Overview SessionConfig is the central configuration object for all Fenic operations. It defines application settings, model configurations, and optional cloud settings.Constructor from fenic.api.session.config import SessionConfig config = SessionConfig( app_name = "my_app" , semantic = SemanticConfig( ... ), db_path = None , cloud = None )
Parameters Name of the application using this session. Used for logging and tracking purposes.
Configuration for semantic models including language models and embedding models. See SemanticConfig for details. When not provided, only non-semantic DataFrame operations are available. Optional path to a local database file for persistent storage. If not provided, an in-memory database is used.
Configuration for cloud-based execution. Only needed for distributed processing. Show CloudConfig Properties
Size of the cloud executor instance. Options:
CloudExecutorSize.SMALL - Small instanceCloudExecutorSize.MEDIUM - Medium instanceCloudExecutorSize.LARGE - Large instanceCloudExecutorSize.XLARGE - Extra large instance Methods to_json() Export the session configuration to a JSON string.
json_str = config.to_json()
Returns: str - JSON representation of the configurationExamples Basic Configuration Simple session with a single language model:
from fenic.api.session.config import SessionConfig, SemanticConfig from fenic.api.session.config import OpenAILanguageModel config = SessionConfig( app_name = "my_app" , semantic = SemanticConfig( language_models = { "gpt4" : OpenAILanguageModel( model_name = "gpt-4.1-nano" , rpm = 100 , tpm = 1000 ) } ) )
Multi-Model Configuration Session with multiple language models and an embedding model:
from pathlib import Path from fenic.api.session.config import ( SessionConfig, SemanticConfig, OpenAILanguageModel, AnthropicLanguageModel, OpenAIEmbeddingModel, ) config = SessionConfig( app_name = "production_app" , db_path = Path( "/path/to/database.db" ), semantic = SemanticConfig( language_models = { "gpt4" : OpenAILanguageModel( model_name = "gpt-4.1-nano" , rpm = 100 , tpm = 1000 ), "claude" : AnthropicLanguageModel( model_name = "claude-3-5-haiku-latest" , rpm = 100 , input_tpm = 100 , output_tpm = 100 ), }, default_language_model = "gpt4" , embedding_models = { "openai_embeddings" : OpenAIEmbeddingModel( model_name = "text-embedding-3-small" , rpm = 100 , tpm = 1000 ) }, default_embedding_model = "openai_embeddings" , ), )
Cloud Execution Configuration Session configured for cloud-based execution:
from fenic.api.session.config import ( SessionConfig, SemanticConfig, CloudConfig, CloudExecutorSize, OpenAILanguageModel, ) config = SessionConfig( app_name = "cloud_app" , semantic = SemanticConfig( language_models = { "gpt4" : OpenAILanguageModel( model_name = "gpt-4.1-nano" , rpm = 100 , tpm = 1000 ) } ), cloud = CloudConfig( size = CloudExecutorSize. MEDIUM ), )
Configuration with LLM Response Caching Reduce costs and improve performance with response caching:
from fenic.api.session.config import ( SessionConfig, SemanticConfig, LLMResponseCacheConfig, OpenAILanguageModel, ) config = SessionConfig( app_name = "cached_app" , semantic = SemanticConfig( language_models = { "gpt4" : OpenAILanguageModel( model_name = "gpt-4.1-nano" , rpm = 100 , tpm = 1000 ) }, llm_response_cache = LLMResponseCacheConfig( enabled = True , ttl = "2h" , # Cache for 2 hours max_size_mb = 1000 , # 1GB cache ) ), )
Usage Once configured, pass the SessionConfig to Session.get_or_create():
from fenic import Session session = Session.get_or_create( config = config)
