Skip to content
View marcusjihansson's full-sized avatar

Block or report marcusjihansson

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. dspy-refragdspy-refragPublic

    DSPy Retrieval-Enhanced Fine-Grained Retrieval Augmented Generation (REFRAG) framework, for an improved RAG in DSPy. This is originally developed by Meta AI.

    Python 35 6

  2. agent_optagent_optPublic

    I started to research different agent optimization techniques for my own benefit, so I built this library. Feel free to take these implementations and start experimenting with different strategies.

    Python 3 1

  3. memory_optmemory_optPublic

    Hierchical memory is the optimization technique applied to the 5 part memory system (cached memory, short term memory and long term memory, RLM memory and Meta Memory)

    Python 1 1

  4. routing-intelligencerouting-intelligencePublic

    This is a research project of the premise that: we should be able to route different queries to different thought models (eg. chain of thought) and then optimize this routing of queries.

    Python 2 1

  5. toon-vs-zon-studytoon-vs-zon-studyPublic

    Research project exploring token-efficient serialization formats for LLM RAG systems. This uses Shopify data and measures: latency, tokens and the strategies success rate.

    Python

  6. dspy-performance-monitordspy-performance-monitorPublic

    This is a performance monitor for dspy classes to measure bottlenecks in production