pythondspyllm-pipelinesagent-frameworkafter-workstart-using
How to Start Using DSPy for LLM Pipelines
Install DSPy, define a tiny typed module, run one predict/optimize loop—less hand-tuned prompting for after-work Python.
Academy notes
Articles and updates from SoloQuant Academy.
Install DSPy, define a tiny typed module, run one predict/optimize loop—less hand-tuned prompting for after-work Python.
Install Haystack, wire a tiny Agent or pipeline with one tool, and learn production-minded NLP agents after work.
Install LlamaIndex, run a tiny Workflow (or agent) over one local doc, and learn event-driven RAG agents after work.
Install Hugging Face smolagents, run a tiny code-agent with one tool, and learn tool-calling without a heavyweight stack.
Semantic Kernel is converging into Microsoft Agent Framework—learn the migration path with one tiny agent tonight.
AutoGen is in maintenance—start with AG2 or Microsoft Agent Framework tonight; use AutoGen only as a migration contrast.
Wei, Dai & Lin (2022) propose a deep multi-factor model for equity factor investing. Plain-language intro for after-work Python learners. Not investment advice.
Harvey, Liu & Zhu (2016) warn that the factor zoo needs much higher t-stat hurdles under multiple testing. Plain-language intro. Not investment advice.
Dixon & Polson (2019) study deep learning on fundamental characteristics for equity factor-style modelling. Plain-language intro. Not investment advice.
Nakagawa, Uchida & Aoshima (2018) explore deep neural nets for factor-style return modelling from characteristics. Plain-language intro. Not investment advice.
Kelly, Pruitt & Su (2019) introduce Instrumented PCA (IPCA): firm characteristics instrument latent factor loadings. Plain-language intro. Not investment advice.
Frazzini & Pedersen (2014) document the low-beta anomaly and the Betting-Against-Beta (BAB) factor. Plain-language intro. Not investment advice.