression_ratio
float
No description available.
​
include_glob
Optional
No description available.
​
exclude_glob
Optional
No description available.
​
path_filter
Optional
No description available.
​
vector_store_provider
str
No description available.
​
vector_store_config
Dict
No description available.
​
collection_name
Optional
No description available.
​
persist_path
str
No description available.
​
embedder_provider
Optional
No description available.
​
embedder_model
Optional
No description available.
​
auto_keywords
frozenset
No description available.
​
auto_min_length
int
No description available.
​
context_template
str
No description available.
​
system_separation
bool
No description available.

​
Methods

get_token_budget()

Get TokenBudget instance for this config.

get_strategy()

Get retrieval strategy based on config and corpus stats.

to_knowledge_config()

Convert to Knowledge-compatible config.

to_rag_config()

Convert to RAG pipeline config.

should_retrieve()

Determine if retrieval should be performed for a query.
  • from_dict: Create from dictionary.
  • to_dict: Convert to dictionary.

​
Source

View on GitHub

praisonaiagents/rag/retrieval_config.py at line 28

Configuration Overview

Agent Config

Evaluation Concept

LLM as Judge

Evaluation Loop