init

README.md

@@ -3,8 +3,11 @@
 </p>
 <h1 align="center">SynthToT</h1>
 <h3 align="center">Generate a synthetic dataset for your data through deliberate problem-solving</h3>
+<h6 align="center"><a href="https://discord.gg/5TesGau62q">Join Mathematics & AI Institue Discord!</a></h6>
 
-##### Table of Content
+<hr>
+
+## Table of Content
 
 - [Introduction](#introduction)
 - [Features](#features)
@@ -27,7 +30,7 @@ SynthToT is an simple AI agent system crafted with [Langchain](https://www.langc
 > ### About Mathematics & AI Institute
 > At the Math and AI Institute, our mission is to bring state-of-the-art research at the intersection of AI and mathematics. We specialize in generative AI technologies, leveraging their potential to empower industries with innovative projects. Generative AI, a cutting-edge field, enables the creation of diverse content, including text, images, and videos, while adapting seamlessly to new data. While we acknowledge the potential risks associated with the rapid evolution of Generative AI, our team is dedicated to ensuring the safety and interpretability of these tools. Our core areas of focus include AI Safety, Industry Integration, Fundamental Research, and Tailored AI Training for various sectors. 
 
-For more information about us, please check out website at [matyz.org/en](https://matyz.org/en)
+> For more information about us, please check out website at [matyz.org/en](https://matyz.org/en)
 
 <hr>
 
@@ -80,10 +83,10 @@ You can view example input_data and output_data from under the `examples` folder
 - **Initialization:** Customizable parameters such as maximum tokens per response, model type, and sampling temperature.
 
     - max_tokens: Limits the number of tokens generated per response.
-    - model: Specifies the language model to use (default is "gpt-3.5-turbo").
+    - model: Specifies the language model to use (default is "gpt-4").
     - temperature: Controls the randomness of the output (default is 0).
 
-- **Template Management:** Utilizes a set of predefined templates (template_step1 to template_step5) and corresponding output keys for structured data generation.
+- **Template Management:** Utilizes a set of predefined Tree-of-Thoughts templates and corresponding output keys for structured data generation.
 
 - **LLMChain:** Initializes an LLMChain with a specified prompt template and output key, using the selected language model and parameters.