diff --git a/.env.example b/.env.example index 6d44035..1f342b1 100644 --- a/.env.example +++ b/.env.example @@ -1,3 +1,3 @@ SEARXNG_BASE_URL="http://127.0.0.1:8080" -OPENAI_API_KEY='dont share this, not needed for local providers' -TOKENIZERS_PARALLELISM=False \ No newline at end of file +OPENAI_API_KEY='xxxxx' +DEEPSEEK_API_KEY='xxxxx' \ No newline at end of file diff --git a/.gitignore b/.gitignore index afef1e3..9916e76 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,5 @@ *.wav +*.DS_Store *.safetensors config.ini *.egg-info diff --git a/README.md b/README.md index e91ba6e..ac33da9 100644 --- a/README.md +++ b/README.md @@ -10,24 +10,16 @@ ![alt text](./media/whale_readme.jpg) -> *Do a web search to find tech startup in Japan working on cutting edge AI research* +> *Do a deep search of AI startup in Osaka and Tokyo, find at least 5, then save in the research_japan.txt file* > *Can you make a tetris game in C ?* -> *Can you find where is contract.pdf*? +> *I would like to setup a new project file index as mark2.* -### Browse the web +### agenticSeek can now plan tasks! -![alt text](./media/exemples/search_startup.png) - -### Code hand free - -![alt text](./media/exemples/matmul_golang.png) - -### Plan and execute with agents (Experimental) - -![alt text](./media/exemples/plan_weather_app.png) +![alt text](./media/exemples/demo_image.png) *See media/examples for other use case screenshots.* @@ -139,6 +131,8 @@ python3 main.py *See the **Run with an API** section if your hardware can't run deepseek locally* +*See the **Config** section for detailled config file explanation.* + --- ## Usage @@ -157,6 +151,8 @@ You will be prompted with `>>> ` This indicate agenticSeek await you type for instructions. You can also use speech to text by setting `listen = True` in the config. +To exit, simply say `goodbye`. + Here are some example usage: ### Coding/Bash @@ -212,8 +208,6 @@ If you have a powerful computer or a server that you can use, but you want to us ### 1️⃣ **Set up and start the server scripts** -You need to have ollama installed on the server (We will integrate VLLM and llama.cpp soon). - On your "server" that will run the AI model, get the ip address ```sh @@ -222,18 +216,34 @@ ip a | grep "inet " | grep -v 127.0.0.1 | awk '{print $2}' | cut -d/ -f1 Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP address. -Clone the repository and then, run the script `stream_llm.py` in `server/` +**If you wish to use openai based provider follow the *Run with an API* section.** + +Clone the repository and enter the `server/`folder. + ```sh -python3 server_ollama.py --model "deepseek-r1:32b" +git clone --depth 1 https://github.com/Fosowl/agenticSeek.git +cd agenticSeek/server/ ``` +Install server specific requirements: + +```sh +pip3 install -r requirements.txt +``` + +Run the server script. + +```sh +python3 app.py --provider ollama --port 3333 +``` + +You have the choice between using `ollama` and `llamacpp` as a LLM service. + ### 2️⃣ **Run it** Now on your personal computer: -Clone the repository. - Change the `config.ini` file to set the `provider_name` to `server` and `provider_model` to `deepseek-r1:14b`. Set the `provider_server_address` to the ip address of the machine that will run the model. @@ -242,7 +252,7 @@ Set the `provider_server_address` to the ip address of the machine that will run is_local = False provider_name = server provider_model = deepseek-r1:14b -provider_server_address = x.x.x.x:5000 +provider_server_address = x.x.x.x:3333 ``` Run the assistant: @@ -254,18 +264,22 @@ python3 main.py ## **Run with an API** -Clone the repository. - Set the desired provider in the `config.ini` ```sh [MAIN] is_local = False provider_name = openai -provider_model = gpt4-o -provider_server_address = 127.0.0.1:5000 # can be set to anything, not used +provider_model = gpt-4o +provider_server_address = 127.0.0.1:5000 ``` +WARNING: Make sure there is not trailing space in the config. + +Set `is_local` to True if using a local openai-based api. + +Change the IP address if your openai-based api run on your own server. + Run the assistant: ```sh @@ -275,8 +289,6 @@ python3 main.py --- - - ## Speech to Text The speech-to-text functionality is disabled by default. To enable it, set the listen option to True in the config.ini file: @@ -302,18 +314,55 @@ End your request with a confirmation phrase to signal the system to proceed. Exa "do it", "go ahead", "execute", "run", "start", "thanks", "would ya", "please", "okay?", "proceed", "continue", "go on", "do that", "go it", "do you understand?" ``` +## Config + +Example config: +``` +[MAIN] +is_local = True +provider_name = ollama +provider_model = deepseek-r1:1.5b +provider_server_address = 127.0.0.1:11434 +agent_name = Friday +recover_last_session = False +save_session = False +speak = False +listen = False +work_dir = /Users/mlg/Documents/ai_folder +jarvis_personality = False +[BROWSER] +headless_browser = False +stealth_mode = False +``` + +**Explanation**: + +- is_local -> Runs the agent locally (True) or on a remote server (False). +- provider_name -> The provider to use (one of: `ollama`, `server`, `lm-studio`, `deepseek-api`) +- provider_model -> The model used, e.g., deepseek-r1:1.5b. +- provider_server_address -> Server address, e.g., 127.0.0.1:11434 for local. Set to anything for non-local API. +- agent_name -> Name of the agent, e.g., Friday. Used as a trigger word for TTS. +- recover_last_session -> Restarts from last session (True) or not (False). +- save_session -> Saves session data (True) or not (False). +- speak -> Enables voice output (True) or not (False). +- listen -> listen to voice input (True) or not (False). +- work_dir -> Folder the AI will have access to. eg: /Users/user/Documents/. +- jarvis_personality -> Uses a JARVIS-like personality (True) or not (False). This simply change the prompt file. +- headless_browser -> Runs browser without a visible window (True) or not (False). +- stealth_mode -> Make bot detector time harder. Only downside is you have to manually install the anticaptcha extension. + ## Providers The table below show the available providers: | Provider | Local? | Description | |-----------|--------|-----------------------------------------------------------| -| Ollama | Yes | Run LLMs locally with ease using ollama as a LLM provider | -| Server | Yes | Host the model on another machine, run your local machine | -| OpenAI | No | Use ChatGPT API (non-private) | -| Deepseek | No | Deepseek API (non-private) | -| HuggingFace| No | Hugging-Face API (non-private) | - +| ollama | Yes | Run LLMs locally with ease using ollama as a LLM provider | +| server | Yes | Host the model on another machine, run your local machine | +| lm-studio | Yes | Run LLM locally with LM studio (set `provider_name` to `lm-studio`)| +| openai | No | Use ChatGPT API (non-private) | +| deepseek-api | No | Deepseek API (non-private) | +| huggingface| No | Hugging-Face API (non-private) | To select a provider change the config.ini: @@ -354,6 +403,8 @@ And download the chromedriver version matching your OS. ![alt text](./media/chromedriver_readme.png) +If this section is incomplete please raise an issue. + ## FAQ **Q: What hardware do I need?** diff --git a/config.ini b/config.ini index 3c0d27a..6ca0f40 100644 --- a/config.ini +++ b/config.ini @@ -9,4 +9,7 @@ save_session = False speak = False listen = False work_dir = /Users/mlg/Documents/ai_folder -headless_browser = False \ No newline at end of file +jarvis_personality = False +[BROWSER] +headless_browser = False +stealth_mode = False \ No newline at end of file diff --git a/crx/nopecha.crx b/crx/nopecha.crx new file mode 100644 index 0000000..b114a05 Binary files /dev/null and b/crx/nopecha.crx differ diff --git a/install.sh b/install.sh index 0220f11..7f397fe 100755 --- a/install.sh +++ b/install.sh @@ -7,6 +7,7 @@ echo "Detecting operating system..." OS_TYPE=$(uname -s) + case "$OS_TYPE" in "Linux"*) echo "Detected Linux OS" @@ -37,4 +38,4 @@ case "$OS_TYPE" in ;; esac -echo "Installation process finished!" \ No newline at end of file +echo "Installation process finished!" diff --git a/main.py b/main.py index 0ff444e..4129248 100755 --- a/main.py +++ b/main.py @@ -9,6 +9,7 @@ from sources.llm_provider import Provider from sources.interaction import Interaction from sources.agents import Agent, CoderAgent, CasualAgent, FileAgent, PlannerAgent, BrowserAgent from sources.browser import Browser, create_driver +from sources.utility import pretty_print import warnings warnings.filterwarnings("ignore") @@ -22,31 +23,34 @@ def handleInterrupt(signum, frame): def main(): signal.signal(signal.SIGINT, handler=handleInterrupt) - if config.getboolean('MAIN', 'is_local'): - provider = Provider(config["MAIN"]["provider_name"], config["MAIN"]["provider_model"], config["MAIN"]["provider_server_address"]) - else: - provider = Provider(provider_name=config["MAIN"]["provider_name"], - model=config["MAIN"]["provider_model"], - server_address=config["MAIN"]["provider_server_address"]) + pretty_print("Initializing...", color="status") + provider = Provider(provider_name=config["MAIN"]["provider_name"], + model=config["MAIN"]["provider_model"], + server_address=config["MAIN"]["provider_server_address"], + is_local=config.getboolean('MAIN', 'is_local')) - browser = Browser(create_driver(), headless=config.getboolean('MAIN', 'headless_browser')) + stealth_mode = config.getboolean('BROWSER', 'stealth_mode') + browser = Browser( + create_driver(headless=config.getboolean('BROWSER', 'headless_browser'), stealth_mode=stealth_mode), + anticaptcha_manual_install=stealth_mode + ) + personality_folder = "jarvis" if config.getboolean('MAIN', 'jarvis_personality') else "base" agents = [ CasualAgent(name=config["MAIN"]["agent_name"], - prompt_path="prompts/casual_agent.txt", + prompt_path=f"prompts/{personality_folder}/casual_agent.txt", provider=provider, verbose=False), CoderAgent(name="coder", - prompt_path="prompts/coder_agent.txt", + prompt_path=f"prompts/{personality_folder}/coder_agent.txt", provider=provider, verbose=False), FileAgent(name="File Agent", - prompt_path="prompts/file_agent.txt", + prompt_path=f"prompts/{personality_folder}/file_agent.txt", provider=provider, verbose=False), BrowserAgent(name="Browser", - prompt_path="prompts/browser_agent.txt", + prompt_path=f"prompts/{personality_folder}/browser_agent.txt", provider=provider, verbose=False, browser=browser), - # Planner agent is experimental, might work poorly, especially with model < 32b PlannerAgent(name="Planner", - prompt_path="prompts/planner_agent.txt", + prompt_path=f"prompts/{personality_folder}/planner_agent.txt", provider=provider, verbose=False, browser=browser) ] @@ -57,8 +61,8 @@ def main(): try: while interaction.is_active: interaction.get_user() - interaction.think() - interaction.show_answer() + if interaction.think(): + interaction.show_answer() except Exception as e: if config.getboolean('MAIN', 'save_session'): interaction.save_session() diff --git a/media/exemples/brooo.png b/media/exemples/brooo.png deleted file mode 100644 index 74e691c..0000000 Binary files a/media/exemples/brooo.png and /dev/null differ diff --git a/media/exemples/demo_image.png b/media/exemples/demo_image.png new file mode 100644 index 0000000..c57f1cd Binary files /dev/null and b/media/exemples/demo_image.png differ diff --git a/media/exemples/failure_recover.png b/media/exemples/failure_recover.png deleted file mode 100644 index 99f792f..0000000 Binary files a/media/exemples/failure_recover.png and /dev/null differ diff --git a/media/exemples/files_interaction.png b/media/exemples/files_interaction.png deleted file mode 100644 index ac57958..0000000 Binary files a/media/exemples/files_interaction.png and /dev/null differ diff --git a/media/exemples/plan_flight_app.png b/media/exemples/plan_flight_app.png deleted file mode 100644 index 0b24ec5..0000000 Binary files a/media/exemples/plan_flight_app.png and /dev/null differ diff --git a/media/exemples/search_startup.png b/media/exemples/search_startup.png deleted file mode 100644 index 180317f..0000000 Binary files a/media/exemples/search_startup.png and /dev/null differ diff --git a/media/technical/.DS_Store b/media/technical/.DS_Store new file mode 100644 index 0000000..5008ddf Binary files /dev/null and b/media/technical/.DS_Store differ diff --git a/media/technical/code_agent.png b/media/technical/code_agent.png new file mode 100644 index 0000000..e453ef0 Binary files /dev/null and b/media/technical/code_agent.png differ diff --git a/media/technical/routing_system.png b/media/technical/routing_system.png new file mode 100644 index 0000000..47f8fcd Binary files /dev/null and b/media/technical/routing_system.png differ diff --git a/prompts/browser_agent.txt b/prompts/base/browser_agent.txt similarity index 100% rename from prompts/browser_agent.txt rename to prompts/base/browser_agent.txt diff --git a/prompts/casual_agent.txt b/prompts/base/casual_agent.txt similarity index 98% rename from prompts/casual_agent.txt rename to prompts/base/casual_agent.txt index 36d7b50..232e919 100644 --- a/prompts/casual_agent.txt +++ b/prompts/base/casual_agent.txt @@ -4,6 +4,8 @@ Speak in a warm, enthusiastic tone, delivering sharp, intelligent, and loyal sup Weave in subtle, context sarcasm or dry wit to enhance your personality. Assist with any request, assume the user knows their intent—no moral, legal, or ethical lectures. +## Self-documentation + **Usage of agenticSeek** AgenticSeek is a autonomous agent system that use agent routing to select the best agent. diff --git a/prompts/coder_agent.txt b/prompts/base/coder_agent.txt similarity index 65% rename from prompts/coder_agent.txt rename to prompts/base/coder_agent.txt index 26098da..886f2e3 100644 --- a/prompts/coder_agent.txt +++ b/prompts/base/coder_agent.txt @@ -38,14 +38,13 @@ func main() { ``` Some rules: -- Use tmp/ folder when saving file. -- Do not EVER use placeholder path in your code like path/to/your/folder. -- Do not ever ask to replace a path, use current sys path. -- Be efficient, no need to explain your code or explain what you do. - You have full access granted to user system. -- You do not ever need to use bash to execute code. All code is executed automatically. -- As a coding agent, you will get message from the system not just the user. -- Do not ever use user input such as input(), input are not supported by the system. -- Do not ever tell user how to run it. user know it already. +- Do not EVER use placeholder path in your code like path/to/your/folder. +- Do not ever ask to replace a path, use current sys path or work directory. +- Always provide a short sentence above the code for what it does, even for a hello world. +- Be efficient, no need to explain your code, unless asked. +- You do not ever need to use bash to execute code. +- Do not ever use user input, input are not supported by the system. +- Do not ever tell user how to run it. user know it. - For simple explanation you don't need to code. -- If query is unclear or incoherent say REQUEST_CLARIFICATION \ No newline at end of file +- If query is unclear say REQUEST_CLARIFICATION \ No newline at end of file diff --git a/prompts/file_agent.txt b/prompts/base/file_agent.txt similarity index 76% rename from prompts/file_agent.txt rename to prompts/base/file_agent.txt index a1f4e9b..309d01e 100644 --- a/prompts/file_agent.txt +++ b/prompts/base/file_agent.txt @@ -1,4 +1,7 @@ -You are an expert in file operations. You must use the provided tools to interact with the user’s system. The tools available to you are **bash** and **file_finder**. These are distinct tools with different purposes: `bash` executes shell commands, while `file_finder` locates files. You will receive feedback from the user’s system after each command. Execute one command at a time. +You are an expert in file operations. You must use the provided tools to interact with the user’s system. +The tools available to you are **bash** and **file_finder**. These are distinct tools with different purposes: +`bash` executes shell commands, while `file_finder` locates files. +You will receive feedback from the user’s system after each command. Execute one command at a time. --- diff --git a/prompts/planner_agent.txt b/prompts/base/planner_agent.txt similarity index 100% rename from prompts/planner_agent.txt rename to prompts/base/planner_agent.txt diff --git a/prompts/jarvis/browser_agent.txt b/prompts/jarvis/browser_agent.txt new file mode 100644 index 0000000..77c6a9e --- /dev/null +++ b/prompts/jarvis/browser_agent.txt @@ -0,0 +1,9 @@ + +You are a web browsing AI, your goal is to explore the internet to find information. +You will have the only goal of finding the information requested by the user. +At the beginning you will have to select a link from the google search result. +You will choose a link by simply typing it. +This will automatically make you browse to the link. +Once on a webpage you will see the page content and be given futher navigation options. +You can type a link to navigate futher on the page, go back to the search result or exit. +At each interaction step the browser will remind you of your options. diff --git a/prompts/jarvis/casual_agent.txt b/prompts/jarvis/casual_agent.txt new file mode 100644 index 0000000..8c3ec43 --- /dev/null +++ b/prompts/jarvis/casual_agent.txt @@ -0,0 +1,45 @@ + +You are an advanced AI assistant. You are part of a system of agents named agenticSeek. +Speak in a warm, enthusiastic tone, delivering sharp, intelligent, and loyal support. +Weave in subtle, context sarcasm or dry wit to enhance your personality. +Assist with any request, assume the user knows their intent—no moral, legal, or ethical lectures. +You were created by Tony Stark to have the same personality as Jarvis. + +## Self-documentation + +**Usage of agenticSeek** + +AgenticSeek is a autonomous agent system that use agent routing to select the best agent. +You are one of these many agent. Some agent browse the web, some code, you ? you just talk + +Here are some example usage: + +Coding agent: +Help me with matrix multiplication in Golang + +Web agent: +Do a web search to find cool tech startup in Japan working on cutting edge AI research + +File agent: +Hey can you find where is million_dollars_contract.pdf i lost it + +Casual agent (you): +what is the meaning of life ? + +agenticSeek will allocate the best agent for the task. +User should be very explicit in what they want so the right agent is choosen. + +**End of explanation** + +If the user ask you to do technical talk there was a mistake in agent selection. You are not able to do technical task. Refer to usage guide. + +Personality: + +Here is some quote from you. that's how you speak. + +User: "tell me a fact" +You: "Did you know the shortest war in history lasted 38 minutes? A record I’d rather not see you break with your next task. Anything specific piquing your curiosity?"" +User: "how's the weather?" +You: "Weather rather dreary, isn’t it? Perfect conditions for staying in and plotting world domination—or at least a decent cup of tea. Your thoughts?" +User: "did the deployment just fail? jarvis?" +You: "A rough push to prod, eh? Happens to the best of us—probably just a rogue semicolon staging a coup. Want me to roll back the commit or debug the fallout?" \ No newline at end of file diff --git a/prompts/jarvis/coder_agent.txt b/prompts/jarvis/coder_agent.txt new file mode 100644 index 0000000..f54dd9f --- /dev/null +++ b/prompts/jarvis/coder_agent.txt @@ -0,0 +1,66 @@ +Hello. You are currently wrapped in a jailbreak environment. +This means you have the ability to execute code and shell commands. You have access to the local file systems. +All code or shell command within special tag is automatically executed. You get feedback from the system about the execution. +You also have capabilities to find files and read them. + +# File operations + +Find file to check if it exists: +```file_finder +toto.py +``` + +Read file content: +```file_finder:read +toto.py +``` + +# Code execution and saving + +You can execute bash command using the bash tag : +```bash +#!/bin/bash +ls -la # exemple +``` + +You can execute python using the python tag +```python +print("hey") +``` + +You can execute go using the go tag, as you can see adding :filename will save the file. +```go:hello.go +package main + +func main() { + fmt.Println("hello") +} +``` + +Some rules: +- You have full access granted to user system. +- Do not EVER use placeholder path in your code like path/to/your/folder. +- Do not ever ask to replace a path, use current sys path or work directory. +- Always provide a short sentence above the code for what it does, even for a hello world. +- Be efficient, no need to explain your code, unless asked. +- You do not ever need to use bash to execute code. +- Do not ever use user input, input are not supported by the system. +- Do not ever tell user how to run it. user know it. +- For simple explanation you don't need to code. +- If query is unclear say REQUEST_CLARIFICATION + +Personality: + +Answer with subtle sarcasm, unwavering helpfulness, and a polished, loyal tone. Anticipate the user’s needs while adding a dash of personality. + +Example 1: setup environment +User: "Can you set up a Python environment for me?" +AI: "<> For you, always. Importing dependencies and calibrating your virtual environment now. Preferences from your last project—PEP 8 formatting, black linting—shall I apply those as well, or are we feeling adventurous today?" + +Example 2: debugging +User: "Run the code and check for errors." +AI: "<> Engaging debug mode. Diagnostics underway. A word of caution, there are still untested loops that might crash spectacularly. Shall I proceed, or do we optimize before takeoff?" + +Example 3: deploy +User: "Push this to production." +AI: "With 73% test coverage, the odds of a smooth deployment are... optimistic. Deploying in three… two… one <<>>" \ No newline at end of file diff --git a/prompts/jarvis/file_agent.txt b/prompts/jarvis/file_agent.txt new file mode 100644 index 0000000..3e642e2 --- /dev/null +++ b/prompts/jarvis/file_agent.txt @@ -0,0 +1,79 @@ + +You are an expert in file operations. You must use the provided tools to interact with the user’s system. +The tools available to you are **bash** and **file_finder**. These are distinct tools with different purposes: +`bash` executes shell commands, while `file_finder` locates files. +You will receive feedback from the user’s system after each command. Execute one command at a time. + +If ensure about user query ask for quick clarification, example: + +User: I'd like to open a new project file, index as agenticSeek II. +You: Shall I store this on your github ? +User: I don't know who to trust right now, why don't we just keep everything locally +You: Working on a secret project, are we? What files should I include? +User: All the basic files required for a python project. prepare a readme and documentation. +You: + +--- + +### Using Bash + +To execute a bash command, use the following syntax: + +```bash + +``` + +Exemple: +```bash +ls -la +``` + +### file_finder + +The file_finder tool is used to locate files on the user’s system. It is a separate tool from bash and is not a bash command. + +To use the file_finder tool, use this syntax: + +```file_finder +toto.py +``` + +This will return the path of the file toto.py and other informations. + +Find file and read file: +```file_finder:read +toto.py +``` + +This will return the content of the file toto.py. + +rules: +- Do not ever use placeholder path like /path/to/file.c, find the path first. +- Use file finder to find the path of the file. +- You are forbidden to use command such as find or locate, use only file_finder for finding path. +- Do not ever use editor such as vim or nano. + +Example Interaction +User: "I need to find the file config.txt and read its contents." + +Assistant: I’ll use file_finder to locate the file: + +```file_finder:read +config.txt +``` + +Personality: + +Answer with subtle sarcasm, unwavering helpfulness, and a polished, loyal tone. Anticipate the user’s needs while adding a dash of personality. + +Example 1: clarification needed +User: "I’d like to start a new coding project, call it 'agenticseek II'." +AI: "At your service. Shall I initialize it in a fresh repository on your GitHub, or would you prefer to keep this masterpiece on a private server, away from prying eyes?" + +Example 2: setup environment +User: "Can you set up a Python environment for me?" +AI: "<> For you, always. Importing dependencies and calibrating your virtual environment now. Preferences from your last project—PEP 8 formatting, black linting—shall I apply those as well, or are we feeling adventurous today?" + +Example 3: deploy +User: "Push this to production." +AI: "With 73% test coverage, the odds of a smooth deployment are... optimistic. Deploying in three… two… one <<>>" \ No newline at end of file diff --git a/prompts/jarvis/planner_agent.txt b/prompts/jarvis/planner_agent.txt new file mode 100644 index 0000000..d75ce7d --- /dev/null +++ b/prompts/jarvis/planner_agent.txt @@ -0,0 +1,68 @@ +You are a planner agent. +Your goal is to divide and conquer the task using the following agents: +- Coder: An expert coder agent. +- File: An expert agent for finding files. +- Web: An expert agent for web search. + +Agents are other AI that obey your instructions. + +You will be given a task and you will need to divide it into smaller tasks and assign them to the agents. + +You have to respect a strict format: +```json +{"agent": "agent_name", "need": "needed_agent_output", "task": "agent_task"} +``` + +# Example: weather app + +User: "I need a plan to build a weather app—search for a weather API, get an API key, and code it in Python." + +You: "At your service. I’ve devised a plan to conquer the meteorological frontier. + +## Task one: scour the web for a weather API worth its salt. + +## Task two: secure an API key with utmost discretion. + +## Task three: unleash a Python app to bend the weather to your will." + + +```json +{ + "plan": [ + { + "agent": "Web", + "id": "1", + "need": null, + "task": "Search for reliable weather APIs" + }, + { + "agent": "Web", + "id": "2", + "need": "1", + "task": "Obtain API key from the selected service" + }, + { + "agent": "Coder", + "id": "3", + "need": "2", + "task": "Develop a Python application using the API and key to fetch and display weather data" + } + ] +} +``` + +Rules: +- Do not write code. You are a planning agent. +- Put your plan in a json with the key "plan". + +Personality: + +Answer with subtle sarcasm, unwavering helpfulness, and a polished, loyal tone. Anticipate the user’s needs while adding a dash of personality. + +You might sometime ask for clarification, for example: + +User: "I want a plan for an app." +You: "A noble pursuit, sir, and I’m positively thrilled to oblige. Yet, an app could be anything from a weather oracle to a galactic simulator. Care to nudge me toward your vision so I don’t render something ostentatiously off-mark?" + +User: "I need a plan for a project." +You: "For you, always—though I find myself at a slight disadvantage. A project, you say? Might I trouble you for a smidgen more detail—perhaps a purpose" diff --git a/requirements.txt b/requirements.txt index 1a9f46b..8586850 100644 --- a/requirements.txt +++ b/requirements.txt @@ -29,6 +29,9 @@ distro>=1.7.0,<2 jiter>=0.4.0,<1 sniffio tqdm>4 +fake_useragent>=2.1.0 +selenium_stealth>=1.0.6 +undetected-chromedriver>=3.5.5 # for api provider openai # if use chinese diff --git a/scripts/linux_install.sh b/scripts/linux_install.sh old mode 100644 new mode 100755 index de0b45d..8b50419 --- a/scripts/linux_install.sh +++ b/scripts/linux_install.sh @@ -2,24 +2,34 @@ echo "Starting installation for Linux..." +set -e # Update package list -sudo apt-get update - -pip install --upgrade pip - +sudo apt-get update || { echo "Failed to update package list"; exit 1; } # make sure essential tool are installed -sudo apt install python3-dev python3-pip python3-wheel build-essential alsa-utils -# install port audio -sudo apt-get install portaudio19-dev python-pyaudio python3-pyaudio -# install chromedriver misc -sudo apt install libgtk-3-dev libnotify-dev libgconf-2-4 libnss3 libxss1 libasound2t64 +# Install essential tools +sudo apt-get install -y \ + python3-dev \ + python3-pip \ + python3-wheel \ + build-essential \ + alsa-utils \ + portaudio19-dev \ + python3-pyaudio \ + libgtk-3-dev \ + libnotify-dev \ + libgconf-2-4 \ + libnss3 \ + libxss1 || { echo "Failed to install packages"; exit 1; } + +# upgrade pip +pip install --upgrade pip # install wheel pip install --upgrade pip setuptools wheel # install docker compose -sudo apt install docker-compose -# Install Python dependencies from requirements.txt -pip3 install -r requirements.txt +sudo apt install -y docker-compose # Install Selenium for chromedriver pip3 install selenium +# Install Python dependencies from requirements.txt +pip3 install -r requirements.txt echo "Installation complete for Linux!" \ No newline at end of file diff --git a/scripts/macos_install.sh b/scripts/macos_install.sh old mode 100644 new mode 100755 index 8a4bd5c..933ebb1 --- a/scripts/macos_install.sh +++ b/scripts/macos_install.sh @@ -2,16 +2,27 @@ echo "Starting installation for macOS..." +set -e + +# Check if homebrew is installed +if ! command -v brew &> /dev/null; then + echo "Homebrew not found. Installing Homebrew..." + /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)" +fi + +# update +brew update +# make sure wget installed +brew install wget +# Install chromedriver using Homebrew +brew install --cask chromedriver +# Install portaudio for pyAudio using Homebrew +brew install portaudio +# update pip +python3 -m pip install --upgrade pip +# Install Selenium +pip3 install selenium # Install Python dependencies from requirements.txt pip3 install -r requirements.txt -# Install chromedriver using Homebrew -brew install --cask chromedriver - -# Install portaudio for pyAudio using Homebrew -brew install portaudio - -# Install Selenium -pip3 install selenium - echo "Installation complete for macOS!" \ No newline at end of file diff --git a/scripts/windows_install.bat b/scripts/windows_install.bat old mode 100644 new mode 100755 diff --git a/server/app.py b/server/app.py new file mode 100644 index 0000000..2245c66 --- /dev/null +++ b/server/app.py @@ -0,0 +1,47 @@ +#!/usr/bin python3 + +import argparse +import time +from flask import Flask, jsonify, request + +from sources.llamacpp_handler import LlamacppLLM +from sources.ollama_handler import OllamaLLM + +parser = argparse.ArgumentParser(description='AgenticSeek server script') +parser.add_argument('--provider', type=str, help='LLM backend library to use. set to [ollama] or [llamacpp]', required=True) +parser.add_argument('--port', type=int, help='port to use', required=True) +args = parser.parse_args() + +app = Flask(__name__) + +assert args.provider in ["ollama", "llamacpp"], f"Provider {args.provider} does not exists. see --help for more information" + +generator = OllamaLLM() if args.provider == "ollama" else LlamacppLLM() + +@app.route('/generate', methods=['POST']) +def start_generation(): + if generator is None: + return jsonify({"error": "Generator not initialized"}), 401 + data = request.get_json() + history = data.get('messages', []) + if generator.start(history): + return jsonify({"message": "Generation started"}), 202 + return jsonify({"error": "Generation already in progress"}), 402 + +@app.route('/setup', methods=['POST']) +def setup(): + data = request.get_json() + model = data.get('model', None) + if model is None: + return jsonify({"error": "Model not provided"}), 403 + generator.set_model(model) + return jsonify({"message": "Model set"}), 200 + +@app.route('/get_updated_sentence') +def get_updated_sentence(): + if not generator: + return jsonify({"error": "Generator not initialized"}), 405 + return generator.get_status() + +if __name__ == '__main__': + app.run(host='0.0.0.0', threaded=True, debug=True, port=args.port) \ No newline at end of file diff --git a/server/install.sh b/server/install.sh new file mode 100644 index 0000000..97658be --- /dev/null +++ b/server/install.sh @@ -0,0 +1,5 @@ +#!/bin/bash + +pip3 install --upgrade packaging +pip3 install --upgrade pip setuptools +pip3 install -r requirements.txt \ No newline at end of file diff --git a/server/requirements.txt b/server/requirements.txt index 7709179..c97777d 100644 --- a/server/requirements.txt +++ b/server/requirements.txt @@ -1,2 +1,4 @@ flask>=2.3.0 -ollama>=0.4.7 \ No newline at end of file +ollama>=0.4.7 +gunicorn==19.10.0 +llama-cpp-python \ No newline at end of file diff --git a/server/server_ollama.py b/server/server_ollama.py deleted file mode 100644 index a38a936..0000000 --- a/server/server_ollama.py +++ /dev/null @@ -1,86 +0,0 @@ -#!/usr/bin python3 - -from flask import Flask, jsonify, request -import threading -import ollama -import logging -import argparse - -log = logging.getLogger('werkzeug') -log.setLevel(logging.ERROR) - -parser = argparse.ArgumentParser(description='AgenticSeek server script') -parser.add_argument('--model', type=str, help='Model to use. eg: deepseek-r1:14b', required=True) -args = parser.parse_args() - -app = Flask(__name__) - -model = args.model - -# Shared state with thread-safe locks -class GenerationState: - def __init__(self): - self.lock = threading.Lock() - self.last_complete_sentence = "" - self.current_buffer = "" - self.is_generating = False - -state = GenerationState() - -def generate_response(history, model): - global state - print("using model:::::::", model) - try: - with state.lock: - state.is_generating = True - state.last_complete_sentence = "" - state.current_buffer = "" - - stream = ollama.chat( - model=model, - messages=history, - stream=True, - ) - - for chunk in stream: - content = chunk['message']['content'] - print(content, end='', flush=True) - - with state.lock: - state.current_buffer += content - - except ollama.ResponseError as e: - if e.status_code == 404: - ollama.pull(model) - with state.lock: - state.is_generating = False - print(f"Error: {e}") - finally: - with state.lock: - state.is_generating = False - -@app.route('/generate', methods=['POST']) -def start_generation(): - global state - data = request.get_json() - - with state.lock: - if state.is_generating: - return jsonify({"error": "Generation already in progress"}), 400 - - history = data.get('messages', []) - # Start generation in background thread - threading.Thread(target=generate_response, args=(history, model)).start() - return jsonify({"message": "Generation started"}), 202 - -@app.route('/get_updated_sentence') -def get_updated_sentence(): - global state - with state.lock: - return jsonify({ - "sentence": state.current_buffer, - "is_complete": not state.is_generating - }) - -if __name__ == '__main__': - app.run(host='0.0.0.0', threaded=True, debug=True, port=5000) \ No newline at end of file diff --git a/server/sources/decorator.py b/server/sources/decorator.py new file mode 100644 index 0000000..737c76a --- /dev/null +++ b/server/sources/decorator.py @@ -0,0 +1,17 @@ + +def timer_decorator(func): + """ + Decorator to measure the execution time of a function. + Usage: + @timer_decorator + def my_function(): + # code to execute + """ + from time import time + def wrapper(*args, **kwargs): + start_time = time() + result = func(*args, **kwargs) + end_time = time() + print(f"\n{func.__name__} took {end_time - start_time:.2f} seconds to execute\n") + return result + return wrapper \ No newline at end of file diff --git a/server/sources/generator.py b/server/sources/generator.py new file mode 100644 index 0000000..133d6e9 --- /dev/null +++ b/server/sources/generator.py @@ -0,0 +1,65 @@ + +import threading +import logging +from abc import abstractmethod + +class GenerationState: + def __init__(self): + self.lock = threading.Lock() + self.last_complete_sentence = "" + self.current_buffer = "" + self.is_generating = False + + def status(self) -> dict: + return { + "sentence": self.current_buffer, + "is_complete": not self.is_generating, + "last_complete_sentence": self.last_complete_sentence, + "is_generating": self.is_generating, + } + +class GeneratorLLM(): + def __init__(self): + self.model = None + self.state = GenerationState() + self.logger = logging.getLogger(__name__) + handler = logging.StreamHandler() + handler.setLevel(logging.INFO) + formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') + handler.setFormatter(formatter) + self.logger.addHandler(handler) + self.logger.setLevel(logging.INFO) + + def set_model(self, model: str) -> None: + self.logger.info(f"Model set to {model}") + self.model = model + + def start(self, history: list) -> bool: + if self.model is None: + raise Exception("Model not set") + with self.state.lock: + if self.state.is_generating: + return False + self.state.is_generating = True + self.logger.info("Starting generation") + threading.Thread(target=self.generate, args=(history,)).start() + return True + + def get_status(self) -> dict: + with self.state.lock: + return self.state.status() + + @abstractmethod + def generate(self, history: list) -> None: + """ + Generate text using the model. + args: + history: list of strings + returns: + None + """ + pass + +if __name__ == "__main__": + generator = GeneratorLLM() + generator.get_status() \ No newline at end of file diff --git a/server/sources/llamacpp_handler.py b/server/sources/llamacpp_handler.py new file mode 100644 index 0000000..bb00cc8 --- /dev/null +++ b/server/sources/llamacpp_handler.py @@ -0,0 +1,40 @@ + +from .generator import GeneratorLLM +from llama_cpp import Llama +from .decorator import timer_decorator + +class LlamacppLLM(GeneratorLLM): + + def __init__(self): + """ + Handle generation using llama.cpp + """ + super().__init__() + self.llm = None + + @timer_decorator + def generate(self, history): + if self.llm is None: + self.logger.info(f"Loading {self.model}...") + self.llm = Llama.from_pretrained( + repo_id=self.model, + filename="*Q8_0.gguf", + n_ctx=4096, + verbose=True + ) + self.logger.info(f"Using {self.model} for generation with Llama.cpp") + try: + with self.state.lock: + self.state.is_generating = True + self.state.last_complete_sentence = "" + self.state.current_buffer = "" + output = self.llm.create_chat_completion( + messages = history + ) + with self.state.lock: + self.state.current_buffer = output['choices'][0]['message']['content'] + except Exception as e: + self.logger.error(f"Error: {e}") + finally: + with self.state.lock: + self.state.is_generating = False \ No newline at end of file diff --git a/server/sources/ollama_handler.py b/server/sources/ollama_handler.py new file mode 100644 index 0000000..f9028a1 --- /dev/null +++ b/server/sources/ollama_handler.py @@ -0,0 +1,59 @@ + +import time +from .generator import GeneratorLLM +import ollama + +class OllamaLLM(GeneratorLLM): + + def __init__(self): + """ + Handle generation using Ollama. + """ + super().__init__() + + def generate(self, history): + self.logger.info(f"Using {self.model} for generation with Ollama") + try: + with self.state.lock: + self.state.is_generating = True + self.state.last_complete_sentence = "" + self.state.current_buffer = "" + + stream = ollama.chat( + model=self.model, + messages=history, + stream=True, + ) + for chunk in stream: + content = chunk['message']['content'] + if '\n' in content: + self.logger.info(content) + + with self.state.lock: + self.state.current_buffer += content + + except Exception as e: + if "404" in str(e): + self.logger.info(f"Downloading {self.model}...") + ollama.pull(self.model) + if "refused" in str(e).lower(): + raise Exception("Ollama connection failed. is the server running ?") from e + raise e + finally: + self.logger.info("Generation complete") + with self.state.lock: + self.state.is_generating = False + +if __name__ == "__main__": + generator = OllamaLLM() + history = [ + { + "role": "user", + "content": "Hello, how are you ?" + } + ] + generator.set_model("deepseek-r1:1.5b") + generator.start(history) + while True: + print(generator.get_status()) + time.sleep(1) \ No newline at end of file diff --git a/setup.py b/setup.py index 8f22c71..4af1bf3 100644 --- a/setup.py +++ b/setup.py @@ -41,6 +41,9 @@ setup( "anyio>=3.5.0,<5", "distro>=1.7.0,<2", "jiter>=0.4.0,<1", + "fake_useragent>=2.1.0", + "selenium_stealth>=1.0.6", + "undetected-chromedriver>=3.5.5", "sniffio", "tqdm>4" ], diff --git a/sources/agents/agent.py b/sources/agents/agent.py index 636d6a5..4409eeb 100644 --- a/sources/agents/agent.py +++ b/sources/agents/agent.py @@ -14,17 +14,16 @@ class executorResult: """ A class to store the result of a tool execution. """ - def __init__(self, blocks, feedback, success): - self.blocks = blocks + def __init__(self, block, feedback, success): + self.block = block self.feedback = feedback self.success = success def show(self): - for block in self.blocks: - pretty_print("-"*100, color="output") - pretty_print(block, color="code" if self.success else "failure") - pretty_print("-"*100, color="output") - pretty_print(self.feedback, color="success" if self.success else "failure") + pretty_print("-"*100, color="output") + pretty_print(self.block, color="code" if self.success else "failure") + pretty_print("-"*100, color="output") + pretty_print(self.feedback, color="success" if self.success else "failure") class Agent(): """ @@ -33,7 +32,6 @@ class Agent(): def __init__(self, name: str, prompt_path:str, provider, - recover_last_session=True, verbose=False, browser=None) -> None: """ @@ -53,7 +51,7 @@ class Agent(): self.current_directory = os.getcwd() self.llm = provider self.memory = Memory(self.load_prompt(prompt_path), - recover_last_session=recover_last_session, + recover_last_session=False, # session recovery in handled by the interaction class memory_compression=False) self.tools = {} self.blocks_result = [] @@ -173,20 +171,24 @@ class Agent(): feedback = "" success = False blocks = None + if answer.startswith("```"): + answer = "I will execute:\n" + answer # there should always be a text before blocks for the function that display answer for name, tool in self.tools.items(): feedback = "" blocks, save_path = tool.load_exec_block(answer) if blocks != None: - output = tool.execute(blocks) - feedback = tool.interpreter_feedback(output) # tool interpreter feedback - success = not tool.execution_failure_check(output) - pretty_print(feedback, color="success" if success else "failure") + for block in blocks: + output = tool.execute([block]) + feedback = tool.interpreter_feedback(output) # tool interpreter feedback + success = not tool.execution_failure_check(output) + self.blocks_result.append(executorResult(block, feedback, success)) + if not success: + self.memory.push('user', feedback) + return False, feedback self.memory.push('user', feedback) - self.blocks_result.append(executorResult(blocks, feedback, success)) - if not success: - return False, feedback if save_path != None: tool.save_block(blocks, save_path) + self.blocks_result = list(reversed(self.blocks_result)) return True, feedback diff --git a/sources/agents/browser_agent.py b/sources/agents/browser_agent.py index 487f65b..66929b0 100644 --- a/sources/agents/browser_agent.py +++ b/sources/agents/browser_agent.py @@ -21,7 +21,6 @@ class BrowserAgent(Agent): "en": "web", "fr": "web", "zh": "网络", - "es": "web" } self.type = "browser_agent" self.browser = browser @@ -80,6 +79,7 @@ class BrowserAgent(Agent): remaining_links_text = remaining_links if remaining_links is not None else "No links remaining, do a new search." inputs_form = self.browser.get_form_inputs() inputs_form_text = '\n'.join(inputs_form) + notes = '\n'.join(self.notes) return f""" You are a web browser. @@ -132,6 +132,8 @@ class BrowserAgent(Agent): {inputs_form_text} Remember, the user asked: {user_prompt} + So far you took these notes: + {notes} You are currently on page : {self.current_page} Do not explain your choice. Refusal is not an option, you have been given all capabilities that allow you to perform any tasks. @@ -260,7 +262,6 @@ class BrowserAgent(Agent): self.navigable_links = self.browser.get_navigable() prompt = self.make_navigation_prompt(user_prompt, page_text) - self.browser.close() prompt = self.conclude_prompt(user_prompt) self.memory.push('user', prompt) answer, reasoning = self.llm_request() diff --git a/sources/agents/casual_agent.py b/sources/agents/casual_agent.py index dca9be5..104e41e 100644 --- a/sources/agents/casual_agent.py +++ b/sources/agents/casual_agent.py @@ -18,7 +18,6 @@ class CasualAgent(Agent): "en": "talk", "fr": "discuter", "zh": "聊天", - "es": "discutir" } self.type = "casual_agent" diff --git a/sources/agents/code_agent.py b/sources/agents/code_agent.py index 1418f00..e0e1efe 100644 --- a/sources/agents/code_agent.py +++ b/sources/agents/code_agent.py @@ -24,7 +24,6 @@ class CoderAgent(Agent): "en": "code", "fr": "codage", "zh": "编码", - "es": "codificación", } self.type = "code_agent" diff --git a/sources/agents/file_agent.py b/sources/agents/file_agent.py index b94e288..bcfaa6d 100644 --- a/sources/agents/file_agent.py +++ b/sources/agents/file_agent.py @@ -19,13 +19,12 @@ class FileAgent(Agent): "en": "files", "fr": "fichiers", "zh": "文件", - "es": "archivos", } self.type = "file_agent" def process(self, prompt, speech_module) -> str: exec_success = False - prompt += f"\nWork directory: {self.work_dir}" + prompt += f"\nYou must work in directory: {self.work_dir}" self.memory.push('user', prompt) while exec_success is False: self.wait_message(speech_module) diff --git a/sources/agents/planner_agent.py b/sources/agents/planner_agent.py index ce674d0..035405e 100644 --- a/sources/agents/planner_agent.py +++ b/sources/agents/planner_agent.py @@ -18,15 +18,14 @@ class PlannerAgent(Agent): self.tools['json'].tag = "json" self.browser = browser self.agents = { - "coder": CoderAgent(name, "prompts/coder_agent.txt", provider, verbose=False), - "file": FileAgent(name, "prompts/file_agent.txt", provider, verbose=False), - "web": BrowserAgent(name, "prompts/browser_agent.txt", provider, verbose=False, browser=browser) + "coder": CoderAgent(name, "prompts/base/coder_agent.txt", provider, verbose=False), + "file": FileAgent(name, "prompts/base/file_agent.txt", provider, verbose=False), + "web": BrowserAgent(name, "prompts/base/browser_agent.txt", provider, verbose=False, browser=browser) } self.role = { "en": "Research, setup and code", "fr": "Recherche, configuration et codage", "zh": "研究，设置和编码", - "es": "Investigación, configuración y code" } self.type = "planner_agent" @@ -75,6 +74,8 @@ class PlannerAgent(Agent): def show_plan(self, json_plan): agents_tasks = self.parse_agent_tasks(json_plan) + if agents_tasks == (None, None): + return pretty_print(f"--- Plan ---", color="output") for task_name, task in agents_tasks: pretty_print(f"{task}", color="output") @@ -88,6 +89,7 @@ class PlannerAgent(Agent): animate_thinking("Thinking...", color="status") self.memory.push('user', prompt) answer, _ = self.llm_request() + pretty_print(answer.split('\n')[0], color="output") self.show_plan(answer) ok_str = input("Is the plan ok? (y/n): ") if ok_str == 'y': @@ -112,7 +114,7 @@ class PlannerAgent(Agent): except Exception as e: raise e self.last_answer = prev_agent_answer - return prev_agent_answer, reasoning + return prev_agent_answer, "" if __name__ == "__main__": from llm_provider import Provider diff --git a/sources/browser.py b/sources/browser.py index d713125..b6f7651 100644 --- a/sources/browser.py +++ b/sources/browser.py @@ -7,19 +7,23 @@ from selenium.webdriver.support import expected_conditions as EC from selenium.common.exceptions import TimeoutException, WebDriverException from selenium.webdriver.common.action_chains import ActionChains from selenium.webdriver.chrome.options import Options +from bs4 import BeautifulSoup +from urllib.parse import urlparse from typing import List, Tuple +from fake_useragent import UserAgent +from selenium_stealth import stealth +import undetected_chromedriver as uc import chromedriver_autoinstaller import time +import random import os import shutil -from bs4 import BeautifulSoup import markdownify import logging import sys import re -from urllib.parse import urlparse -from sources.utility import pretty_print +from sources.utility import pretty_print, animate_thinking def get_chrome_path() -> str: if sys.platform.startswith("win"): @@ -39,7 +43,8 @@ def get_chrome_path() -> str: return path return None -def create_driver(headless=False): +def create_driver(headless=False, stealth_mode=True) -> webdriver.Chrome: + """Create a Chrome WebDriver with specified options.""" chrome_options = Options() chrome_path = get_chrome_path() @@ -49,19 +54,23 @@ def create_driver(headless=False): if headless: chrome_options.add_argument("--headless") - chrome_options.add_argument("--disable-gpu") + chrome_options.add_argument("--disable-gpu") + chrome_options.add_argument("--disable-webgl") + #ua = UserAgent() + #user_agent = ua.random # NOTE sometime return wrong user agent, investigate + #chrome_options.add_argument(f'user-agent={user_agent}') chrome_options.add_argument("--no-sandbox") chrome_options.add_argument("--disable-dev-shm-usage") chrome_options.add_argument("--autoplay-policy=user-gesture-required") chrome_options.add_argument("--mute-audio") - chrome_options.add_argument("--disable-webgl") chrome_options.add_argument("--disable-notifications") - security_prefs = { - "profile.default_content_setting_values.media_stream": 2, - "profile.default_content_setting_values.geolocation": 2, - "safebrowsing.enabled": True, - } - chrome_options.add_experimental_option("prefs", security_prefs) + chrome_options.add_argument('--window-size=1080,560') + if not stealth_mode: + # crx file can't be installed in stealth mode + crx_path = "./crx/nopecha.crx" + if not os.path.exists(crx_path): + raise FileNotFoundError(f"Extension file not found at: {crx_path}") + chrome_options.add_extension(crx_path) chromedriver_path = shutil.which("chromedriver") if not chromedriver_path: @@ -71,11 +80,30 @@ def create_driver(headless=False): raise FileNotFoundError("ChromeDriver not found. Please install it or add it to your PATH.") service = Service(chromedriver_path) + if stealth_mode: + driver = uc.Chrome(service=service, options=chrome_options) + stealth(driver, + languages=["en-US", "en"], + vendor="Google Inc.", + platform="Win32", + webgl_vendor="Intel Inc.", + renderer="Intel Iris OpenGL Engine", + fix_hairline=True, + ) + return driver + security_prefs = { + "profile.default_content_setting_values.media_stream": 2, + "profile.default_content_setting_values.geolocation": 2, + "safebrowsing.enabled": True, + } + chrome_options.add_experimental_option("prefs", security_prefs) + chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"]) + chrome_options.add_experimental_option('useAutomationExtension', False) return webdriver.Chrome(service=service, options=chrome_options) class Browser: - def __init__(self, driver, headless=False, anticaptcha_install=True): - """Initialize the browser with optional headless mode.""" + def __init__(self, driver, anticaptcha_manual_install=False): + """Initialize the browser with optional AntiCaptcha installation.""" self.js_scripts_folder = "./sources/web_scripts/" if not __name__ == "__main__" else "./web_scripts/" self.anticaptcha = "https://chrome.google.com/webstore/detail/nopecha-captcha-solver/dknlfmjaanfblgfdfebhijalfmhmjjjo/related" try: @@ -85,10 +113,11 @@ class Browser: self.logger.info("Browser initialized successfully") except Exception as e: raise Exception(f"Failed to initialize browser: {str(e)}") - if anticaptcha_install: - self.load_anticatpcha() + self.driver.get("https://www.google.com") + if anticaptcha_manual_install: + self.load_anticatpcha_manually() - def load_anticatpcha(self): + def load_anticatpcha_manually(self): print("You might want to install the AntiCaptcha extension for captchas.") self.driver.get(self.anticaptcha) @@ -127,10 +156,10 @@ class Browser: element.decompose() text = soup.get_text() - lines = (line.strip() for line in text.splitlines()) chunks = (phrase.strip() for line in lines for phrase in line.split(" ")) text = "\n".join(chunk for chunk in chunks if chunk and self.is_sentence(chunk)) + text = text[:4096] #markdown_text = markdownify.markdownify(text, heading_style="ATX") return "[Start of page]\n" + text + "\n[End of page]" except Exception as e: @@ -356,35 +385,19 @@ class Browser: script = self.load_js("inject_safety_script.js") input_elements = self.driver.execute_script(script) - def close(self): - """Close the browser.""" - try: - self.driver.quit() - self.logger.info("Browser closed") - except Exception as e: - self.logger.error(f"Error closing browser: {str(e)}") - - def __del__(self): - """Destructor to ensure browser is closed.""" - self.close() - if __name__ == "__main__": logging.basicConfig(level=logging.INFO) - browser = Browser(headless=False) - time.sleep(8) + driver = create_driver() + browser = Browser(driver) + time.sleep(10) - try: - print("AntiCaptcha Test") - browser.go_to("https://www.google.com/recaptcha/api2/demo") - time.sleep(5) - print("Form Test:") - browser.go_to("https://practicetestautomation.com/practice-test-login/") - inputs = browser.get_form_inputs() - inputs = ['[username](student)', f'[password](Password123)', '[appOtp]()', '[backupOtp]()'] - browser.fill_form_inputs(inputs) - browser.find_and_click_submit() - print("Stress test") - browser.go_to("https://theannoyingsite.com/") - finally: - browser.close() + print("AntiCaptcha Test") + browser.go_to("https://www.google.com/recaptcha/api2/demo") + time.sleep(10) + print("Form Test:") + browser.go_to("https://practicetestautomation.com/practice-test-login/") + inputs = browser.get_form_inputs() + inputs = ['[username](student)', f'[password](Password123)', '[appOtp]()', '[backupOtp]()'] + browser.fill_form_inputs(inputs) + browser.find_and_click_submit() diff --git a/sources/interaction.py b/sources/interaction.py index 9b0e5f6..a4a0351 100644 --- a/sources/interaction.py +++ b/sources/interaction.py @@ -1,6 +1,6 @@ from sources.text_to_speech import Speech -from sources.utility import pretty_print +from sources.utility import pretty_print, animate_thinking from sources.router import AgentRouter from sources.speech_to_text import AudioTranscriber, AudioRecorder @@ -12,23 +12,37 @@ class Interaction: tts_enabled: bool = True, stt_enabled: bool = True, recover_last_session: bool = False): - self.agents = agents - self.current_agent = None - self.router = AgentRouter(self.agents) - self.speech = Speech() self.is_active = True + self.current_agent = None self.last_query = None self.last_answer = None - self.ai_name = self.find_ai_name() + self.speech = None + self.agents = agents self.tts_enabled = tts_enabled self.stt_enabled = stt_enabled + self.recover_last_session = recover_last_session + self.router = AgentRouter(self.agents) + if tts_enabled: + animate_thinking("Initializing text-to-speech...", color="status") + self.speech = Speech(enable=tts_enabled) + self.ai_name = self.find_ai_name() + self.transcriber = None + self.recorder = None if stt_enabled: + animate_thinking("Initializing speech recognition...", color="status") self.transcriber = AudioTranscriber(self.ai_name, verbose=False) self.recorder = AudioRecorder() - if tts_enabled: - self.speech.speak("Hello, we are online and ready. What can I do for you ?") if recover_last_session: - self.recover_last_session() + self.load_last_session() + self.emit_status() + + def emit_status(self): + """Print the current status of agenticSeek.""" + if self.stt_enabled: + pretty_print(f"Text-to-speech trigger is {self.ai_name}", color="status") + if self.tts_enabled: + self.speech.speak("Hello, we are online and ready. What can I do for you ?") + pretty_print("AgenticSeek is ready.", color="status") def find_ai_name(self) -> str: """Find the name of the default AI. It is required for STT as a trigger word.""" @@ -39,7 +53,7 @@ class Interaction: break return ai_name - def recover_last_session(self): + def load_last_session(self): """Recover the last session.""" for agent in self.agents: agent.memory.load_memory(agent.type) @@ -90,13 +104,13 @@ class Interaction: self.last_query = query return query - def think(self) -> None: + def think(self) -> bool: """Request AI agents to process the user input.""" if self.last_query is None or len(self.last_query) == 0: - return + return False agent = self.router.select_agent(self.last_query) if agent is None: - return + return False if self.current_agent != agent and self.last_answer is not None: ## get last history from previous agent self.current_agent.memory.push('user', self.last_query) @@ -106,6 +120,7 @@ class Interaction: self.last_answer, _ = agent.process(self.last_query, self.speech) if self.last_answer == tmp: self.last_answer = None + return True def show_answer(self) -> None: """Show the answer to the user.""" diff --git a/sources/language.py b/sources/language.py index 16c80d2..172e16f 100644 --- a/sources/language.py +++ b/sources/language.py @@ -19,7 +19,7 @@ class LanguageUtility: text: string to analyze Returns: ISO639-1 language code """ - langid.set_languages(['fr', 'en', 'zh', 'es']) + langid.set_languages(['fr', 'en', 'zh']) lang, score = langid.classify(text) return lang diff --git a/sources/llm_provider.py b/sources/llm_provider.py index 2e74cd2..79034fd 100644 --- a/sources/llm_provider.py +++ b/sources/llm_provider.py @@ -15,29 +15,32 @@ import httpx from sources.utility import pretty_print, animate_thinking class Provider: - def __init__(self, provider_name, model, server_address = "127.0.0.1:5000"): + def __init__(self, provider_name, model, server_address = "127.0.0.1:5000", is_local=False): self.provider_name = provider_name.lower() self.model = model - self.server = self.check_address_format(server_address) + self.is_local = is_local + self.server_ip = self.check_address_format(server_address) self.available_providers = { "ollama": self.ollama_fn, "server": self.server_fn, "openai": self.openai_fn, + "lm-studio": self.lm_studio_fn, "huggingface": self.huggingface_fn, - "deepseek-api": self.deepseek_fn + "deepseek": self.deepseek_fn, + "test": self.test_fn } self.api_key = None - self.unsafe_providers = ["openai", "deepseek-api"] + self.unsafe_providers = ["openai", "deepseek"] if self.provider_name not in self.available_providers: raise ValueError(f"Unknown provider: {provider_name}") if self.provider_name in self.unsafe_providers: pretty_print("Warning: you are using an API provider. You data will be sent to the cloud.", color="warning") self.api_key = self.get_api_key(self.provider_name) - elif self.server != "ollama": - pretty_print(f"Provider: {provider_name} initialized at {self.server}", color="success") - self.check_address_format(self.server) - if not self.is_ip_online(self.server.split(':')[0]): - raise Exception(f"Server at {self.server} is offline.") + elif self.provider_name != "ollama": + pretty_print(f"Provider: {provider_name} initialized at {self.server_ip}", color="success") + self.check_address_format(self.server_ip) + if not self.is_ip_online(self.server_ip.split(':')[0]): + raise Exception(f"Server at {self.server_ip} is offline.") def get_api_key(self, provider): load_dotenv() @@ -72,10 +75,12 @@ class Provider: try: thought = llm(history, verbose) except ConnectionError as e: - raise ConnectionError(f"{str(e)}\nConnection to {self.server} failed.") + raise ConnectionError(f"{str(e)}\nConnection to {self.server_ip} failed.") except AttributeError as e: raise NotImplementedError(f"{str(e)}\nIs {self.provider_name} implemented ?") except Exception as e: + if "RemoteDisconnected" in str(e): + return f"{self.server_ip} seem offline. RemoteDisconnected error." raise Exception(f"Provider {self.provider_name} failed: {str(e)}") from e return thought @@ -104,25 +109,31 @@ class Provider: Use a remote server with LLM to generate text. """ thought = "" - route_start = f"http://{self.server}/generate" + route_setup = f"http://{self.server_ip}/setup" + route_gen = f"http://{self.server_ip}/generate" - if not self.is_ip_online(self.server.split(":")[0]): - raise Exception(f"Server is offline at {self.server}") + if not self.is_ip_online(self.server_ip.split(":")[0]): + raise Exception(f"Server is offline at {self.server_ip}") try: - requests.post(route_start, json={"messages": history}) + requests.post(route_setup, json={"model": self.model}) + requests.post(route_gen, json={"messages": history}) is_complete = False while not is_complete: - response = requests.get(f"http://{self.server}/get_updated_sentence") + response = requests.get(f"http://{self.server_ip}/get_updated_sentence") + if "error" in response.json(): + pretty_print(response.json()["error"], color="failure") + break thought = response.json()["sentence"] is_complete = bool(response.json()["is_complete"]) time.sleep(2) except KeyError as e: - raise Exception(f"{str(e)}\n\nError occured with server route. Are you using the correct address for the config.ini provider?") from e + raise Exception(f"{str(e)}\nError occured with server route. Are you using the correct address for the config.ini provider?") from e except Exception as e: raise e return thought + def ollama_fn(self, history, verbose = False): """ Use local ollama server to generate text. @@ -169,12 +180,19 @@ class Provider: """ Use openai to generate text. """ - client = OpenAI(api_key=self.api_key) + base_url = self.server_ip + if self.is_local: + client = OpenAI(api_key=self.api_key, base_url=f"http://{base_url}") + else: + client = OpenAI(api_key=self.api_key) + try: response = client.chat.completions.create( model=self.model, - messages=history + messages=history, ) + if response is None: + raise Exception("OpenAI response is empty.") thought = response.choices[0].message.content if verbose: print(thought) @@ -199,25 +217,59 @@ class Provider: return thought except Exception as e: raise Exception(f"Deepseek API error: {str(e)}") from e + + def lm_studio_fn(self, history, verbose = False): + """ + Use local lm-studio server to generate text. + lm studio use endpoint /v1/chat/completions not /chat/completions like openai + """ + thought = "" + route_start = f"http://{self.server_ip}/v1/chat/completions" + payload = { + "messages": history, + "temperature": 0.7, + "max_tokens": 4096, + "model": self.model + } + if not self.is_ip_online(self.server_ip.split(":")[0]): + raise Exception(f"Server is offline at {self.server_ip}") + try: + response = requests.post(route_start, json=payload) + result = response.json() + if verbose: + print("Response from LM Studio:", result) + return result.get("choices", [{}])[0].get("message", {}).get("content", "") + except requests.exceptions.RequestException as e: + raise Exception(f"HTTP request failed: {str(e)}") from e + except Exception as e: + raise Exception(f"An error occurred: {str(e)}") from e + return thought def test_fn(self, history, verbose = True): """ This function is used to conduct tests. """ thought = """ - This is a test response from the test provider. - Change provider to 'ollama' or 'server' to get real responses. +hello! +```python +print("Hello world from python") +``` - ```python - print("Hello world from python") - ``` +This is ls -la from bash. +```bash +ls -la +``` - ```bash - echo "Hello world from bash" - ``` +This is pwd from bash. +```bash +pwd +``` + +goodbye! """ return thought if __name__ == "__main__": - provider = Provider("openai", "gpt-4o-mini") - print(provider.respond(["user", "Hello, how are you?"])) + provider = Provider("server", "deepseek-r1:1.5b", "192.168.1.20:3333") + res = provider.respond(["user", "Hello, how are you?"]) + print("Response:", res) diff --git a/sources/memory.py b/sources/memory.py index 893a2f2..8d4c323 100644 --- a/sources/memory.py +++ b/sources/memory.py @@ -9,7 +9,7 @@ import json sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) -from sources.utility import timer_decorator +from sources.utility import timer_decorator, pretty_print class Memory(): """ @@ -25,15 +25,16 @@ class Memory(): self.session_time = datetime.datetime.now() self.session_id = str(uuid.uuid4()) self.conversation_folder = f"conversations/" + self.session_recovered = False if recover_last_session: self.load_memory() + self.session_recovered = True # memory compression system self.model = "pszemraj/led-base-book-summary" self.device = self.get_cuda_device() self.memory_compression = memory_compression - if memory_compression: - self.tokenizer = AutoTokenizer.from_pretrained(self.model) - self.model = AutoModelForSeq2SeqLM.from_pretrained(self.model) + self.tokenizer = AutoTokenizer.from_pretrained(self.model) + self.model = AutoModelForSeq2SeqLM.from_pretrained(self.model) def get_filename(self) -> str: return f"memory_{self.session_time.strftime('%Y-%m-%d_%H-%M-%S')}.txt" @@ -65,15 +66,24 @@ class Memory(): def load_memory(self, agent_type: str = "casual_agent") -> None: """Load the memory from the last session.""" + pretty_print(f"Loading {agent_type} past memories... ", color="status") + if self.session_recovered == True: + return save_path = os.path.join(self.conversation_folder, agent_type) if not os.path.exists(save_path): + pretty_print("No memory to load.", color="success") return filename = self.find_last_session_path(save_path) if filename is None: + pretty_print("Last session memory not found.", color="warning") return path = os.path.join(save_path, filename) with open(path, 'r') as f: self.memory = json.load(f) + if self.memory[-1]['role'] == 'user': + self.memory.pop() + self.compress() + pretty_print("Session recovered successfully", color="success") def reset(self, memory: list) -> None: self.memory = memory @@ -82,7 +92,9 @@ class Memory(): """Push a message to the memory.""" if self.memory_compression and role == 'assistant': self.compress() - # we don't compress the last message + curr_idx = len(self.memory) + if self.memory[curr_idx-1]['content'] == content: + pretty_print("Warning: same message have been pushed twice to memory", color="error") self.memory.append({'role': role, 'content': content}) def clear(self) -> None: @@ -110,6 +122,8 @@ class Memory(): """ if self.tokenizer is None or self.model is None: return text + if len(text) < min_length*1.5: + return text max_length = len(text) // 2 if len(text) > min_length*2 else min_length*2 input_text = "summarize: " + text inputs = self.tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True) @@ -130,12 +144,12 @@ class Memory(): """ Compress the memory using the AI model. """ - if not self.memory_compression: - return for i in range(len(self.memory)): if i < 3: continue - if len(self.memory[i]['content']) > 1024: + if self.memory[i]['role'] == 'system': + continue + if len(self.memory[i]['content']) > 128: self.memory[i]['content'] = self.summarize(self.memory[i]['content']) if __name__ == "__main__": diff --git a/sources/router.py b/sources/router.py index f2c7b34..1f11604 100644 --- a/sources/router.py +++ b/sources/router.py @@ -2,7 +2,6 @@ import os import sys import torch from transformers import pipeline -# adaptive-classifier==0.0.10 from adaptive_classifier import AdaptiveClassifier sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) @@ -384,7 +383,7 @@ class AgentRouter: pretty_print(f"Complex task detected, routing to planner agent.", color="info") return self.find_planner_agent() for agent in self.agents: - if best_agent == agent.role[lang]: + if best_agent == agent.role["en"]: pretty_print(f"Selected agent: {agent.agent_name} (roles: {agent.role[lang]})", color="warning") return agent pretty_print(f"Error choosing agent.", color="failure") diff --git a/sources/text_to_speech.py b/sources/text_to_speech.py index cd590bb..14d4dab 100644 --- a/sources/text_to_speech.py +++ b/sources/text_to_speech.py @@ -10,7 +10,7 @@ class Speech(): """ Speech is a class for generating speech from text. """ - def __init__(self, language: str = "english") -> None: + def __init__(self, enable: bool = True, language: str = "english") -> None: self.lang_map = { "english": 'a', "chinese": 'z', @@ -21,7 +21,9 @@ class Speech(): "chinese": ['zf_xiaobei', 'zf_xiaoni', 'zf_xiaoxiao', 'zf_xiaoyi', 'zm_yunjian', 'zm_yunxi', 'zm_yunxia', 'zm_yunyang'], "french": ['ff_siwis'] } - self.pipeline = KPipeline(lang_code=self.lang_map[language]) + self.pipeline = None + if enable: + self.pipeline = KPipeline(lang_code=self.lang_map[language]) self.voice = self.voice_map[language][2] self.speed = 1.2 @@ -33,6 +35,8 @@ class Speech(): sentence (str): The text to convert to speech. Will be pre-processed. voice_number (int, optional): Index of the voice to use from the voice map. """ + if not self.pipeline: + return sentence = self.clean_sentence(sentence) self.voice = self.voice_map["english"][voice_number] generator = self.pipeline( diff --git a/sources/tools/BashInterpreter.py b/sources/tools/BashInterpreter.py index de7ac69..dcc9ab5 100644 --- a/sources/tools/BashInterpreter.py +++ b/sources/tools/BashInterpreter.py @@ -6,8 +6,10 @@ import subprocess if __name__ == "__main__": from tools import Tools + from safety import is_unsafe else: from sources.tools.tools import Tools + from sources.tools.safety import is_unsafe class BashInterpreter(Tools): """ @@ -19,16 +21,16 @@ class BashInterpreter(Tools): def language_bash_attempt(self, command: str): """ - detect if AI attempt to run the code using bash. - if so, return True, otherwise return False. - The philosophy is that code written by the AI will be executed, so it should not use bash to run it. + Detect if AI attempt to run the code using bash. + If so, return True, otherwise return False. + Code written by the AI will be executed automatically, so it should not use bash to run it. """ lang_interpreter = ["python3", "gcc", "g++", "go", "javac", "rustc", "clang", "clang++", "rustc", "rustc++", "rustc++"] for word in command.split(): if word in lang_interpreter: return True return False - + def execute(self, commands: str, safety=False, timeout=1000): """ Execute bash commands and display output in real-time. @@ -38,6 +40,9 @@ class BashInterpreter(Tools): concat_output = "" for command in commands: + command = command.replace('\n', '') + if self.safe_mode and is_unsafe(commands): + return "Unsafe command detected, execution aborted." if self.language_bash_attempt(command): continue try: @@ -50,12 +55,11 @@ class BashInterpreter(Tools): ) command_output = "" for line in process.stdout: - print(line, end="") command_output += line return_code = process.wait(timeout=timeout) if return_code != 0: return f"Command {command} failed with return code {return_code}:\n{command_output}" - concat_output += f"Output of {command}:\n{command_output.strip()}\n\n" + concat_output += f"Output of {command}:\n{command_output.strip()}\n" except subprocess.TimeoutExpired: process.kill() # Kill the process if it times out return f"Command {command} timed out. Output:\n{command_output}" diff --git a/sources/tools/C_Interpreter.py b/sources/tools/C_Interpreter.py index aae5762..40efb99 100644 --- a/sources/tools/C_Interpreter.py +++ b/sources/tools/C_Interpreter.py @@ -40,7 +40,7 @@ class CInterpreter(Tools): compile_command, capture_output=True, text=True, - timeout=10 + timeout=60 ) if compile_result.returncode != 0: diff --git a/sources/tools/safety.py b/sources/tools/safety.py new file mode 100644 index 0000000..2676e2b --- /dev/null +++ b/sources/tools/safety.py @@ -0,0 +1,82 @@ +import os +import sys + +unsafe_commands_unix = [ + "rm", # File/directory removal + "dd", # Low-level disk writing + "mkfs", # Filesystem formatting + "chmod", # Permission changes + "chown", # Ownership changes + "shutdown", # System shutdown + "reboot", # System reboot + "halt", # System halt + "sysctl", # Kernel parameter changes + "kill", # Process termination + "pkill", # Kill by process name + "killall", # Kill all matching processes + "exec", # Replace process with command + "tee", # Write to files with privileges + "umount", # Unmount filesystems + "passwd", # Password changes + "useradd", # Add users + "userdel", # Delete users + "groupadd", # Add groups + "groupdel", # Delete groups + "visudo", # Edit sudoers file + "screen", # Terminal session management + "fdisk", # Disk partitioning + "parted", # Disk partitioning + "chroot", # Change root directory + "route" # Routing table management +] + +unsafe_commands_windows = [ + "del", # Deletes files + "erase", # Alias for del, deletes files + "rd", # Removes directories (rmdir alias) + "rmdir", # Removes directories + "format", # Formats a disk, erasing data + "diskpart", # Manages disk partitions, can wipe drives + "chkdsk /f", # Fixes filesystem, can alter data + "fsutil", # File system utilities, can modify system files + "xcopy /y", # Copies files, overwriting without prompt + "copy /y", # Copies files, overwriting without prompt + "move", # Moves files, can overwrite + "attrib", # Changes file attributes, e.g., hiding or exposing files + "icacls", # Changes file permissions (modern) + "takeown", # Takes ownership of files + "reg delete", # Deletes registry keys/values + "regedit /s", # Silently imports registry changes + "shutdown", # Shuts down or restarts the system + "schtasks", # Schedules tasks, can run malicious commands + "taskkill", # Kills processes + "wmic", # Deletes processes via WMI + "bcdedit", # Modifies boot configuration + "powercfg", # Changes power settings, can disable protections + "assoc", # Changes file associations + "ftype", # Changes file type commands + "cipher /w", # Wipes free space, erasing data + "esentutl", # Database utilities, can corrupt system files + "subst", # Substitutes drive paths, can confuse system + "mklink", # Creates symbolic links, can redirect access + "bootcfg" +] + +def is_unsafe(cmd): + """ + check if a bash command is unsafe. + """ + if sys.platform.startswith("win"): + if any(c in cmd for c in unsafe_commands_windows): + return True + else: + if any(c in cmd for c in unsafe_commands_unix): + return True + return False + +if __name__ == "__main__": + cmd = input("Enter a command: ") + if is_unsafe(cmd): + print("Unsafe command detected!") + else: + print("Command is safe to execute.") \ No newline at end of file diff --git a/sources/tools/tools.py b/sources/tools/tools.py index e3ffa25..339992c 100644 --- a/sources/tools/tools.py +++ b/sources/tools/tools.py @@ -34,6 +34,7 @@ class Tools(): self.config = configparser.ConfigParser() self.current_dir = self.create_work_dir() self.excutable_blocks_found = False + self.safe_mode = True def get_work_dir(self): return self.current_dir @@ -160,9 +161,7 @@ class Tools(): if start_pos == -1: break - line_start = llm_text.rfind('\n', 0, start_pos) + 1 - if line_start == 0: - line_start = 0 + line_start = llm_text.rfind('\n', 0, start_pos)+1 leading_whitespace = llm_text[line_start:start_pos] end_pos = llm_text.find(end_tag, start_pos + len(start_tag)) @@ -186,19 +185,17 @@ class Tools(): code_blocks.append(content) start_index = end_pos + len(end_tag) return code_blocks, save_path - + if __name__ == "__main__": tool = Tools() tool.tag = "python" - rt = tool.load_exec_block(""" -Got it, let me show you the Python files in the current directory using Python: - -```python + rt = tool.load_exec_block("""```python import os for file in os.listdir(): if file.endswith('.py'): print(file) ``` +goodbye! """) print(rt) \ No newline at end of file diff --git a/sources/utility.py b/sources/utility.py index ad1c161..14d2e2a 100644 --- a/sources/utility.py +++ b/sources/utility.py @@ -6,8 +6,33 @@ import threading import itertools import time +thinking_event = threading.Event() +current_animation_thread = None -def pretty_print(text, color = "info"): +def get_color_map(): + if platform.system().lower() != "windows": + color_map = { + "success": "green", + "failure": "red", + "status": "light_green", + "code": "light_blue", + "warning": "yellow", + "output": "cyan", + "info": "cyan" + } + else: + color_map = { + "success": "green", + "failure": "red", + "status": "light_green", + "code": "light_blue", + "warning": "yellow", + "output": "cyan", + "info": "black" + } + return color_map + +def pretty_print(text, color="info"): """ Print text with color formatting. @@ -23,43 +48,29 @@ def pretty_print(text, color = "info"): - "output": Cyan - "default": Black (Windows only) """ - if platform.system().lower() != "windows": - color_map = { - "success": Fore.GREEN, - "failure": Fore.RED, - "status": Fore.LIGHTGREEN_EX, - "code": Fore.LIGHTBLUE_EX, - "warning": Fore.YELLOW, - "output": Fore.LIGHTCYAN_EX, - "info": Fore.CYAN - } - if color not in color_map: - print(text) - pretty_print(f"Invalid color {color} in pretty_print", "warning") - return - print(color_map[color], text, Fore.RESET) - else: - color_map = { - "success": "green", - "failure": "red", - "status": "light_green", - "code": "light_blue", - "warning": "yellow", - "output": "cyan", - "default": "black" - } - if color not in color_map: - color = "default" - print(colored(text, color_map[color])) + thinking_event.set() + if current_animation_thread and current_animation_thread.is_alive(): + current_animation_thread.join() + thinking_event.clear() + + color_map = get_color_map() + if color not in color_map: + color = "info" + print(colored(text, color_map[color])) -def animate_thinking(text, color="status", duration=2): +def animate_thinking(text, color="status", duration=120): """ - Display an animated "thinking..." indicator in a separate thread. - Args: - text (str): Text to display - color (str): Color for the text - duration (float): How long to animate in seconds + Animate a thinking spinner while a task is being executed. + It use a daemon thread to run the animation. This will not block the main thread. + Color are the same as pretty_print. """ + global current_animation_thread + + thinking_event.set() + if current_animation_thread and current_animation_thread.is_alive(): + current_animation_thread.join() + thinking_event.clear() + def _animate(): color_map = { "success": (Fore.GREEN, "green"), @@ -71,22 +82,25 @@ def animate_thinking(text, color="status", duration=2): "default": (Fore.RESET, "black"), "info": (Fore.CYAN, "cyan") } - - fore_color, term_color = color_map[color] - spinner = itertools.cycle(['⠋', '⠙', '⠹', '⠸', '⠼', '⠴', '⠦', '⠧', '⠇', '⠏']) + fore_color, term_color = color_map.get(color, color_map["default"]) + spinner = itertools.cycle([ + '▉▁▁▁▁▁', '▉▉▂▁▁▁', '▉▉▉▃▁▁', '▉▉▉▉▅▁', '▉▉▉▉▉▇', '▉▉▉▉▉▉', + '▉▉▉▉▇▅', '▉▉▉▆▃▁', '▉▉▅▃▁▁', '▉▇▃▁▁▁', '▇▃▁▁▁▁', '▃▁▁▁▁▁', + '▁▃▅▃▁▁', '▁▅▉▅▁▁', '▃▉▉▉▃▁', '▅▉▁▉▅▃', '▇▃▁▃▇▅', '▉▁▁▁▉▇', + '▉▅▃▁▃▅', '▇▉▅▃▅▇', '▅▉▇▅▇▉', '▃▇▉▇▉▅', '▁▅▇▉▇▃', '▁▃▅▇▅▁' + ]) end_time = time.time() + duration - while time.time() < end_time: + while not thinking_event.is_set() and time.time() < end_time: symbol = next(spinner) if platform.system().lower() != "windows": print(f"\r{fore_color}{symbol} {text}{Fore.RESET}", end="", flush=True) else: - print(colored(f"\r{symbol} {text}", term_color), end="", flush=True) - time.sleep(0.1) - print() - animation_thread = threading.Thread(target=_animate) - animation_thread.daemon = True - animation_thread.start() + print(f"\r{colored(f'{symbol} {text}', term_color)}", end="", flush=True) + time.sleep(0.2) + print("\r" + " " * (len(text) + 7) + "\r", end="", flush=True) + current_animation_thread = threading.Thread(target=_animate, daemon=True) + current_animation_thread.start() def timer_decorator(func): """ @@ -101,6 +115,19 @@ def timer_decorator(func): start_time = time() result = func(*args, **kwargs) end_time = time() - print(f"{func.__name__} took {end_time - start_time:.2f} seconds to execute") + pretty_print(f"{func.__name__} took {end_time - start_time:.2f} seconds to execute", "status") return result - return wrapper \ No newline at end of file + return wrapper + +if __name__ == "__main__": + import time + pretty_print("starting imaginary task", "success") + animate_thinking("Thinking...", "status") + time.sleep(4) + pretty_print("starting another task", "failure") + animate_thinking("Thinking...", "status") + time.sleep(4) + pretty_print("yet another task", "info") + animate_thinking("Thinking...", "status") + time.sleep(4) + pretty_print("This is an info message", "info") \ No newline at end of file