NewMemoryManager creates and initializes a new MemoryManager with a specified TTL (Time-To-Live).

.

.

EmbeddingConfig holds the configuration settings for text chunking during embedding operations.

Each action should be a timestamp for benchmarking or output management.

LLMConfig struct holds configuration details for the embedding and AI model service.

LLMContainer serves as the main struct that manages LLM operations, embedding configurations, and data storage.

LLMEmbeddingContent represents a single piece of text content that is embedded and stored in the system.

LLMEmbeddingObject represents a collection of embedded text contents grouped under a specific object ID.

LLMResult represents the result of an LLM query, including the generated response, retrieved documents, and logged actions.

LLMTextEmbedding is a struct designed to handle text processing and splitting operations.

Memory structure to store user memory session data.

Memory structure to store user memory question data.

MemoryManager manages session memories with a time-to-live (TTL) mechanism.

OllamaController struct to manage the Ollama embedding and language model service.

OpenAIController struct to manage OpenAI embedding and language model services.

PersistentMemory structure to store user memory session data in a persistent storage (Redis) for future retrival or vector search.

RedisClient manages the connection details for a Redis database instance used for storing embeddings.

Transcriber handles document transcription by extracting text from various file formats.

EmbeddingClient defines an interface to abstract embedding model clients.

LLMClient defines an interface for creating a new LLM (Large Language Model) client instance.

LLMCallOption is a function that configures a LLMCallOptions.