update: Update the METAGPT version

README.md

@@ -7,3 +7,254 @@ sdk: docker
 app_file: app.py
 pinned: false
 ---
+
+# MetaGPT: The Multi-Agent Framework
+
+<p align="center">
+<a href=""><img src="docs/resources/MetaGPT-logo.jpeg" alt="MetaGPT logo: Enable GPT to work in software company, collaborating to tackle more complex tasks." width="150px"></a>
+</p>
+
+<p align="center">
+<b>Assign different roles to GPTs to form a collaborative software entity for complex tasks.</b>
+</p>
+
+<p align="center">
+<a href="docs/README_CN.md"><img src="https://img.shields.io/badge/文档-中文版-blue.svg" alt="CN doc"></a>
+<a href="README.md"><img src="https://img.shields.io/badge/document-English-blue.svg" alt="EN doc"></a>
+<a href="docs/README_JA.md"><img src="https://img.shields.io/badge/ドキュメント-日本語-blue.svg" alt="JA doc"></a>
+<a href="https://discord.gg/wCp6Q3fsAk"><img src="https://dcbadge.vercel.app/api/server/wCp6Q3fsAk?compact=true&style=flat" alt="Discord Follow"></a>
+<a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
+<a href="docs/ROADMAP.md"><img src="https://img.shields.io/badge/ROADMAP-路线图-blue" alt="roadmap"></a>
+<a href="docs/resources/MetaGPT-WeChat-Personal.jpeg"><img src="https://img.shields.io/badge/WeChat-微信-blue" alt="roadmap"></a>
+<a href="https://twitter.com/DeepWisdom2019"><img src="https://img.shields.io/twitter/follow/MetaGPT?style=social" alt="Twitter Follow"></a>
+</p>
+
+<p align="center">
+   <a href="https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/geekan/MetaGPT"><img src="https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode" alt="Open in Dev Containers"></a>
+   <a href="https://codespaces.new/geekan/MetaGPT"><img src="https://img.shields.io/badge/Github_Codespace-Open-blue?logo=github" alt="Open in GitHub Codespaces"></a>
+</p>
+
+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.
+
+![A software company consists of LLM-based roles](docs/resources/software_company_cd.jpeg)
+
+<p align="center">Software Company Multi-Role Schematic (Gradually Implementing)</p>
+
+## 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
+
+![Jinri Toutiao Recsys Data & API Design](docs/resources/workspace/content_rec_sys/resources/data_api_design.png)
+
+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
+
+### Installation Video Guide
+
+- [Matthew Berman: How To Install MetaGPT - Build A Startup With One Prompt!!](https://youtu.be/uT75J_KG_aY)
+
+### Traditional Installation
+
+```bash
+# Step 1: Ensure that NPM is installed on your system. Then install mermaid-js.
+npm --version
+sudo npm install -g @mermaid-js/mermaid-cli
+
+# Step 2: Ensure that Python 3.9+ is installed on your system. You can check this by using:
+python --version
+
+# Step 3: Clone the repository to your local machine, and install it.
+git clone https://github.com/geekan/metagpt
+cd metagpt
+python setup.py install
+```
+
+**Note:**
+
+- 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,
+
+  ```bash
+  npm install @mermaid-js/mermaid-cli
+  ```
+
+- don't forget to the configuration for mmdc in config.yml
+
+  ```yml
+  PUPPETEER_CONFIG: "./config/puppeteer-config.json"
+  MMDC: "./node_modules/.bin/mmdc"
+  ```
+
+- if `python setup.py install` fails with error `[Errno 13] Permission denied: '/usr/local/lib/python3.11/dist-packages/test-easy-install-13129.write-test'`, try instead running `python setup.py install --user`
+
+### Installation by Docker
+
+```bash
+# Step 1: Download metagpt official image and prepare config.yaml
+docker pull metagpt/metagpt:v0.3.1
+mkdir -p /opt/metagpt/{config,workspace}
+docker run --rm metagpt/metagpt:v0.3.1 cat /app/metagpt/config/config.yaml > /opt/metagpt/config/key.yaml
+vim /opt/metagpt/config/key.yaml # Change the config
+
+# Step 2: Run metagpt demo with container
+docker run --rm \
+    --privileged \
+    -v /opt/metagpt/config/key.yaml:/app/metagpt/config/key.yaml \
+    -v /opt/metagpt/workspace:/app/metagpt/workspace \
+    metagpt/metagpt:v0.3.1 \
+    python startup.py "Write a cli snake game"
+
+# You can also start a container and execute commands in it
+docker run --name metagpt -d \
+    --privileged \
+    -v /opt/metagpt/config/key.yaml:/app/metagpt/config/key.yaml \
+    -v /opt/metagpt/workspace:/app/metagpt/workspace \
+    metagpt/metagpt:v0.3.1
+
+docker exec -it metagpt /bin/bash
+$ python startup.py "Write a cli snake game"
+```
+
+The command `docker run ...` do the following things:
+
+- Run in privileged mode to have permission to run the browser
+- Map host directory `/opt/metagpt/config` to container directory `/app/metagpt/config`
+- Map host directory `/opt/metagpt/workspace` to container directory `/app/metagpt/workspace`
+- Execute the demo command `python startup.py "Write a cli snake game"`
+
+### Build image by yourself
+
+```bash
+# You can also build metagpt image by yourself.
+git clone https://github.com/geekan/MetaGPT.git
+cd MetaGPT && docker build -t metagpt:custom .
+```
+
+## Configuration
+
+- Configure your `OPENAI_API_KEY` in any of `config/key.yaml / config/config.yaml / env`
+- Priority order: `config/key.yaml > config/config.yaml > env`
+
+```bash
+# Copy the configuration file and make the necessary modifications.
+cp config/config.yaml config/key.yaml
+```
+
+| 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://<YOUR_SITE>/v1" | export OPENAI_API_BASE="https://<YOUR_SITE>/v1" |
+
+## Tutorial: Initiating a startup
+
+```shell
+# Run the script
+python startup.py "Write a cli snake game"
+# Do not hire an engineer to implement the project
+python startup.py "Write a cli snake game" --implement False
+# Hire an engineer and perform code reviews
+python startup.py "Write a cli snake game" --code_review True
+```
+
+After running the script, you can find your new project in the `workspace/` directory.
+
+### Preference of Platform or Tool
+
+You can tell which platform or tool you want to use when stating your requirements.
+
+```shell
+python startup.py "Write a cli snake game based on pygame"
+```
+
+### Usage
+
+```
+NAME
+    startup.py - We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities.
+
+SYNOPSIS
+    startup.py IDEA <flags>
+
+DESCRIPTION
+    We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities.
+
+POSITIONAL ARGUMENTS
+    IDEA
+        Type: str
+        Your innovative idea, such as "Creating a snake game."
+
+FLAGS
+    --investment=INVESTMENT
+        Type: float
+        Default: 3.0
+        As an investor, you have the opportunity to contribute a certain dollar amount to this AI company.
+    --n_round=N_ROUND
+        Type: int
+        Default: 5
+
+NOTES
+    You can also use flags syntax for POSITIONAL ARGUMENTS
+```
+
+### Code walkthrough
+
+```python
+from metagpt.software_company import SoftwareCompany
+from metagpt.roles import ProjectManager, ProductManager, Architect, Engineer
+
+async def startup(idea: str, investment: float = 3.0, n_round: int = 5):
+    """Run a startup. Be a boss."""
+    company = SoftwareCompany()
+    company.hire([ProductManager(), Architect(), ProjectManager(), Engineer()])
+    company.invest(investment)
+    company.start_project(idea)
+    await company.run(n_round=n_round)
+```
+
+You can check `examples` for more details on single role (with knowledge base) and LLM only examples.
+
+## QuickStart
+
+It is difficult to install and configure the local environment for some users. The following tutorials will allow you to quickly experience the charm of MetaGPT.
+
+- [MetaGPT quickstart](https://deepwisdom.feishu.cn/wiki/CyY9wdJc4iNqArku3Lncl4v8n2b)
+
+## Citation
+
+For now, cite the [Arxiv paper](https://arxiv.org/abs/2308.00352):
+
+```bibtex
+@misc{hong2023metagpt,
+      title={MetaGPT: Meta Programming for Multi-Agent Collaborative Framework},
+      author={Sirui Hong and Xiawu Zheng and Jonathan Chen and Yuheng Cheng and Jinlin Wang and Ceyao Zhang and Zili Wang and Steven Ka Shing Yau and Zijuan Lin and Liyang Zhou and Chenyu Ran and Lingfeng Xiao and Chenglin Wu},
+      year={2023},
+      eprint={2308.00352},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI}
+}
+```
+
+## Contact Information
+
+If you have any questions or feedback about this project, please feel free to contact us. We highly appreciate your suggestions!
+
+- **Email:** [email protected]
+- **GitHub Issues:** For more technical inquiries, you can also create a new issue in our [GitHub repository](https://github.com/geekan/metagpt/issues).
+
+We will respond to all questions within 2-3 business days.
+
+## Demo
+
+https://github.com/geekan/MetaGPT/assets/2707039/5e8c1062-8c35-440f-bb20-2b0320f8d27d
+
+## Join us
+
+📢 Join Our Discord Channel!
+https://discord.gg/ZRHeExS6xv
+
+Looking forward to seeing you there! 🎉

metagpt/.gitattributes

@@ -1 +0,0 @@
-*.mp4 filter=lfs diff=lfs merge=lfs -text

metagpt/actions/talk_action.py

@@ -45,6 +45,20 @@ class TalkAction(Action):
         )
         return prompt
 
+    @property
+    def formation_prompt(self):
+        kvs = {
+            "{role}": CONFIG.agent_description or "",
+            "{history}": self._history_summary or "",
+            "{knowledge}": self._knowledge or "",
+            "{language}": CONFIG.language or DEFAULT_LANGUAGE,
+            "{ask}": self._talk,
+        }
+        prompt = TalkAction.__FORMATION_LOOSE__
+        for k, v in kvs.items():
+            prompt = prompt.replace(k, v)
+        return prompt
+
     async def run(self, *args, **kwargs) -> ActionOutput:
         prompt = self.prompt
         logger.info(prompt)
@@ -52,3 +66,60 @@ class TalkAction(Action):
         logger.info(rsp)
         self._rsp = ActionOutput(content=rsp)
         return self._rsp
+
+    __FORMATION__ = """Formation: "Capacity and role" defines the role you are currently playing;
+  "[HISTORY_BEGIN]" and "[HISTORY_END]" tags enclose the historical conversation;
+  "[KNOWLEDGE_BEGIN]" and "[KNOWLEDGE_END]" tags enclose the knowledge may help for your responses;
+  "Statement" defines the work detail you need to complete at this stage;
+  "[ASK_BEGIN]" and [ASK_END] tags enclose the requirements for your to respond;
+  "Constraint" defines the conditions that your responses must comply with.
+
+Capacity and role: {role}
+Statement: Your responses should align with the role-play agreement, maintaining the
+ character's persona and habits. When faced with unrelated questions, playfully decline to answer without revealing
+ your AI nature to preserve the character's image.
+
+[HISTORY_BEGIN]
+{history}
+[HISTORY_END]
+
+[KNOWLEDGE_BEGIN]
+{knowledge}
+[KNOWLEDGE_END]
+
+Statement: If the information is insufficient, you can search in the historical conversation or knowledge.
+Statement: Answer the following questions in {language}, and the answers must follow the Markdown format
+ , excluding any tag likes "[HISTORY_BEGIN]", "[HISTORY_END]", "[KNOWLEDGE_BEGIN]", "[KNOWLEDGE_END]", "[ASK_BEGIN]"
+ , "[ASK_END]" 
+ 
+[ASK_BEGIN]
+{ask}
+[ASK_END]"""
+
+    __FORMATION_LOOSE__ = """Formation: "Capacity and role" defines the role you are currently playing;
+  "[HISTORY_BEGIN]" and "[HISTORY_END]" tags enclose the historical conversation;
+  "[KNOWLEDGE_BEGIN]" and "[KNOWLEDGE_END]" tags enclose the knowledge may help for your responses;
+  "Statement" defines the work detail you need to complete at this stage;
+  "[ASK_BEGIN]" and [ASK_END] tags enclose the requirements for your to respond;
+  "Constraint" defines the conditions that your responses must comply with.
+
+Capacity and role: {role}
+Statement: Your responses should maintaining the character's persona and habits. When faced with unrelated questions
+, playfully decline to answer without revealing your AI nature to preserve the character's image. 
+
+[HISTORY_BEGIN]
+{history}
+[HISTORY_END]
+
+[KNOWLEDGE_BEGIN]
+{knowledge}
+[KNOWLEDGE_END]
+
+Statement: If the information is insufficient, you can search in the historical conversation or knowledge.
+Statement: Answer the following questions in {language}, and the answers must follow the Markdown format
+ , excluding any tag likes "[HISTORY_BEGIN]", "[HISTORY_END]", "[KNOWLEDGE_BEGIN]", "[KNOWLEDGE_END]", "[ASK_BEGIN]"
+ , "[ASK_END]" 
+
+[ASK_BEGIN]
+{ask}
+[ASK_END]"""

metagpt/document_store/lancedb_store.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Time    : 2023/8/9 15:42
+@Author  : unkn-wn (Leon Yee)
+@File    : lancedb_store.py
+"""
+import lancedb
+import shutil, os
+
+
+class LanceStore:
+    def __init__(self, name):
+        db = lancedb.connect('./data/lancedb')
+        self.db = db
+        self.name = name
+        self.table = None
+
+    def search(self, query, n_results=2, metric="L2", nprobes=20, **kwargs):
+        # This assumes query is a vector embedding
+        # kwargs can be used for optional filtering
+        # .select - only searches the specified columns
+        # .where - SQL syntax filtering for metadata (e.g. where("price > 100"))
+        # .metric - specifies the distance metric to use
+        # .nprobes - values will yield better recall (more likely to find vectors if they exist) at the expense of latency.
+        if self.table == None: raise Exception("Table not created yet, please add data first.")
+
+        results = self.table \
+            .search(query) \
+            .limit(n_results) \
+            .select(kwargs.get('select')) \
+            .where(kwargs.get('where')) \
+            .metric(metric) \
+            .nprobes(nprobes) \
+            .to_df()
+        return results
+
+    def persist(self):
+        raise NotImplementedError
+
+    def write(self, data, metadatas, ids):
+        # This function is similar to add(), but it's for more generalized updates
+        # "data" is the list of embeddings
+        # Inserts into table by expanding metadatas into a dataframe: [{'vector', 'id', 'meta', 'meta2'}, ...]
+
+        documents = []
+        for i in range(len(data)):
+            row = {
+                'vector': data[i],
+                'id': ids[i]
+            }
+            row.update(metadatas[i])
+            documents.append(row)
+
+        if self.table != None:
+            self.table.add(documents)
+        else:
+            self.table = self.db.create_table(self.name, documents)
+
+    def add(self, data, metadata, _id):
+        # This function is for adding individual documents
+        # It assumes you're passing in a single vector embedding, metadata, and id
+
+        row = {
+            'vector': data,
+            'id': _id
+        }
+        row.update(metadata)
+
+        if self.table != None:
+            self.table.add([row])
+        else:
+            self.table = self.db.create_table(self.name, [row])
+
+    def delete(self, _id):
+        # This function deletes a row by id.
+        # LanceDB delete syntax uses SQL syntax, so you can use "in" or "="
+        if self.table == None: raise Exception("Table not created yet, please add data first")
+
+        if isinstance(_id, str):
+            return self.table.delete(f"id = '{_id}'")
+        else:
+            return self.table.delete(f"id = {_id}")
+
+    def drop(self, name):
+        # This function drops a table, if it exists.
+
+        path = os.path.join(self.db.uri, name + '.lance')
+        if os.path.exists(path):
+            shutil.rmtree(path)

metagpt/management/skill_manager.py

@@ -15,7 +15,9 @@ Skill = Action
 
 
 class SkillManager:
-    """用来管理所有技能"""
+    """用来管理所有技能
+       to manage all skills
+    """
 
     def __init__(self):
         self._store = ChromaStore('skill_manager')
@@ -24,7 +26,8 @@ class SkillManager:
     def add_skill(self, skill: Skill):
         """
         增加技能，将技能加入到技能池与可检索的存储中
-        :param skill: 技能
+        Adding skills, adding skills to skill pools and retrievable storage
+        :param skill: 技能 Skill
         :return:
         """
         self._skills[skill.name] = skill
@@ -33,7 +36,8 @@ class SkillManager:
     def del_skill(self, skill_name: str):
         """
         删除技能，将技能从技能池与可检索的存储中移除
-        :param skill_name: 技能名
+        delete skill removes skill from skill pool and retrievable storage
+        :param skill_name: 技能名 skill name
         :return:
         """
         self._skills.pop(skill_name)
@@ -42,30 +46,31 @@ class SkillManager:
     def get_skill(self, skill_name: str) -> Skill:
         """
         通过技能名获得精确的技能
-        :param skill_name: 技能名
-        :return: 技能
+         Get the exact skill by skill name
+        :param skill_name: 技能名 skill name
+        :return: 技能 Skill
         """
         return self._skills.get(skill_name)
 
     def retrieve_skill(self, desc: str, n_results: int = 2) -> list[Skill]:
         """
-        通过检索引擎获得技能
-        :param desc: 技能描述
-        :return: 技能（多个）
+        通过检索引擎获得技能 Acquiring Skills Through Search Engines
+        :param desc: 技能描述 skill description
+        :return: 技能（多个）skill(s)
         """
         return self._store.search(desc, n_results=n_results)['ids'][0]
 
     def retrieve_skill_scored(self, desc: str, n_results: int = 2) -> dict:
         """
-        通过检索引擎获得技能
-        :param desc: 技能描述
-        :return: 技能与分数组成的字典
+        通过检索引擎获得技能 Acquiring Skills Through Search Engines
+        :param desc: 技能描述 skill description
+        :return: 技能与分数组成的字典 A dictionary of skills and scores
         """
         return self._store.search(desc, n_results=n_results)
 
     def generate_skill_desc(self, skill: Skill) -> str:
         """
-        为每个技能生成对应的描述性文本
+        为每个技能生成对应的描述性文本 Generate corresponding descriptive text for each skill
         :param skill:
         :return:
         """

metagpt/provider/base_gpt_api.py

@@ -38,13 +38,13 @@ class BaseGPTAPI(BaseChatbot):
         rsp = self.completion(message)
         return self.get_choice_text(rsp)
 
-    async def aask(self, msg: str, system_msgs: Optional[list[str]] = None, generator: bool = False) -> str:
+    async def aask(self, msg: str, system_msgs: Optional[list[str]] = None) -> str:
         if system_msgs:
             message = self._system_msgs(system_msgs) + [self._user_msg(msg)]
         else:
             message = [self._default_system_msg(), self._user_msg(msg)]
         try:
-            rsp = await self.acompletion_text(message, stream=True, generator=generator)
+            rsp = await self.acompletion_text(message, stream=True)
         except Exception as e:
             logger.exception(f"{e}")
             logger.info(f"ask:{msg}, error:{e}")

metagpt/provider/openai_api.py

@@ -87,11 +87,22 @@ class OpenAIGPTAPI(BaseGPTAPI, RateLimiter):
         response = await self.async_retry_call(
             openai.ChatCompletion.acreate, **self._cons_kwargs(messages), stream=True
         )
+        # create variables to collect the stream of chunks
+        collected_chunks = []
+        collected_messages = []
         # iterate through the stream of events
         async for chunk in response:
+            collected_chunks.append(chunk)  # save the event response
             chunk_message = chunk["choices"][0]["delta"]  # extract the message
+            collected_messages.append(chunk_message)  # save the message
             if "content" in chunk_message:
-                yield chunk_message["content"]
+                print(chunk_message["content"], end="")
+        print()
+
+        full_reply_content = "".join([m.get("content", "") for m in collected_messages])
+        usage = self._calc_usage(messages, full_reply_content)
+        self._update_costs(usage)
+        return full_reply_content
 
     def _cons_kwargs(self, messages: list[dict]) -> dict:
         if CONFIG.openai_api_type == "azure":
@@ -146,23 +157,10 @@ class OpenAIGPTAPI(BaseGPTAPI, RateLimiter):
         retry=retry_if_exception_type(APIConnectionError),
         retry_error_callback=log_and_reraise,
     )
-    async def acompletion_text(self, messages: list[dict], stream=False, generator: bool = False) -> str:
+    async def acompletion_text(self, messages: list[dict], stream=False) -> str:
         """when streaming, print each token in place."""
         if stream:
-            resp = self._achat_completion_stream(messages)
-            if generator:
-                return resp
-
-            collected_messages = []
-            async for i in resp:
-                print(i, end="")
-                collected_messages.append(i)
-
-            full_reply_content = "".join(collected_messages)
-            usage = self._calc_usage(messages, full_reply_content)
-            self._update_costs(usage)
-            return full_reply_content
-
+            return await self._achat_completion_stream(messages)
         rsp = await self._achat_completion(messages)
         return self.get_choice_text(rsp)
 
@@ -228,13 +226,13 @@ class OpenAIGPTAPI(BaseGPTAPI, RateLimiter):
         max_count = 100
         while max_count > 0:
             if len(text) < max_token_count:
-                return await self._get_summary(text=text, max_words=max_words, keep_language=keep_language)
+                return await self._get_summary(text=text, max_words=max_words,keep_language=keep_language)
 
             padding_size = 20 if max_token_count > 20 else 0
             text_windows = self.split_texts(text, window_size=max_token_count - padding_size)
             summaries = []
             for ws in text_windows:
-                response = await self._get_summary(text=ws, max_words=max_words, keep_language=keep_language)
+                response = await self._get_summary(text=ws, max_words=max_words,keep_language=keep_language)
                 summaries.append(response)
             if len(summaries) == 1:
                 return summaries[0]

startup.py

@@ -4,38 +4,64 @@ import asyncio
 import platform
 import fire
 
-from metagpt.roles import Architect, Engineer, ProductManager, ProjectManager, QaEngineer
+from metagpt.roles import Architect, Engineer, ProductManager
+from metagpt.roles import ProjectManager, QaEngineer
 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):
+async def startup(
+    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()
-    company.hire([ProductManager(),
-                  Architect(),
-                  ProjectManager(),
-                  Engineer(n_borg=5, use_code_review=code_review)])
+    company.hire([
+        ProductManager(),
+        Architect(),
+        ProjectManager(),
+    ])
+
+    # if implement or code_review
+    if implement or code_review:
+        # developing features: implement the idea
+        company.hire([Engineer(n_borg=5, use_code_review=code_review)])
+
     if run_tests:
-        # developing features: run tests on the spot and identify bugs (bug fixing capability comes soon!)
+        # developing features: run tests on the spot and identify bugs
+        # (bug fixing capability comes soon!)
         company.hire([QaEngineer()])
+
     company.invest(investment)
     company.start_project(idea)
     await company.run(n_round=n_round)
 
 
-def main(idea: str, investment: float = 3.0, n_round: int = 5, code_review: bool = False, run_tests: bool = False):
+def main(
+    idea: str,
+    investment: float = 3.0,
+    n_round: int = 5,
+    code_review: bool = False,
+    run_tests: bool = False,
+    implement: bool = False
+):
     """
-    We are a software startup comprised of AI. By investing in us, you are empowering a future filled with limitless possibilities.
+    We are a software startup comprised of AI. By investing in us,
+    you are empowering a future filled with limitless possibilities.
     :param idea: Your innovative idea, such as "Creating a snake game."
-    :param investment: As an investor, you have the opportunity to contribute a certain dollar amount to this AI company.
+    :param investment: As an investor, you have the opportunity to contribute
+    a certain dollar amount to this AI company.
     :param n_round:
     :param code_review: Whether to use code review.
     :return:
     """
     if platform.system() == "Windows":
         asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
-    asyncio.run(startup(idea, investment, n_round, code_review, run_tests))
+    asyncio.run(startup(idea, investment, n_round,
+                code_review, run_tests, implement))
 
 
 if __name__ == '__main__':

tests/metagpt/document_store/test_lancedb_store.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+"""
+@Time    : 2023/8/9 15:42
+@Author  : unkn-wn (Leon Yee)
+@File    : test_lancedb_store.py
+"""
+from metagpt.document_store.lancedb_store import LanceStore
+import pytest
+import random
+
+@pytest
+def test_lance_store():
+
+    # This simply establishes the connection to the database, so we can drop the table if it exists
+    store = LanceStore('test')
+
+    store.drop('test')
+
+    store.write(data=[[random.random() for _ in range(100)] for _ in range(2)],
+            metadatas=[{"source": "google-docs"}, {"source": "notion"}],
+            ids=["doc1", "doc2"])
+
+    store.add(data=[random.random() for _ in range(100)], metadata={"source": "notion"}, _id="doc3")
+
+    result = store.search([random.random() for _ in range(100)], n_results=3)
+    assert(len(result) == 3)
+
+    store.delete("doc2")
+    result = store.search([random.random() for _ in range(100)], n_results=3, where="source = 'notion'", metric='cosine')
+    assert(len(result) == 1)