Skip to content

Agent Zero AI framework

img fix + knowledge_tool

Alessandro24542faf6764
diff --git a/README.md b/README.md
index 0887be3e7..fdc0260b1 100644
--- a/README.md
+++ b/README.md
@@ -55,7 +55,7 @@
- No coding is required, only prompting and communication skills.
- With a solid system prompt, the framework is reliable even with small models, including precise tool usage.
-![Agent 1 System Load](/docs/res/ui_screen1.png)
+![Agent 1 System Load](/docs/res/ui_screen.png)
## Keep in mind
1. **Agent Zero can be dangerous!**
@@ -85,17 +85,26 @@ If you cannot provide all the necessary conditions or API keys, just change the
![Time example](/docs/res/time_example.jpg)
## Setup
-A detailed setup guide with a video can be found in /docs/installation.md. Open the [Documentation](docs/installation.md#in-depth-guide-for-windows-and-macos).
+A detailed setup guide for Windows, macOS and Linux with a video can be found in the new Agent Zero Documentation at [this page](docs/installation.md#in-depth-guide-for-windows-and-macos).
-## Changelog [since version 0.7]
+## Consult the Documentation
+The documentation dives deep into the framework and its features. It is a good place to start if you are new to Agent Zero. Click [here](docs/README.md) to see the Documentation.
-### v0.7.1
+## Coming up
+- **Preinstalled bundles**
+- **Knowledge tool open-sourcing and web scraping tool**
+- **User interaction refinements**
+- **In-context switchable LLMs**
+
+### Changelog [since version 0.7]
+
+#### v0.7.1
- **Bug Fixes**
- **Persistent Chats** - Serialized to /tmp/chats and automatically loaded in run_ui.py on startup
- **Preinstalled binaries and bundler scripts**
- **Documentation stack merged into the repository**
-### New in version 0.7
+#### New in version 0.7
> - UI Revamp
> - Auto Memory
> - Instruments
@@ -105,9 +114,4 @@ A detailed setup guide with a video can be found in /docs/installation.md. Open
> [!NOTE]
> **Changes to launch files since v0.6:**
> - main.py file has been replaced with run_ui.py (webui) and run_cli.py (terminal) launch files.
-> - configuration has been moved to initialize.py for both webui and terminal launch files.
-
-## Coming up
-- **Preinstalled bundles**
-- **Knowledge tool improvements and web scraping tool**
-- **User interaction refinements**
\ No newline at end of file
+> - configuration has been moved to initialize.py for both webui and terminal launch files.
\ No newline at end of file
diff --git a/docs/architecture.md b/docs/architecture.md
index 047b40db8..325eaf2e5 100644
--- a/docs/architecture.md
+++ b/docs/architecture.md
@@ -69,6 +69,18 @@ The memory system is a critical component of Agent Zero, enabling the agent to l
| memory_tool | Enables agents to save, load, delete and forget information from memory. |
| webpage_content_tool | Enables agents to fetch and analyze the text content of webpages. |
+- **Knowledge Tool:** The `knowledge_tool` uses DuckDuckGo and Perplexity APIs to search the web and retrieve information. It can also search the local knowledge base and memory for relevant information. The tool returns a summary of the information, which can be used by the agent to make decisions or answer questions.
+
+> [!TIP]
+> The Perplexity API key is the only service recommended for a full experience of
+> Agent Zero, but you can use DuckDuckGo by leaving the Perplexity API key value
+> empty. DuckDuckGo usage in Agent Zero is free of charge but has its rate limits.
+
+> [!NOTE]
+> It's important to note that the DuckDuckGo API is not as powerful as Perplexity
+> and may not return accurate or relevant results for some queries. The Perplexity
+> API is yet to be replaced with an open-source alternative.
+
- **Custom Tools:** Users can create custom tools to extend Agent Zero's capabilities. Custom tools can be integrated into the framework by defining a tool specification, which includes the tool's prompt to be placed in `/prompts/$FOLDERNAME/agent.system.tool.$TOOLNAME.md`, as further detailed [here](#adding-tools).
- **Tools vs. Instruments:** Tools are always present in system prompt, so you should keep them to minimum. To save yourself some tokens, use the [Instruments module](#adding-instruments) to call custom scripts or functions.
diff --git a/docs/res/ui_screen.png b/docs/res/ui_screen.png
new file mode 100644
index 000000000..90bb5ab31
Binary files /dev/null and b/docs/res/ui_screen.png differ
diff --git a/docs/res/ui_screen1.png b/docs/res/ui_screen1.png
deleted file mode 100644
index 1b32397c0..000000000
Binary files a/docs/res/ui_screen1.png and /dev/null differ
diff --git a/docs/usage.md b/docs/usage.md
index 72364ba38..f87719172 100644
--- a/docs/usage.md
+++ b/docs/usage.md
@@ -74,7 +74,7 @@ app.run(request_handler=NoRequestLoggingWSGIRequestHandler, host="0.0.0.0", port
## Using code_execution_tool outside of the Docker Container
> [!CAUTION]
-> VERY IMPORTANT NOTICE: We believe in safe and ethical AI development, and highly
+> We believe in safe and ethical AI development, and highly
> suggest you to use the Docker container designed for running Agent Zero.
> This is a dangerous and untested feature, and we are not responsible for any damage
> or illegal activities or legal liabilities caused by the use of this feature.