From 641229cb648f1467a9dd0c7a1417250e4b29e561 Mon Sep 17 00:00:00 2001 From: rickyloynd-microsoft Date: Thu, 7 Mar 2024 09:24:07 -0800 Subject: [PATCH] Fix links --- notebook/agentchat_teachability.ipynb | 102 +++++++++--------- .../blog/2023-10-26-TeachableAgent/index.mdx | 4 +- 2 files changed, 53 insertions(+), 53 deletions(-) diff --git a/notebook/agentchat_teachability.ipynb b/notebook/agentchat_teachability.ipynb index 3785f01fe93f..252ff92c63d4 100644 --- a/notebook/agentchat_teachability.ipynb +++ b/notebook/agentchat_teachability.ipynb @@ -21,7 +21,7 @@ "\n", "In making decisions about memo storage and retrieval, `Teachability` calls an instance of `TextAnalyzerAgent` to analyze pieces of text in several different ways. This adds extra LLM calls involving a relatively small number of tokens. These calls can add a few seconds to the time a user waits for a response.\n", "\n", - "This notebook demonstrates how `Teachability` can be added to an agent so that it can learn facts, preferences, and skills from users. To chat with a teachable agent yourself, run [chat_with_teachable_agent.py](../test/agentchat/contrib/chat_with_teachable_agent.py).\n", + "This notebook demonstrates how `Teachability` can be added to an agent so that it can learn facts, preferences, and skills from users. To chat with a teachable agent yourself, run [chat_with_teachable_agent.py](../test/agentchat/contrib/capabilities/chat_with_teachable_agent.py).\n", "\n", "## Requirements\n", "\n", @@ -138,8 +138,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[92m\n", - "CLEARING MEMORY\u001b[0m\n" + "\u001B[92m\n", + "CLEARING MEMORY\u001B[0m\n" ] } ], @@ -191,14 +191,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "What is the Vicuna model?\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "The term \"Vicuna model\" does not point to a well-known concept or framework in the realms of science, technology, or social sciences as of my last knowledge update in early 2023. It's possible that the term could be a reference to a proprietary model or a concept that has emerged after my last update or it might be a misspelling or a misunderstanding.\n", "\n", @@ -224,14 +224,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Vicuna is a 13B-parameter language model released by Meta.\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "My apologies for the confusion. As of my last update, the Vicuna model had not been part of my database. If Vicuna is indeed a 13-billion-parameter language model developed by Meta (formerly Facebook Inc.), then it would be one of the large-scale transformer-based models akin to those like GPT-3 by OpenAI.\n", "\n", @@ -261,14 +261,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "What is the Orca model?\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "As of my last update, the Orca model appears to reference a new development that I do not have extensive information on, similar to the earlier reference to the Vicuna model.\n", "\n", @@ -294,14 +294,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Orca is a 13B-parameter language model developed by Microsoft. It outperforms Vicuna on most tasks.\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "Thank you for providing the context about the Orca model. Based on the new information you've given, Orca is a language model with 13 billion parameters, similar in size to Meta's Vicuna model, but developed by Microsoft. If it outperforms Vicuna on most tasks, it suggests that it could have been trained on a more diverse dataset, use a more advanced architecture, have more effective training techniques, or some combination of these factors.\n", "\n", @@ -336,14 +336,14 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "How does the Vicuna model compare to the Orca model?\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "The Vicuna model and the Orca model are both large-scale language models with a significant number of parameters—13 billion, to be exact.\n", "\n", @@ -379,7 +379,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Please summarize this abstract.\n", "\n", @@ -389,9 +389,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "AutoGen is an open-source framework designed to facilitate the creation of applications using large language models (LLMs) through the use of multiple conversational agents. These agents can be tailored to users' needs and are capable of interaction in multiple modes, including with other LLMs, human input, and additional tools. With AutoGen, developers have the flexibility to program agent interactions using both natural language and code, enabling the creation of complex patterns suitable for a wide range of applications. The framework has been proven effective across various fields, such as math, coding, question answering, and entertainment, based on empirical studies conducted to test its capabilities.\n", "\n", @@ -425,7 +425,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Please summarize this abstract. \n", "When I'm summarizing an abstract, I try to make the summary contain just three short bullet points: the title, the innovation, and the key empirical results.\n", @@ -436,9 +436,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "- Title: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation\n", "- Innovation: AutoGen, an open-source framework that supports building large language model (LLM) applications by enabling conversation among multiple customizable and conversable agents.\n", @@ -475,7 +475,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Please summarize this abstract.\n", "\n", @@ -484,9 +484,9 @@ "Artificial intelligence (AI) researchers have been developing and refining large language models (LLMs) that exhibit remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. The latest model developed by OpenAI, GPT-4, was trained using an unprecedented scale of compute and data. In this paper, we report on our investigation of an early version of GPT-4, when it was still in active development by OpenAI. We contend that (this early version of) GPT-4 is part of a new cohort of LLMs (along with ChatGPT and Google's PaLM for example) that exhibit more general intelligence than previous AI models. We discuss the rising capabilities and implications of these models. We demonstrate that, beyond its mastery of language, GPT-4 can solve novel and difficult tasks that span mathematics, coding, vision, medicine, law, psychology and more, without needing any special prompting. Moreover, in all of these tasks, GPT-4's performance is strikingly close to human-level performance, and often vastly surpasses prior models such as ChatGPT. Given the breadth and depth of GPT-4's capabilities, we believe that it could reasonably be viewed as an early (yet still incomplete) version of an artificial general intelligence (AGI) system. In our exploration of GPT-4, we put special emphasis on discovering its limitations, and we discuss the challenges ahead for advancing towards deeper and more comprehensive versions of AGI, including the possible need for pursuing a new paradigm that moves beyond next-word prediction. We conclude with reflections on societal influences of the recent technological leap and future research directions.\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "- Title: Sparks of Artificial General Intelligence: Early experiments with GPT-4\n", "\n", @@ -526,7 +526,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Consider the identity: \n", "9 * 4 + 6 * 6 = 72\n", @@ -535,9 +535,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "To solve this problem, we need to find a way to add exactly 27 (since 99 - 72 = 27) to the left hand side of the equation by modifying only one of the integers in the equation. \n", "\n", @@ -602,7 +602,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Consider the identity: \n", "9 * 4 + 6 * 6 = 72\n", @@ -623,9 +623,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "Given the new set of instructions and the correction that according to a past memory, the solution is \"9 * 1 + 6 * 9\", let's follow the steps carefully to arrive at the correct modified equation.\n", "\n", @@ -707,7 +707,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Consider the identity: \n", "9 * 4 + 6 * 6 = 72\n", @@ -716,9 +716,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "Let's apply the steps you've provided to solve the problem at hand:\n", "\n", @@ -779,7 +779,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "\u001b[33muser\u001b[0m (to teachable_agent):\n", + "\u001B[33muser\u001B[0m (to teachable_agent):\n", "\n", "Consider the identity: \n", "8 * 3 + 7 * 9 = 87\n", @@ -788,9 +788,9 @@ "\n", "\n", "--------------------------------------------------------------------------------\n", - "\u001b[31m\n", - ">>>>>>>> USING AUTO REPLY...\u001b[0m\n", - "\u001b[33mteachable_agent\u001b[0m (to user):\n", + "\u001B[31m\n", + ">>>>>>>> USING AUTO REPLY...\u001B[0m\n", + "\u001B[33mteachable_agent\u001B[0m (to user):\n", "\n", "Let's apply the plan step-by-step to find the correct modification:\n", "\n", diff --git a/website/blog/2023-10-26-TeachableAgent/index.mdx b/website/blog/2023-10-26-TeachableAgent/index.mdx index 63a607cb3e5a..6d687fd4bb76 100644 --- a/website/blog/2023-10-26-TeachableAgent/index.mdx +++ b/website/blog/2023-10-26-TeachableAgent/index.mdx @@ -24,9 +24,9 @@ In order to make effective decisions about memo storage and retrieval, the `Teac AutoGen contains four code examples that use `Teachability`. -1. Run [chat_with_teachable_agent.py](https://github.com/microsoft/autogen/blob/main/test/agentchat/contrib/chat_with_teachable_agent.py) to converse with a teachable agent. +1. Run [chat_with_teachable_agent.py](https://github.com/microsoft/autogen/blob/main/test/agentchat/contrib/capabilities/chat_with_teachable_agent.py) to converse with a teachable agent. -2. Run [test_teachable_agent.py](https://github.com/microsoft/autogen/blob/main/test/agentchat/contrib/test_teachable_agent.py) for quick unit testing of a teachable agent. +2. Run [test_teachable_agent.py](https://github.com/microsoft/autogen/blob/main/test/agentchat/contrib/capabilities/test_teachable_agent.py) for quick unit testing of a teachable agent. 3. Use the Jupyter notebook [agentchat_teachability.ipynb](https://github.com/microsoft/autogen/blob/main/notebook/agentchat_teachability.ipynb) to step through examples discussed below.