In this blog, we will give you a brief introduction to AgentBoard, an open source AI agent visualization toolkit which can be used the same way as Tensorboard, which helps visaulize Tensors data during model training. AgentBoard aims to visualize key elements and information of AI Agents running loops in development and production stages of real-world scenarios. It provides easy logging APIs in python and can help log multiple data types such as text (prompt), tools use (function calling of LLM API), image, audio and video. With organized logging schemas, agentboard will visualize the agent-loop (PLAN -> ACT -> REFLECT -> REACT etc ), RAG (Retrieval Augumented Generation), Autonomous Agents running, Multi-Agents orchestration, etc. The rest of the blog will cover the basic data types usage, visualization of Agent Loop, Chat History, Tool Use, Functions Calling, RAG, etc.

This blog summarizes the latest research development of retrieval papers published in ACL2023 conferences. This year there are total 76 papers related to retrieval in ACL2023. Most of the authors' affiliations are top research institutes (Google Research, DeepMind, Meta FAIR) and universities (Stanford, Berkeley, MIT, CMU and others).

In this blog, we will introduce how to use ChatGPT stock analysis chatbot to quickly generate professional charts of financial data. A few AI techniques such as RAG (Retrieval Augmented Generation), Text2SQL, and Larget Language Models (LLM) are used to help users find financial data, draw chart to compare key metrics, and adjust the color and shape of the chart using simple natural language prompts. A typical scenrio for professional financial analysts is to draw chart to compare the market capitalization, PE ratio of stocks from global market in converted currencies (US Dollars for example). This is a frequent scenario of daily workflow. The snapshots of AI generated charts is shown using DeepNLP Financial Assistant. You can try by clicking the button below the page, copy and paste the query in the chatbox and ask AI to generate charts or tables in few seconds, copy the charts to your reports or send to your manager. From the chart, we can see that on January 15th, Microsoft (MSFT) market cap reaches 2,887 Billon US dollars, and Apple (AAPL) reaches 2,874.68 Billion US dollars. Microsoft's market cap surpassed Apple and became the company of largest market capitalization in United States. The real-time stock data is from the web APIs, and converted to SQL using Text2SQL and LLM techniques.

In this blog, we will introduce how to use ChatGPT stock analysis chatbot to quickly generate professional charts of financial data. A few AI techniques such as RAG (Retrieval Augmented Generation), Text2SQL, and Larget Language Models (LLM) are used to help users find financial data, draw chart to compare key metrics, and adjust the color and shape of the chart using simple natural language prompts. A typical scenrio for professional financial analysts is to draw chart to compare the market capitalization, PE ratio of stocks from global market in converted currencies (US Dollars for example). This is a frequent scenario of daily workflow. The snapshots of AI generated charts is shown using DeepNLP Financial Assistant. You can try by clicking the button below the page, copy and paste the query in the chatbox and ask AI to generate charts or tables in few seconds, copy the charts to your reports or send to your manager. From the chart, we can see that on January 15th, Microsoft (MSFT) market cap reaches 2,887 Billon US dollars, and Apple (AAPL) reaches 2,874.68 Billion US dollars. Microsoft's market cap surpassed Apple and became the company of largest market capitalization in United States. The real-time stock data is from the web APIs, and converted to SQL using Text2SQL and LLM techniques.

We are witnessing great success in recent development of generative Artificial Intelligence in many fields, such as AI assistant, Chatbot, AI Writer. Among all the AI native products, AI Search Engine such as Perplexity, Gemini and SearchGPT are most attrative to website owners, bloggers and web content publishers. AI Search Engine is a new tool to provide answers directly to users' questions (queries). In this blog, we will give some brief introduction to basic concepts of AI Search Engine, including Large Language Models (LLM), Retrieval-Augmented Generation(RAG), Citations and Sources. Then we will highlight some majors differences between traditional Search Engine Optimization (SEO) and Generative Engine Optimization(GEO). And then we will cover some latest research and strategies to help website owners or content publishers to better optimize their content in Generative AI Search Engines.

This blog summarizes the latest research development of Retrieval papers published in KDD2023 conferences. This year there are total 8 papers related to Retrieval in KDD2023. Most of the authors' affiliations are top research institutes (Google Research, DeepMind, Meta FAIR) and universities (Stanford, Berkeley, MIT, CMU and others).

In this post, we will talk about some real-world applications of deep candidates generation (vector-retrieval) models in the matching stage of recommendation scenario. Commercial recommendation system will recommend tens of millions of items to each user. And the recommendation process usually consists of two stages: The first stage is the candidate generation(matching) stage, a few hundred candidates are selected from the pool of all candidate items. The second stage is the ranking stage in which hundreds of items are ranked and sorted by the ranking score. Then the top rated items are displayed to users.