# REMem

## Docs

- [BaseConfig](https://mintlify.wiki/intuit-ai-research/REMem/api/config.md): Configuration class for ReMem system parameters
- [EmbeddingStore](https://mintlify.wiki/intuit-ai-research/REMem/api/embedding-store.md): Storage and retrieval system for embeddings with persistent caching
- [BaseEmbeddingModel](https://mintlify.wiki/intuit-ai-research/REMem/api/embeddings/base.md): Base interface for all embedding models in Remem
- [GritLMEmbeddingModel](https://mintlify.wiki/intuit-ai-research/REMem/api/embeddings/gritlm.md): GritLM unified embedding and generation model
- [NVEmbedV2EmbeddingModel](https://mintlify.wiki/intuit-ai-research/REMem/api/embeddings/nvidia.md): NVIDIA NV-Embed-v2 embedding model client
- [OpenAI Embedding Clients](https://mintlify.wiki/intuit-ai-research/REMem/api/embeddings/openai.md): OpenAI and OpenAI-compatible embedding API clients
- [QA Evaluation Metrics](https://mintlify.wiki/intuit-ai-research/REMem/api/evaluation/qa-metrics.md): Metrics for evaluating question-answering performance
- [Retrieval Evaluation Metrics](https://mintlify.wiki/intuit-ai-research/REMem/api/evaluation/retrieval-metrics.md): Metrics for evaluating document retrieval performance
- [Episodic Extraction](https://mintlify.wiki/intuit-ai-research/REMem/api/extraction/episodic.md): Extract episodic facts and entities from conversational text
- [Episodic Gist Extraction](https://mintlify.wiki/intuit-ai-research/REMem/api/extraction/episodic-gist.md): Extract both fine-grained facts and high-level gists from episodes
- [OpenIE](https://mintlify.wiki/intuit-ai-research/REMem/api/extraction/openie.md): Extract entities and knowledge graph triples from text
- [Temporal Extraction](https://mintlify.wiki/intuit-ai-research/REMem/api/extraction/temporal.md): Extract facts with temporal qualifiers and time-aware relationships
- [BaseLLM](https://mintlify.wiki/intuit-ai-research/REMem/api/llm/base.md): Abstract base class for LLM implementations in Remem
- [CacheOpenAI](https://mintlify.wiki/intuit-ai-research/REMem/api/llm/openai.md): OpenAI LLM client with SQLite-based response caching
- [VLLMOffline](https://mintlify.wiki/intuit-ai-research/REMem/api/llm/vllm.md): vLLM offline inference engine for local model deployment
- [ReMem](https://mintlify.wiki/intuit-ai-research/REMem/api/remem.md): Core class for the ReMem retrieval-augmented generation framework
- [RAGStrategy Base Class](https://mintlify.wiki/intuit-ai-research/REMem/api/strategies/base.md): Abstract base class and factory for RAG strategies
- [DefaultRAGStrategy](https://mintlify.wiki/intuit-ai-research/REMem/api/strategies/default.md): Default RAG strategy for OpenIE-based extraction
- [EpisodicGistStrategy](https://mintlify.wiki/intuit-ai-research/REMem/api/strategies/episodic-gist.md): Strategy for episodic gist-based extraction and retrieval
- [TemporalStrategy](https://mintlify.wiki/intuit-ai-research/REMem/api/strategies/temporal.md): Strategy for temporal-based extraction and retrieval
- [Baseline Methods](https://mintlify.wiki/intuit-ai-research/REMem/benchmarks/baselines.md): Comparison with baseline retrieval and reasoning methods
- [Benchmark Datasets](https://mintlify.wiki/intuit-ai-research/REMem/benchmarks/datasets.md): Detailed documentation of supported benchmark datasets
- [Benchmarks Overview](https://mintlify.wiki/intuit-ai-research/REMem/benchmarks/overview.md): Comprehensive benchmarking suite for evaluating ReMem on long-context QA datasets
- [Running Benchmarks](https://mintlify.wiki/intuit-ai-research/REMem/benchmarks/running.md): Step-by-step guide to running ReMem benchmarks
- [Architecture](https://mintlify.wiki/intuit-ai-research/REMem/concepts/architecture.md): Understanding REMem's hybrid memory graph architecture and processing pipeline
- [Extraction Methods](https://mintlify.wiki/intuit-ai-research/REMem/concepts/extraction-methods.md): The 4 extraction methods in REMem and how they transform documents into structured memory
- [Memory Graph](https://mintlify.wiki/intuit-ai-research/REMem/concepts/memory-graph.md): Understanding REMem's hybrid memory graph structure with entities, facts, episodic traces, and gist summaries
- [Retrieval Strategies](https://mintlify.wiki/intuit-ai-research/REMem/concepts/retrieval-strategies.md): How REMem retrieves relevant passages using dense search combined with graph exploration
- [Custom Extraction Methods](https://mintlify.wiki/intuit-ai-research/REMem/customization/extraction.md): Add custom information extraction methods to REMem
- [Custom Evaluation Metrics](https://mintlify.wiki/intuit-ai-research/REMem/customization/metrics.md): Add custom evaluation metrics to REMem
- [Custom Preprocessing](https://mintlify.wiki/intuit-ai-research/REMem/customization/preprocessing.md): Customize chunking and text preprocessing in REMem
- [Custom Prompt Templates](https://mintlify.wiki/intuit-ai-research/REMem/customization/prompts.md): Customize LLM prompts for extraction and QA in REMem
- [Custom RAG Strategies](https://mintlify.wiki/intuit-ai-research/REMem/customization/rag-strategies.md): Create custom retrieval strategies for different extraction methods
- [Configuration](https://mintlify.wiki/intuit-ai-research/REMem/guides/configuration.md): Complete reference for BaseConfig parameters and their usage
- [Embedding Models](https://mintlify.wiki/intuit-ai-research/REMem/guides/embeddings.md): How to use different embedding models in REMem
- [Evaluation](https://mintlify.wiki/intuit-ai-research/REMem/guides/evaluation.md): How to evaluate retrieval and QA performance with REMem
- [Indexing Documents](https://mintlify.wiki/intuit-ai-research/REMem/guides/indexing.md): Learn how to index documents using ReMem.index() to build a knowledge graph
- [Question Answering](https://mintlify.wiki/intuit-ai-research/REMem/guides/question-answering.md): Learn how to use ReMem.rag_for_qa() for end-to-end retrieval-augmented generation
- [Retrieving Passages](https://mintlify.wiki/intuit-ai-research/REMem/guides/retrieval.md): Learn how to retrieve relevant passages using ReMem.retrieve()
- [Installation](https://mintlify.wiki/intuit-ai-research/REMem/installation.md): Detailed installation instructions for REMem including Python requirements, dependencies, and configuration options
- [Introduction to REMem](https://mintlify.wiki/intuit-ai-research/REMem/introduction.md): A brain-inspired retrieval-augmented generation system with hybrid episodic memory graphs for complex, multi-hop reasoning over long-form text
- [Quickstart](https://mintlify.wiki/intuit-ai-research/REMem/quickstart.md): Get up and running with REMem in 5 minutes