et lux in tenebris lucet

Building A SEC 10K Analyst with Memory Layer

Modeling financial markets is hard. SEC data is valuable. Pattern recognition needs memory. Mem0 makes memory management easier.

• Details

Evaluating Local GenAI Models for Finance

As the world of generative AI is rapidly evolving weevaluate the performance of three types of models for typical tasks in regular investment workflows. We explore which model-prompt combination is useful

• Details

Financial Datasets for Cognitive Agent Training

An exploration of financial datasets that can be used for common tasks in training cognitive agents for reasoning, summarizing, and annotated bodies of financial texts.

• Details

Using FinBERT-MRC for Naming Entities

Financial named entity recognition using BERT under the machine reading comprehension paradigm. The naive approach when working with financial news is to calculate sentiments. What else is there?

• Details

Risk Management for Autonomous Agents

Risk Management is still considered an afterthought when we are building our AI/ML products. Many otherwise good companies have suffered the consequences of this.

• Details

Investing Agents with Langchain RAG

One thing that all of us have dreamed of is an investment agent who is much better than us in trading, always makes the right decisions, and makes us money while we are sleeping. It is unlikely that such an agent might ever exist

• Details

• Agents

• Cookbooks

• Datasets

• Prompts