Merge pull request #164 from MervinPraison/develop

Release version 0.0.74

Author: MervinPraison

Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==0.0.73 gunicorn markdown
+RUN pip install flask praisonai==0.0.74 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

README.md

@@ -35,6 +35,7 @@ Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, rep
 | **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
 | **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
 | **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
+| **Realtime** | Real-time voice interaction with AI | [https://docs.praison.ai/ui/realtime](https://docs.praison.ai/ui/realtime) |
 
 | Other Features | Description | Docs |
 |---|---|---|
@@ -56,6 +57,7 @@ Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, rep
 | **PraisonAI Code** | `pip install "praisonai[code]"` |
 | **PraisonAI Chat** | `pip install "praisonai[chat]"` |
 | **PraisonAI Train** | `pip install "praisonai[train]"` |
+| **PraisonAI Realtime** | `pip install "praisonai[realtime]"` |
 
 ## Key Features
 
@@ -68,6 +70,7 @@ Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, rep
 - Custom Tool Integration
 - Internet Search Capability (using Crawl4AI and Tavily)
 - Vision Language Model (VLM) Support
+- Real-time Voice Interaction
 
 ## TL;DR Multi Agents
 

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ <h2 id="raises">Raises</h2>
             file.write(&#34;FROM python:3.11-slim\n&#34;)
             file.write(&#34;WORKDIR /app\n&#34;)
             file.write(&#34;COPY . .\n&#34;)
-            file.write(&#34;RUN pip install flask praisonai==0.0.73 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==0.0.74 gunicorn markdown\n&#34;)
             file.write(&#34;EXPOSE 8080\n&#34;)
             file.write(&#39;CMD [&#34;gunicorn&#34;, &#34;-b&#34;, &#34;0.0.0.0:8080&#34;, &#34;api:app&#34;]\n&#39;)
 

docs/ui/realtime.md

@@ -0,0 +1,57 @@
+# Realtime Voice Interface
+
+The Realtime Voice Interface in PraisonAI provides an interactive, voice-based communication channel with AI models. This interface allows for real-time audio input and output, enabling a more natural and dynamic conversation experience.
+
+## Features
+
+- Real-time voice input processing
+- Text-to-speech output for AI responses
+- Seamless integration with OpenAI's realtime API
+- Support for various AI models
+- Persistent conversation history
+
+## Getting Started
+
+To use the Realtime Voice Interface, follow these steps:
+
+1. Install PraisonAI with the realtime dependencies:
+   ```bash
+   pip install "praisonai[realtime]"
+   ```
+
+2. Set up your OpenAI API key:
+   ```bash
+   export OPENAI_API_KEY="your-api-key-here"
+   ```
+
+3. Launch the Realtime Voice Interface:
+   ```bash
+   praisonai realtime
+   ```
+
+## Usage
+
+Once the interface is launched:
+
+1. Click the microphone button or press 'P' to start voice input.
+2. Speak your message or query.
+3. The AI will process your input and respond with both text and voice.
+4. The conversation history is maintained for context in ongoing discussions.
+
+## Configuration
+
+You can configure various aspects of the Realtime Voice Interface:
+
+- Model selection: Choose different AI models for processing.
+- Voice settings: Adjust voice characteristics for the AI's speech output.
+- Audio settings: Configure input/output audio formats and quality.
+
+## Troubleshooting
+
+If you encounter issues:
+
+- Ensure your microphone is properly connected and permitted in your browser.
+- Check your internet connection for stable real-time communication.
+- Verify that your OpenAI API key is correctly set and has the necessary permissions.
+
+For more detailed information and advanced usage, please refer to the [PraisonAI documentation](https://docs.praison.ai).

mkdocs.yml

@@ -18,6 +18,7 @@ nav:
       - User Interface: ui/ui.md
       - Chat: ui/chat.md
       - Code: ui/code.md
+      - Realtime: ui/realtime.md
       - Train: train.md
       - CrewAI: framework/crewai.md
       - AutoGen: framework/autogen.md

poetry.lock

@@ -3,7 +3,7 @@ class Praisonai < Formula
 
     desc "AI tools for various AI applications"
     homepage "https://github.com/MervinPraison/PraisonAI"
-    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/0.0.73.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/0.0.74.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
 

praisonai.rb

@@ -130,6 +130,10 @@ def main(self):
             self.create_code_interface()
             return
 
+        if getattr(args, 'realtime', False):
+            self.create_realtime_interface()
+            return
+        
         if args.agent_file == 'train':
             package_root = os.path.dirname(os.path.abspath(__file__))
             config_yaml_destination = os.path.join(os.getcwd(), 'config.yaml')
@@ -256,6 +260,7 @@ def parse_args(self):
         parser.add_argument("--hf", type=str, help="Hugging Face model name")
         parser.add_argument("--ollama", type=str, help="Ollama model name")
         parser.add_argument("--dataset", type=str, help="Dataset name for training", default="yahma/alpaca-cleaned")
+        parser.add_argument("--realtime", action="store_true", help="Start the realtime voice interaction interface")
         args, unknown_args = parser.parse_known_args()
 
         if unknown_args and unknown_args[0] == '-b' and unknown_args[1] == 'api:app':
@@ -270,6 +275,8 @@ def parse_args(self):
         if args.agent_file == 'code':
             args.ui = 'chainlit'
             args.code = True
+        if args.agent_file == 'realtime':
+            args.realtime = True
 
         return args
 
@@ -416,6 +423,29 @@ def create_chainlit_interface(self):
         else:
             print("ERROR: Chainlit is not installed. Please install it with 'pip install \"praisonai\[ui]\"' to use the UI.")        
 
+    def create_realtime_interface(self):
+        """
+        Create a Chainlit interface for the realtime voice interaction application.
+        """
+        if CHAINLIT_AVAILABLE:
+            import praisonai
+            os.environ["CHAINLIT_PORT"] = "8088"  # Ensure this port is not in use by another service
+            root_path = os.path.join(os.path.expanduser("~"), ".praison")
+            os.environ["CHAINLIT_APP_ROOT"] = root_path
+            public_folder = os.path.join(os.path.dirname(praisonai.__file__), 'public')
+            if not os.path.exists(os.path.join(root_path, "public")):
+                if os.path.exists(public_folder):
+                    shutil.copytree(public_folder, os.path.join(root_path, "public"), dirs_exist_ok=True)
+                    logging.info("Public folder copied successfully!")
+                else:
+                    logging.info("Public folder not found in the package.")
+            else:
+                logging.info("Public folder already exists.")
+            realtime_ui_path = os.path.join(os.path.dirname(praisonai.__file__), 'ui', 'realtime.py')
+            chainlit_run([realtime_ui_path])
+        else:
+            print("ERROR: Realtime UI is not installed. Please install it with 'pip install \"praisonai[realtime]\"' to use the realtime UI.")
+
 if __name__ == "__main__":
     praison_ai = PraisonAI()
     praison_ai.main()

praisonai/cli.py

@@ -56,7 +56,7 @@ def create_dockerfile(self):
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==0.0.73 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==0.0.74 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')