Expert guide for building applications with the Claude Agent SDK for Python. Use when working with the SDK to create automated workflows, implement custom tools (in-process MCP servers), configure hooks for agent behavior control, or integrate Claude Code into Python applications.
Expert guidance for setting up, configuring, and troubleshooting Claude Code Router - a powerful tool for routing Claude Code requests to different LLM models and providers. Use when working with multi-model setups, cost optimization, provider switching, or advanced Claude Code configurations.
Perform financial text analysis using FinBERT models including sentiment analysis, ESG classification, and forward-looking statement detection on financial documents and reports.
Expert guidance for building applications with LangChain, LangGraph, and LangSmith SDKs. Provides code examples, best practices, and implementation patterns for Python and JavaScript/TypeScript based on official documentation.
Latent Dirichlet Allocation (LDA) topic modeling for financial text analysis using Scikit-learn and Gensim frameworks. Use when performing topic modeling, text mining, financial document analysis, or extracting themes from large text corpora.
Guide for fine-tuning and training large language models using LLaMA-Factory. Use when users want to train, fine-tune, evaluate, or deploy LLMs locally, including tasks like supervised fine-tuning (SFT), LoRA adaptation, RLHF, preference optimization (DPO/KTO), or model deployment.
Text vectorization and semantic analysis using Alibaba Cloud DashScope's text-embedding-v4 model. Provides 6 major capabilities - semantic search, recommendation systems, text clustering, zero-shot classification, anomaly detection, and advanced embedding features (sparse/dense vectors, hybrid search).
Access and analyze SEC EDGAR filings data using comprehensive APIs for searching, downloading, parsing financial statements, insider trading, institutional holdings, and extracting structured data from 10-K, 10-Q, 8-K and other SEC forms.
A Python toolkit for sentence segmentation with unified API supporting NLTK, spaCy, PySBD, and Stanza frameworks. Easily split text into sentences using multiple NLP libraries through a consistent interface.
Expert guidance for working with vLLM - a fast, easy-to-use library for Large Language Model (LLM) inference and serving. Use when deploying LLMs, setting up inference servers, optimizing model serving, implementing distributed inference, or troubleshooting vLLM performance issues.
★not rated 2 10mo agoA62 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: