KeyArgo
/
smolagents
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Refine doc

This commit is contained in:
Aymeric 2024-12-22 22:09:53 +01:00
parent 773008524c
commit 3a28bda490
4 changed files with 19 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -25,11 +25,9 @@ limitations under the License.
</p>
<h3 align="center">
<p>Run agents!</p>
<p>Agents - build great agents!</p>
</h3>
# Agents
Agents is a library that enables you to run powerful agents in a few lines of code!
It is:
- lightweight

23
docs/source/conceptual_guides/intro_agents.md
View File

@ -52,26 +52,31 @@ Programs are not just tools anymore, confined to an ultra-specialized task : the
### When to use an agentic system ?
Given the definition above, agents are useful when you need an LLM to help you determine the workflow of an app.
You should regularize to not use any agentic behaviour.
Agents are useful when you need an LLM to help you determine the workflow of an app.
For intance, let's say you're making an app that handles customer requests on a surfing trip website.
It's advise to regularize towards not using any agentic behaviour.
Ask yourself: do I really need flexibility in the workflow to efficiently solve the task at hand? If a fixed workflow would work, you might as well build it all in good old no-AI code for 100% robustness. Agents are useful when the ficed workflow is not enough.
If you know in advance that the requests will have to be classified in either of 2 buckets according to deterministic criteria, and you have a predefined workflow for each of these 2 cases, then this means you can make a fixed workflow.
For instance, if you let the user click a button to determine their query, and it goes into either of these:
Let's take an example: say you're making an app that handles customer requests on a surfing trip website.
You could know in advance that the requests will have to be classified in either of 2 buckets according to deterministic criteria, and you have a predefined workflow for each of these 2 cases.
For instance, this is if you let the user click a button to determine their query, and it goes into either of these buckets:
1. Want some knowledge on the trips. Then you give them access to a search bar to search your knowledge base
2. Wants to talk to sales. Then you let them type in a contact form.
If that deterministic workflow fits all queries, by all means just hardcode verything: this will give you a 100% reliable system with no risk of error introduced by letting unpredictable LLMs meddle in your workflow.
If that deterministic workflow fits all queries, by all means just code verything: this will give you a 100% reliable system with no risk of error introduced by letting unpredictable LLMs meddle in your workflow.
But what if the workflow can't be determined that well in advance? Say, 10% or 20% of users requests won't fit properly into your rigid categories, and risk being mishandled by the program?
But what if the workflow can't be determined that well in advance? Say, 10% or 20% of users requests do not fit properly into your rigid categories, and are thus not handled properly by your program?
Let's say, a user wants to ask : "I can come on Monday, but I forgot my passport so risk being delayed to Wednesday, is it possible to take me and my stuff to surf on Tuesday morning, with a concellation insurance?"
This question into play many factors: availability of employees, weather, travelling distance, knowledge about cancellation policies...
Probably none of the predetermined criteria above won't work properly.
Probably none of the predetermined criteria above won't work properly on this question.
That percentage of "won't fit in a predetermined workflow" means that you need more flexibility: making your system agentic will provide it that flexibility. In our example, you could just make a multi-step agent that has access to a weather API tool, a google maps API to compute travel distance, an employee availability dashboard and a RAG system on your knowledge base.
If these cases where the predetermined workflow falls short are frequent, that means you need more flexibility: making your system agentic will provide it that flexibility. In our example, you could just make a multi-step agent that has access to a weather API tool, a google maps API to compute travel distance, an employee availability dashboard and a RAG system on your knowledge base.
Actually, most real-life tasks do not fit in a pre-determined workflow. This is why until today, our programs where always focused on infinitely narrow tasks, like "compute the sum of these numbers" or "find the shortest path in this graph".
Agentic systems are a great way to introduce the vast world of real-world tasks to programs!
### Why {Agents}?

2
docs/source/guided_tour.md
View File

@ -17,7 +17,7 @@ rendered properly in your Markdown viewer.
[[open-in-colab]]
This visit of your framework should take about 15 minutes. It will show you how to build an agent, how to run it, and how to customize it to make it work better for your use-case. For more in-depth use, you will then want to check out our tutorials like [Building good agents](./tutorials/building_good_agents).
This visit of your framework should take about 15 minutes. It will show you how to build an agent, how to run it, and how to customize it to make it work better for your use-case. For more in-depth usage, you will then want to check out our tutorials like [Building good agents](./tutorials/building_good_agents).
### Building your agent

7
docs/source/index.md
View File

@ -15,10 +15,9 @@ rendered properly in your Markdown viewer.
# Agents
This library is the simplest framework out there to build powerful agents!
In particular, it has first-class support for Code Agents, i.e. agents that write their actions in code (as opposed to "agents being used to write code", which many good libraries do).
This library is the simplest framework out there to build powerful agents! By the way, wtf are "agents"? We provide our definition [in this page](conceptual_guides/intro_agents), whe're you'll also find tips for when to use them or not (spoilers: you'll often be better off without agents).
Amongst other things, this library provides first-class support for Code Agents, i.e. agents that write their actions in code (as opposed to "agents being used to write code", which many good libraries already do), [read more here](tutorials/secure_code_execution).
<div class="mt-10">
<div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-2 md:gap-y-4 md:gap-x-5">
@ -32,7 +31,7 @@ In particular, it has first-class support for Code Agents, i.e. agents that writ
</a>
<a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./conceptual_guides/intro_agents"
><div class="w-full text-center bg-gradient-to-br from-pink-400 to-pink-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Conceptual guides</div>
<p class="text-gray-700">High-level explanations for building a better understanding of important topics to build better functioning agents.</p>
<p class="text-gray-700">High-level explanations for building a better understanding of important topics.</p>
</a>
<a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./tutorials/building_good_agents"
><div class="w-full text-center bg-gradient-to-br from-purple-400 to-purple-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Tutorials</div>