update figs and wording

website/docs/Getting-Started.md

@@ -6,13 +6,15 @@
 
 AutoGen is a framework that enables development of LLM applications using multiple agents that can converse with each other to solve task. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools. 
 
+![AutoGen Overview](/img/autogen_agentchat.png)
+
 ### Main Features
 
-* AutoGen enables building next-gen LLM applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and augments their weakness.
-* It supports diverse conversation patterns for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy,
+* AutoGen enables building next-gen LLM applications based on **multi-agent conversations** with minimal effort. It simplifies the orchestration, automation and optimization of a complex LLM workflow. It maximizes the performance of LLM models and augments their weakness.
+* It supports **diverse conversation patterns** for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy,
 the number of agents, and agent conversation topology.
-* It provides a collection of working systems with different complexities. These systems span a wide range of applications from various domains and complexities. They demonstrate how AutoGen can easily support different conversation patterns.
-* AutoGen provides a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` as an enhanced inference API. It allows easy performance tuning, utilities like API unification & caching, and advanced usage patterns, such as error handling, multi-config inference, context programming etc.
+* It provides a collection of working systems with different complexities. These systems span a **wide range of applications** from various domains and complexities. They demonstrate how AutoGen can easily support different conversation patterns.
+* AutoGen provides a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` as an **enhanced inference API**. It allows easy performance tuning, utilities like API unification & caching, and advanced usage patterns, such as error handling, multi-config inference, context programming etc.
 
 AutoGen is powered by collaborative [research studies](/docs/Research) from Microsoft, Penn State University, and University of Washington.
 
@@ -28,10 +30,12 @@ By automating chat among multiple capable agents, one can easily make them colle
 from flaml.autogen import AssistantAgent, UserProxyAgent
 assistant = AssistantAgent("assistant")
 user_proxy = UserProxyAgent("user_proxy")
-user_proxy.initiate_chat(assistant, message="Show me the YTD gain of 10 largest technology companies as of today.")
+user_proxy.initiate_chat(assistant, message="PLot a chart of META and TESLA stock price change YTD.")
 # This initiates an automated chat between the two agents to solve the task
 ```
 
+The figure below shows an example conversation flow with AutoGen.
+![Agent Chat Example](/img/chat_example.png)
 
 #### Enhanced LLM Inferences
 Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` with powerful functionalites like tuning, caching, error handling, templating. For example, you can optimize generations by LLM with your own tuning data, success metrics and budgets.

website/docusaurus.config.js

@@ -4,7 +4,7 @@ const katex = require('rehype-katex');
 
 module.exports = {
   title: 'AutoGen',
-  tagline: 'Enabling Next-Gen LLM Applications',
+  tagline: 'A Multi-Agent Conversation Framework',
   url: 'https://microsoft.github.io/',
   baseUrl: '/AutoGen/',
   onBrokenLinks: 'throw',

website/src/components/HomepageFeatures.js

@@ -5,8 +5,8 @@ import styles from './HomepageFeatures.module.css';
 
 const FeatureList = [
   {
-    title: 'Build Workflows with Multi-Agent Conversations',
-    Svg: require('../../static/img/auto.svg').default,
+    title: 'Multi-Agent Conversations',
+    Svg: require('../../static/img/conv.svg').default,
     docLink: './docs/Use-Cases/agent_chat',
     description: (
       <>
@@ -15,8 +15,8 @@ const FeatureList = [
     ),
   },
   {
-    title: 'Support Diverse Applications At Ease',
-    Svg: require('../../static/img/fast.svg').default,
+    title: 'Easily Build Diverse Applications',
+    Svg: require('../../static/img/autogen_app.svg').default,
     docLink: './docs/Use-Cases/agent_chat#diverse-applications-implemented-with-autogen',
     description: (
       <>
@@ -25,7 +25,7 @@ const FeatureList = [
     ),
   },
   {
-    title: 'Optimize Performance of LLM Inferences',
+    title: 'Enhanced LLM Inference & Optimization',
     Svg: require('../../static/img/extend.svg').default,
     docLink: './docs/Use-Cases/enhanced_inference',
     description: (

website/static/img/autogen_app.svg

@@ -0,0 +1 @@
+<svg width="123" height="123" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" xml:space="preserve" overflow="hidden"><g transform="translate(-630 -377)"><g><g><g><g><path d="M710.577 446.269C716.052 448.234 721.233 450.473 725.523 453.982 727.577 455.585 728.799 458.028 728.848 460.634L731.079 478.926C731.259 480.308 730.652 481.675 729.505 482.468 727.319 483.881 724.968 485.021 722.505 485.864L722.505 488.543C725.471 487.591 728.301 486.257 730.924 484.576 732.862 483.253 733.897 480.956 733.604 478.627L731.388 460.515C731.307 457.18 729.738 454.056 727.111 451.999 722.501 448.227 717.027 445.878 711.269 443.821L705.014 441.254C704.059 440.864 703.435 439.934 703.438 438.902L703.438 435.156C708.234 431.568 711.06 425.93 711.065 419.941L711.065 416.257C711.723 416.528 712.426 416.675 713.138 416.69 713.839 416.69 714.408 416.121 714.408 415.419 714.408 415.283 714.386 415.147 714.343 415.018L713.056 411.155C712.495 409.391 712.045 407.594 711.711 405.774 710.457 399.63 706.416 394.418 700.776 391.676 699.872 391.204 698.779 391.285 697.953 391.884L697.569 391.315C697.049 390.51 696.226 389.95 695.286 389.762 685.449 387.913 675.963 394.157 672.731 404.05 672.177 405.775 671.894 407.575 671.892 409.387L671.88 411.286C671.871 413.063 671.505 414.82 670.803 416.453L668.436 421.978C668.16 422.624 668.458 423.371 669.103 423.647 669.262 423.715 669.432 423.75 669.604 423.75 669.703 423.75 669.802 423.738 669.898 423.715 670.111 423.664 671.319 423.372 673.173 422.846 673.936 427.753 676.586 432.167 680.556 435.149L680.556 438.902C680.559 439.934 679.935 440.864 678.979 441.253L672.682 443.838C666.943 445.891 661.489 448.235 656.909 451.982 654.272 454.04 652.695 457.171 652.611 460.515L650.396 478.636C650.106 480.963 651.142 483.256 653.079 484.577 655.704 486.259 658.536 487.593 661.504 488.545L661.504 485.866C659.039 485.023 656.686 483.882 654.497 482.468 653.352 481.678 652.743 480.315 652.92 478.935L655.141 460.762 655.15 460.635C655.202 458.021 656.432 455.57 658.497 453.967 662.768 450.472 667.943 448.237 673.416 446.272L676.06 445.346C679.498 447.717 685.506 449.171 692 449.171 698.492 449.171 704.5 447.717 707.938 445.346ZM673.139 417.455C673.975 415.511 674.412 413.418 674.423 411.302L674.434 409.403C674.434 407.854 674.675 406.314 675.147 404.839 677.66 397.147 684.374 391.979 691.853 391.979 692.848 391.981 693.84 392.075 694.818 392.26 695.086 392.327 695.317 392.497 695.461 392.734L696.595 394.417C696.987 394.999 697.777 395.153 698.359 394.761 698.378 394.748 698.398 394.734 698.416 394.72L699.439 393.946C699.48 393.912 699.536 393.902 699.586 393.921 704.563 396.286 708.133 400.861 709.216 406.264L709.217 406.264C709.572 408.19 710.049 410.092 710.645 411.958L711.165 413.52C708.476 411.997 705.311 408.037 703.616 405.335 703.396 404.984 703.018 404.762 702.604 404.741 702.189 404.717 701.789 404.9 701.536 405.23 695.179 413.403 678.203 418.788 671.799 420.582ZM675.643 422.115C683.116 419.816 695.943 415.085 702.415 408.113 704.113 410.628 706.171 412.88 708.524 414.797L708.524 419.94C708.529 429.06 701.141 436.456 692.022 436.462 683.735 436.467 676.729 430.329 675.643 422.114ZM692.001 446.628C687.492 446.739 683.013 445.855 678.884 444.039L679.944 443.604C681.854 442.825 683.102 440.965 683.097 438.902L683.097 436.77C688.656 439.741 695.33 439.748 700.896 436.789L700.896 438.902C700.891 440.965 702.138 442.825 704.049 443.604L705.112 444.041C700.985 445.856 696.508 446.739 692.001 446.628Z" fill="#000000" fill-rule="nonzero" fill-opacity="1"/><path d="M719.963 461.29C719.956 458.799 717.931 456.785 715.439 456.792 715.435 456.792 715.431 456.792 715.427 456.792L668.546 456.792C666.062 456.794 664.049 458.807 664.047 461.29L664.047 490.075 655.151 490.075 655.151 492.965C655.168 495.441 657.173 497.444 659.65 497.458L724.365 497.458C726.842 497.442 728.845 495.436 728.859 492.96L728.859 490.075 719.963 490.075ZM726.317 492.616 726.317 492.955C726.311 494.034 725.439 494.907 724.36 494.917L659.654 494.917C658.576 494.91 657.702 494.039 657.692 492.96L657.692 492.616 666.588 492.616 666.588 461.29C666.589 460.21 667.465 459.335 668.545 459.333L715.464 459.333C716.545 459.335 717.42 460.21 717.422 461.29L717.422 492.616Z" fill="#000000" fill-rule="nonzero" fill-opacity="1"/><path d="M683.633 469.538 676.503 476.668 683.633 483.797 685.425 482.005 680.1 476.668 685.425 471.33 683.633 469.538Z" fill="#000000" fill-rule="nonzero" fill-opacity="1"/><path d="M698.54 471.33 703.865 476.668 698.54 482.005 700.332 483.797 707.461 476.668 700.332 469.538 698.54 471.33Z" fill="#000000" fill-rule="nonzero" fill-opacity="1"/><path d="M687.814 483.708 690.165 484.686 696.112 470.301 693.774 469.322 687.814 483.708Z" fill="#000000" fill-rule="nonzero" fill-opacity="1"/></g></g></g></g></g></svg>