Skip to content
View pseudobarbie8's full-sized avatar
🟡
brought to you by a killer playlist and coffee
🟡
brought to you by a killer playlist and coffee

Organizations

@Dokist-ai

Block or report pseudobarbie8

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.

Content in all repositories owned by your account will be closed.
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
pseudobarbie8/README.md
RAG systems for document-heavy industries | LLM agents to production | Python, PyTorch, LangChain

LinkedIn    Dev.to    Hugging Face

class pseudobarbie:
    role          = "AI Engineer, building Dokist"
    focus         = ["RAG", "LLM Agents", "Document Intelligence", "Legaltech", "Fintech"]
    stack         = ["PyTorch", "MCP", "LangChain", "FastAPI", "Docker"] # eval on CUAD + SEC EDGAR
    mission       = "making documents less tedious"
    side_projects = "github.com/pseudobarbie/side-quests"
    currently_reading = "Self-RAG (Asai et al., ICLR '24): LLMs that audit their own retrieval"

    def contact(self):
        return "https://www.linkedin.com/in/pseudobarbie/"

Dokist-ai/core - building retrieval systems that actually retrieve for legal & financial docs.

pseudobarbie/side-quests - tooling, agents, detours & learning logs.

core side-quests huggingface

Pinned Loading

  1. Dokist-ai/core Dokist-ai/core Public

    RAG systems, LLM agents, and production pipelines for legal and financial document intelligence.

    Dockerfile 5

  2. legal-retrieval-fr-ar-pilot legal-retrieval-fr-ar-pilot Public

    Pilot dataset and baselines toward an open French/Arabic legal retrieval benchmark. Questions written from public legal articles, no legal review yet.

    Python 1

  3. hf-rag-demo hf-rag-demo Public

    A minimal retrieval-augmented generation demo built with Sentence Transformers + Streamlit. Live on Hugging Face.

    Python 2

  4. legal-doc-classification legal-doc-classification Public

    Notebook on end-to-end NLP pipeline for classifying legal contract clauses. BERT → fine-tuning → evaluation on imbalanced data. Published on kaggle.

    Jupyter Notebook 2

  5. baby-gpt-shakespeare baby-gpt-shakespeare Public

    Learning experiment: training a tiny character-level GPT on Shakespeare, following Karpathy’s nanoGPT. My notes and runs.

    Jupyter Notebook 1

  6. side-quests side-quests Public

    Small scale experiments, tooling, learning logs, and anything in between.

    2