You may use the button above to open this repo in a Codespace
-For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
-
+For more info, check out
+the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
+
## VS Code Dev Containers
+
-Note: If you click this link you will open the main repo and not your local cloned repo, you can use this link and replace with your username and cloned repo name:
+Note: If you click this link you will open the main repo and not your local cloned repo, you can use this link and
+replace with your username and cloned repo name:
https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/geekan/MetaGPT
-
-If you already have VS Code and Docker installed, you can use the button above to get started. This will cause VS Code to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin up a dev container for use.
+If you already have VS Code and Docker installed, you can use the button above to get started. This will cause VS Code
+to automatically install the Dev Containers extension if needed, clone the source code into a container volume, and spin
+up a dev container for use.
You can also follow these steps to open this repo in a container using the VS Code Dev Containers extension:
-1. If this is your first time using a development container, please ensure your system meets the pre-reqs (i.e. have Docker installed) in the [getting started steps](https://aka.ms/vscode-remote/containers/getting-started).
+1. If this is your first time using a development container, please ensure your system meets the pre-reqs (i.e. have
+ Docker installed) in the [getting started steps](https://aka.ms/vscode-remote/containers/getting-started).
2. Open a locally cloned copy of the code:
- - Fork and Clone this repository to your local filesystem.
- - Press F1 and select the **Dev Containers: Open Folder in Container...** command.
- - Select the cloned copy of this folder, wait for the container to start, and try things out!
+ - Fork and Clone this repository to your local filesystem.
+ - Press F1 and select the **Dev Containers: Open Folder in Container...** command.
+ - Select the cloned copy of this folder, wait for the container to start, and try things out!
You can learn more in the [Dev Containers documentation](https://code.visualstudio.com/docs/devcontainers/containers).
## Tips and tricks
-* If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will disable line ending conversion and should prevent this. See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files) for more info.
-* If you'd like to review the contents of the image used in this dev container, you can check it out in the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.
+* If you are working with the same repository folder in a container and Windows, you'll want consistent line endings (
+ otherwise you may see hundreds of changes in the SCM view). The `.gitattributes` file in the root of this repo will
+ disable line ending conversion and should prevent this.
+ See [tips and tricks](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files)
+ for more info.
+* If you'd like to review the contents of the image used in this dev container, you can check it out in
+ the [devcontainers/images](https://github.com/devcontainers/images/tree/main/src/python) repo.
diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index a774d0ed1..6ad3b598d 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -1,27 +1,25 @@
// For format details, see https://aka.ms/devcontainer.json. For config options, see the
// README at: https://github.com/devcontainers/templates/tree/main/src/python
{
- "name": "Python 3",
- // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
- "image": "mcr.microsoft.com/devcontainers/python:0-3.11",
+ "name": "Python 3",
+ // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+ "image": "mcr.microsoft.com/devcontainers/python:0-3.11",
+ // Features to add to the dev container. More info: https://containers.dev/features.
+ // "features": {},
- // Features to add to the dev container. More info: https://containers.dev/features.
- // "features": {},
+ // Configure tool-specific properties.
+ "customizations": {
+ // Configure properties specific to VS Code.
+ "vscode": {
+ "settings": {},
+ "extensions": [
+ "streetsidesoftware.code-spell-checker"
+ ]
+ }
+ },
+ // Use 'postCreateCommand' to run commands after the container is created.
+ "postCreateCommand": "./.devcontainer/postCreateCommand.sh"
- // Configure tool-specific properties.
- "customizations": {
- // Configure properties specific to VS Code.
- "vscode": {
- "settings": {},
- "extensions": [
- "streetsidesoftware.code-spell-checker"
- ]
- }
- },
-
- // Use 'postCreateCommand' to run commands after the container is created.
- "postCreateCommand": "./.devcontainer/postCreateCommand.sh"
-
- // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
- // "remoteUser": "root"
+ // Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+ // "remoteUser": "root"
}
diff --git a/.devcontainer/docker-compose.yaml b/.devcontainer/docker-compose.yaml
index a9988b1f3..2f0116bf8 100644
--- a/.devcontainer/docker-compose.yaml
+++ b/.devcontainer/docker-compose.yaml
@@ -5,10 +5,10 @@ services:
dockerfile: Dockerfile
context: ..
volumes:
- # Update this to wherever you want VS Code to mount the folder of your project
+ # Update this to wherever you want VS Code to mount the folder of your project
- ..:/workspaces:cached
networks:
- - metagpt-network
+ - metagpt-network
# environment:
# MONGO_ROOT_USERNAME: root
# MONGO_ROOT_PASSWORD: example123
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index b1892a709..db11ddbb5 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -8,11 +8,11 @@ repos:
rev: 5.11.5
hooks:
- id: isort
- args: ['--profile', 'black']
+ args: [ '--profile', 'black' ]
exclude: >-
- (?x)^(
- .*__init__\.py$
- )
+ (?x)^(
+ .*__init__\.py$
+ )
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
@@ -24,4 +24,4 @@ repos:
rev: 23.3.0
hooks:
- id: black
- args: ['--line-length', '120']
\ No newline at end of file
+ args: [ '--line-length', '120' ]
\ No newline at end of file
diff --git a/README.md b/README.md
index c326190b0..19869a34f 100644
--- a/README.md
+++ b/README.md
@@ -25,9 +25,11 @@ # MetaGPT: The Multi-Agent Framework
-1. MetaGPT takes a **one line requirement** as input and outputs **user stories / competitive analysis / requirements / data structures / APIs / documents, etc.**
-2. Internally, MetaGPT includes **product managers / architects / project managers / engineers.** It provides the entire process of a **software company along with carefully orchestrated SOPs.**
- 1. `Code = SOP(Team)` is the core philosophy. We materialize SOP and apply it to teams composed of LLMs.
+1. MetaGPT takes a **one line requirement** as input and outputs **user stories / competitive analysis / requirements /
+ data structures / APIs / documents, etc.**
+2. Internally, MetaGPT includes **product managers / architects / project managers / engineers.** It provides the entire
+ process of a **software company along with carefully orchestrated SOPs.**
+ 1. `Code = SOP(Team)` is the core philosophy. We materialize SOP and apply it to teams composed of LLMs.
@@ -35,21 +37,17 @@ # MetaGPT: The Multi-Agent Framework
## MetaGPT's Abilities
-
https://github.com/geekan/MetaGPT/assets/34952977/34345016-5d13-489d-b9f9-b82ace413419
-
-
## Examples (fully generated by GPT-4)
-For example, if you type `python startup.py "Design a RecSys like Toutiao"`, you would get many outputs, one of them is data & api design
+For example, if you type `python startup.py "Design a RecSys like Toutiao"`, you would get many outputs, one of them is
+data & api design
-It costs approximately **$0.2** (in GPT-4 API fees) to generate one example with analysis and design, and around **$2.0** for a full project.
-
-
-
+It costs approximately **$0.2** (in GPT-4 API fees) to generate one example with analysis and design, and around **$2.0
+** for a full project.
## Installation
@@ -75,10 +73,12 @@ # Step 3: Clone the repository to your local machine, and install it.
**Note:**
-- If already have Chrome, Chromium, or MS Edge installed, you can skip downloading Chromium by setting the environment variable
+- If already have Chrome, Chromium, or MS Edge installed, you can skip downloading Chromium by setting the environment
+ variable
`PUPPETEER_SKIP_CHROMIUM_DOWNLOAD` to `true`.
-- Some people are [having issues](https://github.com/mermaidjs/mermaid.cli/issues/15) installing this tool globally. Installing it locally is an alternative solution,
+- Some people are [having issues](https://github.com/mermaidjs/mermaid.cli/issues/15) installing this tool globally.
+ Installing it locally is an alternative solution,
```bash
npm install @mermaid-js/mermaid-cli
@@ -91,72 +91,75 @@ # Step 3: Clone the repository to your local machine, and install it.
MMDC: "./node_modules/.bin/mmdc"
```
-- if `pip install -e.` fails with error `[Errno 13] Permission denied: '/usr/local/lib/python3.11/dist-packages/test-easy-install-13129.write-test'`, try instead running `pip install -e. --user`
+- if `pip install -e.` fails with
+ error `[Errno 13] Permission denied: '/usr/local/lib/python3.11/dist-packages/test-easy-install-13129.write-test'`,
+ try instead running `pip install -e. --user`
-- To convert Mermaid charts to SVG, PNG, and PDF formats. In addition to the Node.js version of Mermaid-CLI, you now have the option to use Python version Playwright, pyppeteer or mermaid.ink for this task.
+- To convert Mermaid charts to SVG, PNG, and PDF formats. In addition to the Node.js version of Mermaid-CLI, you now
+ have the option to use Python version Playwright, pyppeteer or mermaid.ink for this task.
- - Playwright
- - **Install Playwright**
+ - Playwright
+ - **Install Playwright**
- ```bash
- pip install playwright
- ```
+ ```bash
+ pip install playwright
+ ```
- - **Install the Required Browsers**
+ - **Install the Required Browsers**
- to support PDF conversion, please install Chrominum.
+ to support PDF conversion, please install Chrominum.
- ```bash
- playwright install --with-deps chromium
- ```
+ ```bash
+ playwright install --with-deps chromium
+ ```
- - **modify `config.yaml`**
+ - **modify `config.yaml`**
- uncomment MERMAID_ENGINE from config.yaml and change it to `playwright`
+ uncomment MERMAID_ENGINE from config.yaml and change it to `playwright`
- ```yaml
- MERMAID_ENGINE: playwright
- ```
+ ```yaml
+ MERMAID_ENGINE: playwright
+ ```
- - pyppeteer
- - **Install pyppeteer**
+ - pyppeteer
+ - **Install pyppeteer**
- ```bash
- pip install pyppeteer
- ```
+ ```bash
+ pip install pyppeteer
+ ```
- - **Use your own Browsers**
+ - **Use your own Browsers**
- pyppeteer alow you use installed browsers, please set the following envirment
-
- ```bash
- export PUPPETEER_EXECUTABLE_PATH = /path/to/your/chromium or edge or chrome
- ```
+ pyppeteer alow you use installed browsers, please set the following envirment
- please do not use this command to install browser, it is too old
+ ```bash
+ export PUPPETEER_EXECUTABLE_PATH = /path/to/your/chromium or edge or chrome
+ ```
- ```bash
- pyppeteer-install
- ```
+ please do not use this command to install browser, it is too old
- - **modify `config.yaml`**
+ ```bash
+ pyppeteer-install
+ ```
- uncomment MERMAID_ENGINE from config.yaml and change it to `pyppeteer`
+ - **modify `config.yaml`**
- ```yaml
- MERMAID_ENGINE: pyppeteer
- ```
+ uncomment MERMAID_ENGINE from config.yaml and change it to `pyppeteer`
- - mermaid.ink
- - **modify `config.yaml`**
+ ```yaml
+ MERMAID_ENGINE: pyppeteer
+ ```
- uncomment MERMAID_ENGINE from config.yaml and change it to `ink`
+ - mermaid.ink
+ - **modify `config.yaml`**
- ```yaml
- MERMAID_ENGINE: ink
- ```
+ uncomment MERMAID_ENGINE from config.yaml and change it to `ink`
- Note: this method does not support pdf export.
+ ```yaml
+ MERMAID_ENGINE: ink
+ ```
+
+ Note: this method does not support pdf export.
### Installation by Docker
@@ -212,7 +215,7 @@ # Copy the configuration file and make the necessary modifications.
```
| Variable Name | config/key.yaml | env |
-| ------------------------------------------ | ----------------------------------------- | ----------------------------------------------- |
+|--------------------------------------------|-------------------------------------------|-------------------------------------------------|
| OPENAI_API_KEY # Replace with your own key | OPENAI_API_KEY: "sk-..." | export OPENAI_API_KEY="sk-..." |
| OPENAI_API_BASE # Optional | OPENAI_API_BASE: "https://.*)(```.*?)",
- r"(.*?```python.*?\s+)?(?P.*)",
+ r"(.*?```python.*?\s+)?(?P.*)(```.*?)",
+ r"(.*?```python.*?\s+)?(?P.*)",
):
match = re.search(pattern, text, re.DOTALL)
if not match:
@@ -180,7 +180,7 @@ class OutputParser:
if start_index != -1 and end_index != -1:
# Extract the structure part
- structure_text = text[start_index : end_index + 1]
+ structure_text = text[start_index: end_index + 1]
try:
# Attempt to convert the text to a Python data type using ast.literal_eval
diff --git a/metagpt/utils/custom_decoder.py b/metagpt/utils/custom_decoder.py
index 373d16356..2a274564c 100644
--- a/metagpt/utils/custom_decoder.py
+++ b/metagpt/utils/custom_decoder.py
@@ -36,11 +36,11 @@ def py_make_scanner(context):
return parse_object((string, idx + 1), strict, _scan_once, object_hook, object_pairs_hook, memo)
elif nextchar == "[":
return parse_array((string, idx + 1), _scan_once)
- elif nextchar == "n" and string[idx : idx + 4] == "null":
+ elif nextchar == "n" and string[idx: idx + 4] == "null":
return None, idx + 4
- elif nextchar == "t" and string[idx : idx + 4] == "true":
+ elif nextchar == "t" and string[idx: idx + 4] == "true":
return True, idx + 4
- elif nextchar == "f" and string[idx : idx + 5] == "false":
+ elif nextchar == "f" and string[idx: idx + 5] == "false":
return False, idx + 5
m = match_number(string, idx)
@@ -51,11 +51,11 @@ def py_make_scanner(context):
else:
res = parse_int(integer)
return res, m.end()
- elif nextchar == "N" and string[idx : idx + 3] == "NaN":
+ elif nextchar == "N" and string[idx: idx + 3] == "NaN":
return parse_constant("NaN"), idx + 3
- elif nextchar == "I" and string[idx : idx + 8] == "Infinity":
+ elif nextchar == "I" and string[idx: idx + 8] == "Infinity":
return parse_constant("Infinity"), idx + 8
- elif nextchar == "-" and string[idx : idx + 9] == "-Infinity":
+ elif nextchar == "-" and string[idx: idx + 9] == "-Infinity":
return parse_constant("-Infinity"), idx + 9
else:
raise StopIteration(idx)
@@ -89,7 +89,7 @@ WHITESPACE_STR = " \t\n\r"
def JSONObject(
- s_and_end, strict, scan_once, object_hook, object_pairs_hook, memo=None, _w=WHITESPACE.match, _ws=WHITESPACE_STR
+ s_and_end, strict, scan_once, object_hook, object_pairs_hook, memo=None, _w=WHITESPACE.match, _ws=WHITESPACE_STR
):
"""Parse a JSON object from a string and return the parsed object.
@@ -118,12 +118,12 @@ def JSONObject(
memo_get = memo.setdefault
# Use a slice to prevent IndexError from being raised, the following
# check will raise a more specific ValueError if the string is empty
- nextchar = s[end : end + 1]
+ nextchar = s[end: end + 1]
# Normally we expect nextchar == '"'
if nextchar != '"' and nextchar != "'":
if nextchar in _ws:
end = _w(s, end).end()
- nextchar = s[end : end + 1]
+ nextchar = s[end: end + 1]
# Trivial empty object
if nextchar == "}":
if object_pairs_hook is not None:
@@ -146,9 +146,9 @@ def JSONObject(
key = memo_get(key, key)
# To skip some function call overhead we optimize the fast paths where
# the JSON key separator is ": " or just ":".
- if s[end : end + 1] != ":":
+ if s[end: end + 1] != ":":
end = _w(s, end).end()
- if s[end : end + 1] != ":":
+ if s[end: end + 1] != ":":
raise JSONDecodeError("Expecting ':' delimiter", s, end)
end += 1
@@ -179,7 +179,7 @@ def JSONObject(
elif nextchar != ",":
raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
end = _w(s, end).end()
- nextchar = s[end : end + 1]
+ nextchar = s[end: end + 1]
end += 1
if nextchar != '"':
raise JSONDecodeError("Expecting property name enclosed in double quotes", s, end - 1)
@@ -257,7 +257,7 @@ def py_scanstring(s, end, strict=True, _b=BACKSLASH, _m=STRINGCHUNK.match, delim
else:
uni = _decode_uXXXX(s, end)
end += 5
- if 0xD800 <= uni <= 0xDBFF and s[end : end + 2] == "\\u":
+ if 0xD800 <= uni <= 0xDBFF and s[end: end + 2] == "\\u":
uni2 = _decode_uXXXX(s, end + 1)
if 0xDC00 <= uni2 <= 0xDFFF:
uni = 0x10000 + (((uni - 0xD800) << 10) | (uni2 - 0xDC00))
@@ -272,14 +272,14 @@ scanstring = py_scanstring
class CustomDecoder(json.JSONDecoder):
def __init__(
- self,
- *,
- object_hook=None,
- parse_float=None,
- parse_int=None,
- parse_constant=None,
- strict=True,
- object_pairs_hook=None
+ self,
+ *,
+ object_hook=None,
+ parse_float=None,
+ parse_int=None,
+ parse_constant=None,
+ strict=True,
+ object_pairs_hook=None
):
super().__init__(
object_hook=object_hook,
diff --git a/metagpt/utils/file.py b/metagpt/utils/file.py
index f3691549b..f7c9f2894 100644
--- a/metagpt/utils/file.py
+++ b/metagpt/utils/file.py
@@ -6,9 +6,10 @@
@File : file.py
@Describe : General file operations.
"""
-import aiofiles
from pathlib import Path
+import aiofiles
+
from metagpt.logs import logger
@@ -72,4 +73,3 @@ class File:
except Exception as e:
logger.error(f"Error reading file: {e}")
raise e
-
diff --git a/metagpt/utils/highlight.py b/metagpt/utils/highlight.py
index e6cbb228c..a7f8e7c7a 100644
--- a/metagpt/utils/highlight.py
+++ b/metagpt/utils/highlight.py
@@ -1,7 +1,7 @@
# 添加代码语法高亮显示
from pygments import highlight as highlight_
-from pygments.lexers import PythonLexer, SqlLexer
from pygments.formatters import TerminalFormatter, HtmlFormatter
+from pygments.lexers import PythonLexer, SqlLexer
def highlight(code: str, language: str = 'python', formatter: str = 'terminal'):
diff --git a/metagpt/utils/mermaid.py b/metagpt/utils/mermaid.py
index 5e5b275b0..2d8d3aed6 100644
--- a/metagpt/utils/mermaid.py
+++ b/metagpt/utils/mermaid.py
@@ -135,7 +135,6 @@ MMC2 = """sequenceDiagram
S-->>SE: return summary
SE-->>M: return summary"""
-
if __name__ == "__main__":
loop = asyncio.new_event_loop()
result = loop.run_until_complete(mermaid_to_file(MMC1, PROJECT_ROOT / f"{CONFIG.mermaid_engine}/1"))
diff --git a/metagpt/utils/mmdc_ink.py b/metagpt/utils/mmdc_ink.py
index 3d91cde9d..45cc2af52 100644
--- a/metagpt/utils/mmdc_ink.py
+++ b/metagpt/utils/mmdc_ink.py
@@ -6,9 +6,9 @@
@File : mermaid.py
"""
import base64
-import os
-from aiohttp import ClientSession,ClientError
+from aiohttp import ClientSession, ClientError
+
from metagpt.logs import logger
diff --git a/metagpt/utils/mmdc_playwright.py b/metagpt/utils/mmdc_playwright.py
index bdbfd82ff..5fef3708b 100644
--- a/metagpt/utils/mmdc_playwright.py
+++ b/metagpt/utils/mmdc_playwright.py
@@ -8,10 +8,13 @@
import os
from urllib.parse import urljoin
+
from playwright.async_api import async_playwright
+
from metagpt.logs import logger
-async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, height=2048)-> int:
+
+async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, height=2048) -> int:
"""
Converts the given Mermaid code to various output formats and saves them to files.
@@ -24,20 +27,21 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
Returns:
int: Returns 1 if the conversion and saving were successful, -1 otherwise.
"""
- suffixes=['png', 'svg', 'pdf']
+ suffixes = ['png', 'svg', 'pdf']
__dirname = os.path.dirname(os.path.abspath(__file__))
async with async_playwright() as p:
browser = await p.chromium.launch()
device_scale_factor = 1.0
context = await browser.new_context(
- viewport={'width': width, 'height': height},
- device_scale_factor=device_scale_factor,
- )
+ viewport={'width': width, 'height': height},
+ device_scale_factor=device_scale_factor,
+ )
page = await context.new_page()
async def console_message(msg):
logger.info(msg.text)
+
page.on('console', console_message)
try:
@@ -72,7 +76,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
}''', [mermaid_code, mermaid_config, my_css, background_color])
- if 'svg' in suffixes :
+ if 'svg' in suffixes:
svg_xml = await page.evaluate('''() => {
const svg = document.querySelector('svg');
const xmlSerializer = new XMLSerializer();
@@ -82,7 +86,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
with open(f'{output_file_without_suffix}.svg', 'wb') as f:
f.write(svg_xml.encode('utf-8'))
- if 'png' in suffixes:
+ if 'png' in suffixes:
clip = await page.evaluate('''() => {
const svg = document.querySelector('svg');
const rect = svg.getBoundingClientRect();
diff --git a/metagpt/utils/mmdc_pyppeteer.py b/metagpt/utils/mmdc_pyppeteer.py
index 7ec30fd12..690a26eb8 100644
--- a/metagpt/utils/mmdc_pyppeteer.py
+++ b/metagpt/utils/mmdc_pyppeteer.py
@@ -7,11 +7,14 @@
"""
import os
from urllib.parse import urljoin
-from pyppeteer import launch
-from metagpt.logs import logger
-from metagpt.config import CONFIG
-async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, height=2048)-> int:
+from pyppeteer import launch
+
+from metagpt.config import CONFIG
+from metagpt.logs import logger
+
+
+async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048, height=2048) -> int:
"""
Converts the given Mermaid code to various output formats and saves them to files.
@@ -24,15 +27,14 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
Returns:
int: Returns 1 if the conversion and saving were successful, -1 otherwise.
"""
- suffixes = ['png', 'svg', 'pdf']
+ suffixes = ['png', 'svg', 'pdf']
__dirname = os.path.dirname(os.path.abspath(__file__))
-
if CONFIG.pyppeteer_executable_path:
browser = await launch(headless=True,
- executablePath=CONFIG.pyppeteer_executable_path,
- args=['--disable-extensions',"--no-sandbox"]
- )
+ executablePath=CONFIG.pyppeteer_executable_path,
+ args=['--disable-extensions', "--no-sandbox"]
+ )
else:
logger.error("Please set the environment variable:PYPPETEER_EXECUTABLE_PATH.")
return -1
@@ -41,6 +43,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
async def console_message(msg):
logger.info(msg.text)
+
page.on('console', console_message)
try:
@@ -73,7 +76,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
}
}''', [mermaid_code, mermaid_config, my_css, background_color])
- if 'svg' in suffixes :
+ if 'svg' in suffixes:
svg_xml = await page.evaluate('''() => {
const svg = document.querySelector('svg');
const xmlSerializer = new XMLSerializer();
@@ -83,7 +86,7 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
with open(f'{output_file_without_suffix}.svg', 'wb') as f:
f.write(svg_xml.encode('utf-8'))
- if 'png' in suffixes:
+ if 'png' in suffixes:
clip = await page.evaluate('''() => {
const svg = document.querySelector('svg');
const rect = svg.getBoundingClientRect();
@@ -94,7 +97,8 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
height: Math.ceil(rect.height)
};
}''')
- await page.setViewport({'width': clip['x'] + clip['width'], 'height': clip['y'] + clip['height'], 'deviceScaleFactor': device_scale_factor})
+ await page.setViewport({'width': clip['x'] + clip['width'], 'height': clip['y'] + clip['height'],
+ 'deviceScaleFactor': device_scale_factor})
screenshot = await page.screenshot(clip=clip, omit_background=True, scale='device')
logger.info(f"Generating {output_file_without_suffix}.png..")
with open(f'{output_file_without_suffix}.png', 'wb') as f:
@@ -110,4 +114,3 @@ async def mermaid_to_file(mermaid_code, output_file_without_suffix, width=2048,
return -1
finally:
await browser.close()
-
diff --git a/metagpt/utils/parse_html.py b/metagpt/utils/parse_html.py
index 62de26541..f2395026f 100644
--- a/metagpt/utils/parse_html.py
+++ b/metagpt/utils/parse_html.py
@@ -16,7 +16,7 @@ class WebPage(BaseModel):
class Config:
underscore_attrs_are_private = True
- _soup : Optional[BeautifulSoup] = None
+ _soup: Optional[BeautifulSoup] = None
_title: Optional[str] = None
@property
@@ -24,7 +24,7 @@ class WebPage(BaseModel):
if self._soup is None:
self._soup = BeautifulSoup(self.html, "html.parser")
return self._soup
-
+
@property
def title(self):
if self._title is None:
diff --git a/metagpt/utils/pycst.py b/metagpt/utils/pycst.py
index afd85a547..4d1a86c91 100644
--- a/metagpt/utils/pycst.py
+++ b/metagpt/utils/pycst.py
@@ -37,12 +37,12 @@ def get_docstring_statement(body: DocstringNode) -> cst.SimpleStatementLine:
if not isinstance(expr, cst.Expr):
return None
-
+
val = expr.value
if not isinstance(val, (cst.SimpleString, cst.ConcatenatedString)):
return None
-
- evaluated_value = val.evaluated_value
+
+ evaluated_value = val.evaluated_value
if isinstance(evaluated_value, bytes):
return None
@@ -56,6 +56,7 @@ class DocstringCollector(cst.CSTVisitor):
stack: A list to keep track of the current path in the CST.
docstrings: A dictionary mapping paths in the CST to their corresponding docstrings.
"""
+
def __init__(self):
self.stack: list[str] = []
self.docstrings: dict[tuple[str, ...], cst.SimpleStatementLine] = {}
@@ -96,9 +97,10 @@ class DocstringTransformer(cst.CSTTransformer):
stack: A list to keep track of the current path in the CST.
docstrings: A dictionary mapping paths in the CST to their corresponding docstrings.
"""
+
def __init__(
- self,
- docstrings: dict[tuple[str, ...], cst.SimpleStatementLine],
+ self,
+ docstrings: dict[tuple[str, ...], cst.SimpleStatementLine],
):
self.stack: list[str] = []
self.docstrings = docstrings
@@ -125,7 +127,8 @@ class DocstringTransformer(cst.CSTTransformer):
key = tuple(self.stack)
self.stack.pop()
- if hasattr(updated_node, "decorators") and any((i.decorator.value == "overload") for i in updated_node.decorators):
+ if hasattr(updated_node, "decorators") and any(
+ (i.decorator.value == "overload") for i in updated_node.decorators):
return updated_node
statement = self.docstrings.get(key)
diff --git a/metagpt/utils/read_document.py b/metagpt/utils/read_document.py
index c837baf25..d2fafbc17 100644
--- a/metagpt/utils/read_document.py
+++ b/metagpt/utils/read_document.py
@@ -8,6 +8,7 @@
import docx
+
def read_docx(file_path: str) -> list:
"""Open a docx file"""
doc = docx.Document(file_path)
diff --git a/metagpt/utils/singleton.py b/metagpt/utils/singleton.py
index 474b537db..a9e0862c0 100644
--- a/metagpt/utils/singleton.py
+++ b/metagpt/utils/singleton.py
@@ -20,4 +20,3 @@ class Singleton(abc.ABCMeta, type):
if cls not in cls._instances:
cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwargs)
return cls._instances[cls]
-
\ No newline at end of file
diff --git a/metagpt/utils/special_tokens.py b/metagpt/utils/special_tokens.py
index 2adb93c77..5e780ce05 100644
--- a/metagpt/utils/special_tokens.py
+++ b/metagpt/utils/special_tokens.py
@@ -1,4 +1,4 @@
# token to separate different code messages in a WriteCode Message content
-MSG_SEP = "#*000*#"
+MSG_SEP = "#*000*#"
# token to seperate file name and the actual code text in a code message
FILENAME_CODE_SEP = "#*001*#"
diff --git a/metagpt/utils/text.py b/metagpt/utils/text.py
index be3c52edd..c36058e42 100644
--- a/metagpt/utils/text.py
+++ b/metagpt/utils/text.py
@@ -3,7 +3,8 @@ from typing import Generator, Sequence
from metagpt.utils.token_counter import TOKEN_MAX, count_string_tokens
-def reduce_message_length(msgs: Generator[str, None, None], model_name: str, system_text: str, reserved: int = 0,) -> str:
+def reduce_message_length(msgs: Generator[str, None, None], model_name: str, system_text: str,
+ reserved: int = 0, ) -> str:
"""Reduce the length of concatenated message segments to fit within the maximum token size.
Args:
@@ -27,11 +28,11 @@ def reduce_message_length(msgs: Generator[str, None, None], model_name: str, sys
def generate_prompt_chunk(
- text: str,
- prompt_template: str,
- model_name: str,
- system_text: str,
- reserved: int = 0,
+ text: str,
+ prompt_template: str,
+ model_name: str,
+ system_text: str,
+ reserved: int = 0,
) -> Generator[str, None, None]:
"""Split the text into chunks of a maximum token size.
@@ -49,9 +50,9 @@ def generate_prompt_chunk(
current_token = 0
current_lines = []
- reserved = reserved + count_string_tokens(prompt_template+system_text, model_name)
+ reserved = reserved + count_string_tokens(prompt_template + system_text, model_name)
# 100 is a magic number to ensure the maximum context length is not exceeded
- max_token = TOKEN_MAX.get(model_name, 2048) - reserved - 100
+ max_token = TOKEN_MAX.get(model_name, 2048) - reserved - 100
while paragraphs:
paragraph = paragraphs.pop(0)
@@ -103,7 +104,7 @@ def decode_unicode_escape(text: str) -> str:
return text.encode("utf-8").decode("unicode_escape", "ignore")
-def _split_by_count(lst: Sequence , count: int):
+def _split_by_count(lst: Sequence, count: int):
avg = len(lst) // count
remainder = len(lst) % count
start = 0
diff --git a/metagpt/utils/token_counter.py b/metagpt/utils/token_counter.py
index a5a65803a..2b9f21fb8 100644
--- a/metagpt/utils/token_counter.py
+++ b/metagpt/utils/token_counter.py
@@ -24,7 +24,6 @@ TOKEN_COSTS = {
"text-embedding-ada-002": {"prompt": 0.0004, "completion": 0.0},
}
-
TOKEN_MAX = {
"gpt-3.5-turbo": 4096,
"gpt-3.5-turbo-0301": 4096,
diff --git a/requirements.txt b/requirements.txt
index de861ded9..e855b6e83 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -42,4 +42,5 @@ pytest-mock==3.11.1
open-interpreter==0.1.4; python_version>"3.9"
ta==0.10.2
semantic-kernel==0.3.10.dev0
+websocket-client==0.58.0
diff --git a/startup.py b/startup.py
index e2a903c9b..df94aeaba 100644
--- a/startup.py
+++ b/startup.py
@@ -15,12 +15,12 @@ from metagpt.software_company import SoftwareCompany
async def startup(
- idea: str,
- investment: float = 3.0,
- n_round: int = 5,
- code_review: bool = False,
- run_tests: bool = False,
- implement: bool = True,
+ idea: str,
+ investment: float = 3.0,
+ n_round: int = 5,
+ code_review: bool = False,
+ run_tests: bool = False,
+ implement: bool = True,
):
"""Run a startup. Be a boss."""
company = SoftwareCompany()
@@ -48,12 +48,12 @@ async def startup(
def main(
- idea: str,
- investment: float = 3.0,
- n_round: int = 5,
- code_review: bool = True,
- run_tests: bool = False,
- implement: bool = True,
+ idea: str,
+ investment: float = 3.0,
+ n_round: int = 5,
+ code_review: bool = True,
+ run_tests: bool = False,
+ implement: bool = True,
):
"""
We are a software startup comprised of AI. By investing in us,
diff --git a/tests/conftest.py b/tests/conftest.py
index feecc7715..d2ac8304f 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -6,14 +6,14 @@
@File : conftest.py
"""
+import asyncio
+import re
from unittest.mock import Mock
import pytest
from metagpt.logs import logger
from metagpt.provider.openai_api import OpenAIGPTAPI as GPTAPI
-import asyncio
-import re
class Context:
diff --git a/tests/metagpt/actions/mock.py b/tests/metagpt/actions/mock.py
index a800690e8..fe82fe01e 100644
--- a/tests/metagpt/actions/mock.py
+++ b/tests/metagpt/actions/mock.py
@@ -159,7 +159,6 @@ sequenceDiagram
The original requirements did not specify whether the game should have a save/load feature, multiplayer support, or any specific graphical user interface. More information on these aspects could help in further refining the product design and requirements.
"""
-
PROJECT_MANAGEMENT_SAMPLE = '''## Required Python third-party packages: Provided in requirements.txt format
```python
"pytest==6.2.5"
@@ -217,7 +216,6 @@ The original requirements did not specify whether the game should have a save/lo
```
'''
-
WRITE_CODE_PROMPT_SAMPLE = """
你是一个工程师。下面是背景信息与你的当前任务，请为任务撰写代码。
撰写的代码应该符合PEP8，优雅，模块化，易于阅读与维护，代码本身应该有__main__入口来防止桩函数
@@ -375,7 +373,6 @@ if __name__ == '__main__':
print('No results found.')
"""
-
REFINED_CODE = '''
import requests
diff --git a/tests/metagpt/actions/test_clone_function.py b/tests/metagpt/actions/test_clone_function.py
index 6d4432dcd..e11402c97 100644
--- a/tests/metagpt/actions/test_clone_function.py
+++ b/tests/metagpt/actions/test_clone_function.py
@@ -2,7 +2,6 @@ import pytest
from metagpt.actions.clone_function import CloneFunction, run_function_code
-
source_code = """
import pandas as pd
import ta
@@ -37,7 +36,10 @@ def get_expected_res():
stock_data['SMA'] = ta.trend.sma_indicator(stock_data['Close'], window=6)
stock_data[['Date', 'Close', 'SMA']].head()
# 计算布林带
- stock_data['bb_upper'], stock_data['bb_middle'], stock_data['bb_lower'] = ta.volatility.bollinger_hband_indicator(stock_data['Close'], window=20), ta.volatility.bollinger_mavg(stock_data['Close'], window=20), ta.volatility.bollinger_lband_indicator(stock_data['Close'], window=20)
+ stock_data['bb_upper'], stock_data['bb_middle'], stock_data['bb_lower'] = ta.volatility.bollinger_hband_indicator(
+ stock_data['Close'], window=20), ta.volatility.bollinger_mavg(stock_data['Close'],
+ window=20), ta.volatility.bollinger_lband_indicator(
+ stock_data['Close'], window=20)
stock_data[['Date', 'Close', 'bb_upper', 'bb_middle', 'bb_lower']].head()
return stock_data
diff --git a/tests/metagpt/actions/test_debug_error.py b/tests/metagpt/actions/test_debug_error.py
index 555c84e4e..2393d2cc9 100644
--- a/tests/metagpt/actions/test_debug_error.py
+++ b/tests/metagpt/actions/test_debug_error.py
@@ -144,12 +144,12 @@ Engineer
---
'''
+
@pytest.mark.asyncio
async def test_debug_error():
-
debug_error = DebugError("debug_error")
file_name, rewritten_code = await debug_error.run(context=EXAMPLE_MSG_CONTENT)
- assert "class Player" in rewritten_code # rewrite the same class
- assert "while self.score > 21" in rewritten_code # a key logic to rewrite to (original one is "if self.score > 12")
+ assert "class Player" in rewritten_code # rewrite the same class
+ assert "while self.score > 21" in rewritten_code # a key logic to rewrite to (original one is "if self.score > 12")
diff --git a/tests/metagpt/actions/test_detail_mining.py b/tests/metagpt/actions/test_detail_mining.py
index c9d5331f9..1266960cc 100644
--- a/tests/metagpt/actions/test_detail_mining.py
+++ b/tests/metagpt/actions/test_detail_mining.py
@@ -10,6 +10,7 @@ import pytest
from metagpt.actions.detail_mining import DetailMining
from metagpt.logs import logger
+
@pytest.mark.asyncio
async def test_detail_mining():
topic = "如何做一个生日蛋糕"
@@ -17,7 +18,6 @@ async def test_detail_mining():
detail_mining = DetailMining("detail_mining")
rsp = await detail_mining.run(topic=topic, record=record)
logger.info(f"{rsp.content=}")
-
+
assert '##OUTPUT' in rsp.content
assert '蛋糕' in rsp.content
-
diff --git a/tests/metagpt/actions/test_ui_design.py b/tests/metagpt/actions/test_ui_design.py
index d284b20f2..dedd0b30e 100644
--- a/tests/metagpt/actions/test_ui_design.py
+++ b/tests/metagpt/actions/test_ui_design.py
@@ -4,7 +4,7 @@
#
from tests.metagpt.roles.ui_role import UIDesign
-llm_resp= '''
+llm_resp = '''
# UI Design Description
```The user interface for the snake game will be designed in a way that is simple, clean, and intuitive. The main elements of the game such as the game grid, snake, food, score, and game over message will be clearly defined and easy to understand. The game grid will be centered on the screen with the score displayed at the top. The game controls will be intuitive and easy to use. The design will be modern and minimalist with a pleasing color scheme.```
@@ -100,6 +100,7 @@ body {
font-size: 3em;
'''
+
def test_ui_design_parse_css():
ui_design_work = UIDesign(name="UI design action")
@@ -161,7 +162,7 @@ def test_ui_design_parse_css():
transform: translate(-50%, -50%);
font-size: 3em;
'''
- assert ui_design_work.parse_css_code(context=llm_resp)==css
+ assert ui_design_work.parse_css_code(context=llm_resp) == css
def test_ui_design_parse_html():
@@ -185,7 +186,4 @@ def test_ui_design_parse_html():