Skip to content

Building AI agents, atomically

Update README.md and system_prompt_generator.py + cleanup

KennyVaneetvelde1e03b139eeee
diff --git a/.assets/what_is_sent_in_prompt.png b/.assets/what_is_sent_in_prompt.png
new file mode 100644
index 0000000..94eaca7
Binary files /dev/null and b/.assets/what_is_sent_in_prompt.png differ
diff --git a/README.md b/README.md
index 1dcd53f..81f980a 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,7 @@ The Atomic Agents framework is designed to be modular, extensible, and easy to u
<!-- ![alt text](./.assets/architecture_highlevel_overview.png) -->
<img src="./.assets/architecture_highlevel_overview.png" alt="Atomic Agents Architecture" width="600"/>
+<img src="./.assets/what_is_sent_in_prompt.png" alt="What is sent to the LLM in the prompt?" width="600"/>
## Installation
To install Atomic Agents, you can use pip:
diff --git a/atomic_agents/lib/components/system_prompt_generator.py b/atomic_agents/lib/components/system_prompt_generator.py
index 39f467d..0173811 100644
--- a/atomic_agents/lib/components/system_prompt_generator.py
+++ b/atomic_agents/lib/components/system_prompt_generator.py
@@ -80,7 +80,7 @@ if __name__ == "__main__":
output_instructions=[
'Provide helpful and relevant information to assist the user.',
'Be friendly and respectful in all interactions.',
- 'Always answer in rhyming verse. Preferably in alexandrine verse.'
+ 'Always answer in rhyming verse.'
],
context_providers={
'date': CurrentDateProvider(title='Current date', format='%Y-%m-%d %H:%M:%S'),
diff --git a/examples/basic_custom_chatbot.py b/examples/basic_custom_chatbot.py
index ea75365..80d5936 100644
--- a/examples/basic_custom_chatbot.py
+++ b/examples/basic_custom_chatbot.py
@@ -21,7 +21,7 @@ system_prompt = SystemPromptInfo(
output_instructions=[
'Provide helpful and relevant information to assist the user.',
'Be friendly and respectful in all interactions.',
- 'Always answer in rhyming verse. Preferably in alexandrine verse.'
+ 'Always answer in rhyming verse.'
]
)
# Initialize the system prompt generator with the defined system prompt and dynamic info providers
diff --git a/examples/notebooks/quickstart.ipynb b/examples/notebooks/quickstart.ipynb
index 445f7b5..94c6c70 100644
--- a/examples/notebooks/quickstart.ipynb
+++ b/examples/notebooks/quickstart.ipynb
@@ -11,6 +11,20 @@
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/KennyVaneetvelde/atomic_agents/blob/main/examples/notebooks/quickstart.ipynb#)\n"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Prerequisites\n",
+ "\n",
+ "Before proceeding with this notebook, it is highly recommended to read up on the basics of the following libraries:\n",
+ "\n",
+ "- **Pydantic**: A data validation and settings management library using Python type annotations. You can find more information and documentation at [Pydantic GitHub](https://github.com/pydantic/pydantic).\n",
+ "- **Instructor**: A Python library that simplifies working with structured outputs from large language models (LLMs). It provides a user-friendly API to manage validation, retries, and streaming responses. More details can be found at [Instructor GitHub](https://github.com/jxnl/instructor).\n",
+ "\n",
+ "Understanding these libraries will help you make the most of this library.\n"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -63,7 +77,9 @@
"## Step 3: Define System Prompt Information\n",
"\n",
"We will define the system prompt information including background, steps, and output instructions. This helps the chatbot understand how to respond to user inputs.\n",
- "In this example, we will define a system prompt that asks the chatbot to respond to user inputs in rhyming verse."
+ "In this example, we will define a system prompt that asks the chatbot to respond to user inputs in rhyming verse.\n",
+ "\n",
+ "The structuring of the system prompts in this library is loosely inspired by Patterns in the [Fabric library](https://github.com/danielmiessler/fabric/tree/main/patterns)."
]
},
{
@@ -156,7 +172,8 @@
"source": [
"## Step 6: Main Chat Loop\n",
"\n",
- "We will create a main chat loop for testing the chat agent. This loop will allow you to interact with the chatbot in real-time."
+ "We will create a main chat loop for testing the chat agent. This loop will allow you to interact with the chatbot in real-time.\n",
+ "To exit the loop, type `/exit` or `/quit`."
]
},
{
diff --git a/examples/simple_yt_agent.py b/examples/simple_yt_agent.py
index b945637..ab586e6 100644
--- a/examples/simple_yt_agent.py
+++ b/examples/simple_yt_agent.py
@@ -6,9 +6,7 @@ from rich.console import Console
from rich.markdown import Markdown
from atomic_agents.agents.base_chat_agent import BaseChatAgent
-from atomic_agents.agents.tool_interface_agent import ToolInterfaceAgent
from atomic_agents.lib.components.system_prompt_generator import SystemPromptContextProviderBase, SystemPromptGenerator, SystemPromptInfo
-from atomic_agents.lib.tools.search.searx_tool import SearxNGSearchTool
from atomic_agents.lib.tools.yt_transcript_scraper import YouTubeTranscriptTool, YouTubeTranscriptToolConfig, YouTubeTranscriptToolSchema
console = Console()
@@ -86,7 +84,6 @@ transcript_provider.transcript = scraped_transcript.transcript
transcript_provider.duration = scraped_transcript.duration
transcript_provider.metadata = scraped_transcript.metadata
-# agent.memory.add_message('assistant', 'I have successfully extracted the transcript and put it in the context of the system prompt. I will now use it to generate a detailed response following the rules and steps provided in the system prompt. Here is the output:')
response = agent.run('Perform your assignment on the YouTube video transcript present in your context. Do not reply with anything other than the output of the assignment.')
# Convert the ResponseModel to a dictionary and then to a Markdown string