aboutsummaryrefslogtreecommitdiffstats
path: root/README.md
diff options
context:
space:
mode:
authorsigoden <sigoden@gmail.com>2024-06-22 06:52:45 +0800
committerGitHub <noreply@github.com>2024-06-22 06:52:45 +0800
commitadfb7c2b49ba4ba691e89683afa700eabbb3388c (patch)
tree730829361b85a15e5dd0d323ae185c00068ce053 /README.md
parenta799428b397ac7789a91cf94a9c408ee8a2dd6e2 (diff)
downloadllm-functions-docker-adfb7c2b49ba4ba691e89683afa700eabbb3388c.tar.gz
refactor: rename bot to agent (#44)
Diffstat (limited to 'README.md')
-rw-r--r--README.md32
1 files changed, 16 insertions, 16 deletions
diff --git a/README.md b/README.md
index 20f854e..9690a69 100644
--- a/README.md
+++ b/README.md
@@ -17,7 +17,7 @@ Make sure you have the following tools installed:
git clone https://github.com/sigoden/llm-functions
```
-**2. Build tools and bots:**
+**2. Build tools and agents:**
- Create a `./tools.txt` file with each tool filename on a new line.
@@ -26,14 +26,14 @@ get_current_weather.sh
may_execute_py_code.py
```
-- Create a `./bots.txt` file with each bot name on a new line.
+- Create a `./agents.txt` file with each agent name on a new line.
```
todo-sh
hackernews
```
-- Run `argc build` to build functions declarations files (`functions.json`) and binaries (`./bin`) for tools and bots.
+- Run `argc build` to build functions declarations files (`functions.json`) and binaries (`./bin`) for tools and agents.
**3. Configure your AIChat:**
@@ -63,7 +63,7 @@ Now you can interact with your LLM using natural language prompts that trigger y
![execute-type-showcase](https://github.com/sigoden/llm-functions/assets/4012553/1dbc345f-daf9-4d65-a49f-3df8c7df1727)
-![bot-showcase](https://github.com/sigoden/llm-functions/assets/4012553/b4411eeb-d79c-4245-8ec2-dd424ba25621)
+![agent-showcase](https://github.com/sigoden/llm-functions/assets/4012553/b4411eeb-d79c-4245-8ec2-dd424ba25621)
## Writing Your Own Tools
@@ -122,32 +122,32 @@ def main(code: str):
```
-## Writing Bots
+## Writing Agents
-Bot = Prompt + Tools (Function Callings) + Knowndge (RAG). It's also known as OpenAI's GPTs.
+Agent = Prompt + Tools (Function Callings) + Knowndge (RAG). It's also known as OpenAI's GPTs.
-The bot has the following folder structure:
+The agent has the following folder structure:
```
-└── bots
- └── mybot
+└── agents
+ └── myagent
├── embeddings/ # Contains RAG files for knownledge
├── functions.json # Function declarations file (Auto-generated)
- ├── index.yaml # Bot definition file
- └── tools.{sh,js,py} # Bot tools script
+ ├── index.yaml # Agent definition file
+ └── tools.{sh,js,py} # Agent tools script
```
-The bot definition file (`index.yaml`) defines crucial aspects of your bot:
+The agent definition file (`index.yaml`) defines crucial aspects of your agent:
```yaml
-name: TestBot
-description: This is test bot
+name: TestAgent
+description: This is test agent
version: v0.1.0
-instructions: You are a test bot to ...
+instructions: You are a test agent to ...
conversation_starters:
- What can you do?
```
-Refer to `./bots/todo-{sh,js,py}` for examples of how to implement a bot.
+Refer to `./agents/todo-{sh,js,py}` for examples of how to implement a agent.
## License