Update README.md

Clarification and inclusion of FS application notes

Author: SL-Mar

README.md

@@ -1,26 +1,24 @@
-# QuantCoder v0.3
+# The QuantCoder Project  
 
-QuantCoder is a  tool designed to streamline the process of searching for research articles, downloading PDFs, summarizing content, and generating QuantConnect Python algorithms based on the extracted data.
+QuantCoder is a tool designed to streamline the process of searching for research articles, downloading PDFs, summarizing content, and generating QuantConnect Python algorithms based on the extracted data. This project was initiated in November 2023 with the goal of leveraging large language models (LLMs) within the LangChain framework to autonomously develop trading algorithms.
 
-For an explanation of the code, refer to article : https://medium.com/ai-advances/from-finance-papers-to-trading-algorithms-an-automated-approach-ccd2180ee306?sk=c1e67131cd822bccc1acab1b53ae5331
+## Background
 
-This code is now integrated as coding engine in the project QuantCoder_FS, expected to be released Q2 2025. Refer to aricle : https://medium.com/ai-advances/towards-automating-quantitative-finance-research-c868a2a6477e
-Screenshots of the development are visible in a dedicated folder QuantCoder_FS_Demo. 
+The initial version of QuantCoder was a Python prototype that utilized a cognitive architecture described in the article ["Dual Agent Chatbots and Expert Systems Design"](https://towardsdev.com/dual-agent-chatbots-and-expert-systems-design-25e2cba434e9) published by Towards Dev. This version successfully coded a blended momentum and mean-reversion strategy, as explained in the article ["Outperforming the Market (1000% in 10 years)"](https://medium.com/coinmonks/how-to-outperform-the-market-fe151b944c77?sk=7066045abe12d5cf88c7edc80ec2679c), which garnered significant attention with over 10,000 impressions on LinkedIn.
 
-## Features
+## Current Evolution : QuantCoder v0.3
+
+The current version, QuantCoder v0.3, is detailed in the article ["From Finance Papers to Trading Algorithms: An Automated Approach"](https://ai.gopubby.com/from-finance-papers-to-trading-algorithms-an-automated-approach-ccd2180ee306) and is available in this repository. It received notable attention in the publication AI Advances.
+
+### Features
 
 - **Search Articles**: Query the CrossRef API to find relevant journal articles.
 - **List Articles**: View previously searched articles.
 - **Download PDFs**: Download article PDFs using direct links or Unpaywall.
 - **Summarize Articles**: Generate concise summaries of downloaded articles.
 - **Generate QuantConnect Code**: Create QuantConnect Python algorithms based on article summaries.
-- **Interactive Mode**: Perform all steps interactively with guided prompts.
-
-## Installation
-
-Detailed installation instructions will be provided once the CLI is fully set up.
 
-## Usage
+### Usage
 
 To launch the interactive mode of **QuantCLI**, follow these steps:
 
@@ -31,28 +29,22 @@ To launch the interactive mode of **QuantCLI**, follow these steps:
    ```bash
    quantcli interactive
 
-## Project History
+### Strategies 
 
-The project was initiated in November 2023 with the goal of leveraging large language models (LLMs) within the LangChain framework to autonomously develop a trading algorithm. 
-The cognitive architecture underpinning this system is comprehensively detailed in the article:
-https://medium.com/towardsdev/dual-agent-chatbots-and-expert-systems-design-25e2cba434e9
+A folder in this repository contains trading strategies generated using the QuantCoder tool. These strategies may have been refined manually or enhanced using other LLM-based methods. Please note that the author assumes no responsibility for the performance, accuracy, or outcomes resulting from the use of these strategies. Traders are strongly advised to exercise due diligence, conduct thorough research, and independently validate any strategy before applying it in live trading or investment activities.
 
-The trading strategy generated by the system is elaborated in this article: 
-https://medium.com/coinmonks/how-to-outperform-the-market-fe151b944c77
-Following a LinkedIn post announcing this innovative approach, which garnered approximately 10,000 impressions, I published several articles on AI-assisted pair-coding. 
-This positive reception inspired me to integrate the research, summarization of quantitative finance articles, and algorithm coding into a unified workflow. More insights 
-can be found in the article:
-https://medium.com/ai-advances/from-finance-papers-to-trading-algorithms-an-automated-approach-ccd2180ee306
-which received significant attention in publication AI advances.
+## Full-stack application : QuantCoder_FS 
 
-Subsequently, I released the initial proof of concept workflow (v0.1) on GitHub. The codebase was then refactored to adhere more closely to object-oriented programming (OOP) 
-standards in version 0.2, and a user interface was introduced in version 0.3.
+QuantCoder v0.3 has been integrated as a coding engine in the full-stack version of QuantCoder, currently under development in a private repository. This full-stack version includes:
 
-As of December 2024, I am developing the full-stack version of this tool (v0.3). The next phase involves enhancing code generation accuracy through an agent-based workflow 
-using the CrewAI framework. I anticipate releasing the beta version to the quantitative finance community in Q3 2025.
+- **Chat with Fundamentals**: Instant financial analysis by accessing EODHD data.
+- **Search Articles**: Locate relevant academic articles.
+- **Summarize Articles**: Extract key insights from articles.
+- **Code Articles**: Generate trading algorithms based on article summaries.
 
+These workflows are designed to evolve continuously, improving with advancements in LLMs and cognitive frameworks. For transparency and collaboration, these workflows will be demonstrated as Jupyter notebooks in this repository and in relevant Medium articles.
 
 ## License
 
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+The material contained this repo is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.