Merge pull request #368 from MervinPraison/develop

Enhance train.py with Dynamic Stop Token Generation for Ollama Models

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.64 gunicorn markdown
+RUN pip install flask praisonai==2.0.67 gunicorn markdown
 EXPOSE 8080
 CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]

docs/api/praisonai/deploy.html

@@ -110,7 +110,7 @@ Loads environment variables from .env file or system and sets them.</p>
             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==2.0.64 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.67 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/train.mdx

@@ -20,6 +20,17 @@ icon: "dumbbell"
 export HF_TOKEN=xxxxxxxxxxxxxx
 ```
 
+## Initilise praisonai train
+
+```bash
+praisonai train init
+```
+
+## Required
+
+1. HF_TOKEN
+2. Below config.yaml file in the same directory
+
 ## To upload to ollama.com (Linux)
 
 ```bash

praisonai.rb

@@ -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/2.0.64.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.67.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

praisonai/cli.py

@@ -25,7 +25,6 @@ CALL_MODULE_AVAILABLE = False
 CREWAI_AVAILABLE = False
 AUTOGEN_AVAILABLE = False
 PRAISONAI_AVAILABLE = False
-TRAIN_AVAILABLE = False
 try:
     # Create necessary directories and set CHAINLIT_APP_ROOT
     if "CHAINLIT_APP_ROOT" not in os.environ:
@@ -72,12 +71,6 @@ try:
 except ImportError:
     pass
 
-try:
-    import accelerate
-    TRAIN_AVAILABLE = True
-except ImportError:
-    pass
-
 logging.basicConfig(level=os.environ.get('LOGLEVEL', 'INFO'), format='%(asctime)s - %(levelname)s - %(message)s')
 logging.getLogger('alembic').setLevel(logging.ERROR)
 logging.getLogger('gradio').setLevel(logging.ERROR)
@@ -399,13 +392,8 @@ class PraisonAI:
                 sys.exit(0)
 
             elif args.command == 'train':
-                if not TRAIN_AVAILABLE:
-                    print("[red]ERROR: Train feature is not installed. Install with:[/red]")
-                    print("\npip install \"praisonai[train]\"\n")
-                    sys.exit(1)
                 package_root = os.path.dirname(os.path.abspath(__file__))
                 config_yaml_destination = os.path.join(os.getcwd(), 'config.yaml')
-                
 
             elif args.command == 'ui':
                 if not CHAINLIT_AVAILABLE:

praisonai/deploy.py

@@ -56,7 +56,7 @@ class CloudDeployer:
             file.write("FROM python:3.11-slim\n")
             file.write("WORKDIR /app\n")
             file.write("COPY . .\n")
-            file.write("RUN pip install flask praisonai==2.0.64 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.67 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

praisonai/setup/setup_conda_env.sh

@@ -12,7 +12,7 @@ elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
     # Linux
     MINICONDA_URL="https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh"
     
-    # Check and install libcurl development package if not present
+    # Install libcurl development package if not present (Debian based)
     if command -v dpkg &> /dev/null; then
         if ! dpkg -s libcurl4-openssl-dev &> /dev/null; then
             echo "libcurl4-openssl-dev is not installed. Installing..."
@@ -25,6 +25,24 @@ elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
         echo "Non-Debian based Linux detected. Please ensure libcurl development libraries are installed."
     fi
 
+    # Check if ollama is installed and executable; if not, install it
+    if ! command -v ollama &> /dev/null; then
+        echo "Ollama is not installed. Installing Ollama..."
+        curl -fsSL https://ollama.com/install.sh | sh
+        
+        # Generate SSH key non-interactively only if it doesn't already exist
+        if [ ! -f ~/.ssh/id_ed25519 ]; then
+            echo "Generating SSH key for Ollama..."
+            ssh-keygen -t ed25519 -N "" -f ~/.ssh/id_ed25519 -q
+        else
+            echo "SSH key ~/.ssh/id_ed25519 already exists. Skipping generation."
+        fi
+        echo "Copying SSH key to /usr/share/ollama/.ollama..."
+        sudo cp ~/.ssh/id_ed25519 /usr/share/ollama/.ollama
+    else
+        echo "Ollama is already installed."
+    fi
+
 elif [[ "$OSTYPE" == "msys" || "$OSTYPE" == "win32" ]]; then
     # Windows
     MINICONDA_URL="https://repo.anaconda.com/miniconda/Miniconda3-latest-Windows-x86_64.exe"
@@ -35,12 +53,12 @@ else
     exit 1
 fi
 
-# Check if conda is already installed
+# Check if conda is installed
 if ! command -v conda &> /dev/null; then
     echo "Conda is not installed. Installing Miniconda..."
-    wget $MINICONDA_URL -O ~/miniconda.sh
-    bash ~/miniconda.sh -b -p $HOME/miniconda
-    source $HOME/miniconda/bin/activate
+    wget "$MINICONDA_URL" -O ~/miniconda.sh
+    bash ~/miniconda.sh -b -p "$HOME/miniconda"
+    source "$HOME/miniconda/bin/activate"
     conda init
 else
     echo "Conda is already installed."
@@ -48,38 +66,34 @@ fi
 
 # Create and activate the Conda environment
 ENV_NAME="praison_env"
-if conda info --envs | grep -q $ENV_NAME; then
+if conda info --envs | grep -q "$ENV_NAME"; then
     echo "Environment $ENV_NAME already exists. Recreating..."
-    conda env remove -y -n $ENV_NAME  # Remove existing environment
+    conda env remove -y -n "$ENV_NAME"
     if [[ "$OSTYPE" == "darwin"* ]]; then
-        # macOS (both Intel and M1/M2)
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 -c pytorch -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 -c pytorch -y
     elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
-        # Linux
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
     fi
 else
     echo "Creating new environment $ENV_NAME..."
     if [[ "$OSTYPE" == "darwin"* ]]; then
-        # macOS (both Intel and M1/M2)
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 -c pytorch -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 -c pytorch -y
     elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
-        # Linux
-        conda create --name $ENV_NAME python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
+        conda create --name "$ENV_NAME" python=3.10 pytorch=2.3.0 cudatoolkit=11.8 -c pytorch -c nvidia -y
     fi
 fi
 
 # Activate the environment
-source $HOME/miniconda/bin/activate $ENV_NAME
+source "$HOME/miniconda/bin/activate" "$ENV_NAME"
 
 # Install cmake via conda
 echo "Installing cmake..."
 conda install -y cmake
 
 # Get full path of pip within the activated environment
-PIP_FULL_PATH=$(conda run -n $ENV_NAME which pip)
+PIP_FULL_PATH=$(conda run -n "$ENV_NAME" which pip)
 
-# Install other packages within the activated environment using pip
+# Install other packages using pip
 $PIP_FULL_PATH install --upgrade pip 
 $PIP_FULL_PATH install "xformers==0.0.26.post1"
 $PIP_FULL_PATH install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git@038e6d4c8d40207a87297ab3aaf787c19b1006d1"

praisonai/train.py

@@ -312,26 +312,41 @@ class TrainModel:
 
     def prepare_modelfile_content(self):
         output_model = self.config["hf_model_name"]
+        # Determine stop tokens from config or infer based on model name
+        model_name = self.config["model_name"].lower()
+        if "phi" in model_name:
+            inferred_stop_tokens = ["<|end|>", "<|user|>", "<|assistant|>"]
+        elif "llava" in model_name:
+            inferred_stop_tokens = ["</s>", "USER:", "ASSSISTANT:"]
+        elif "mistral" in model_name:
+            inferred_stop_tokens = ["[INST]", "[/INST]"]
+        elif "qwen" in model_name:
+            inferred_stop_tokens = ["<|endoftext|>"]
+        elif "deepseek" in model_name:
+            inferred_stop_tokens = ["<｜begin▁of▁sentence｜>", "<｜end▁of▁sentence｜>", "<｜User｜>", "<｜Assistant｜>"]
+        else:
+            inferred_stop_tokens = ["<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"]
+        # Use stop_tokens from config if provided, otherwise use inferred
+        model_stop_tokens = self.config.get("stop_tokens", inferred_stop_tokens)
+
         gguf_path = f"{output_model}/unsloth.Q4_K_M.gguf"
         if not os.path.exists(gguf_path):
             self.model, self.hf_tokenizer = self.load_model()
             self.save_model_gguf()
+        stop_parameters = "\n".join([f'PARAMETER stop "{token}"' for token in model_stop_tokens])
         return f"""FROM {output_model}/unsloth.Q4_K_M.gguf
 
-TEMPLATE \"\"\"Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{{{ if .Prompt }}}}
+    TEMPLATE \"\"\"Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{{{ if .Prompt }}}}
 
-### Instruction:
-{{{{ .Prompt }}}}
+    ### Instruction:
+    {{{{ .Prompt }}}}
 
-{{{{ end }}}}### Response:
-{{{{ .Response }}}}\"\"\"
+    {{{{ end }}}}### Response:
+    {{{{ .Response }}}}\"\"\"
+
+    {stop_parameters}
+    """
 
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop ""
-PARAMETER stop "<|reserved_special_token_"
-"""
 
     def create_and_push_ollama_model(self):
         modelfile_content = self.prepare_modelfile_content()

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.64"
+version = "2.0.67"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration."
 readme = "README.md"
 license = ""
@@ -84,7 +84,7 @@ autogen = ["pyautogen>=0.2.19", "praisonai-tools>=0.0.7", "crewai"]
 
 [tool.poetry]
 name = "PraisonAI"
-version = "2.0.64"
+version = "2.0.67"
 description = "PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human–agent collaboration."
 authors = ["Mervin Praison"]
 license = ""

uv.lock

@@ -3060,7 +3060,7 @@ wheels = [
 
 [[package]]
 name = "praisonai"
-version = "2.0.64"
+version = "2.0.67"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },