Merge pull request #377 from MervinPraison/develop

Bump version to 2.0.72 and enhance CLI configuration in train and cli…

docker/Dockerfile

@@ -1,6 +1,6 @@
 FROM python:3.11-slim
 WORKDIR /app
 COPY . .
-RUN pip install flask praisonai==2.0.68 gunicorn markdown
+RUN pip install flask praisonai==2.0.72 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==2.0.68 gunicorn markdown\n&#34;)
+            file.write(&#34;RUN pip install flask praisonai==2.0.72 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

@@ -28,8 +28,11 @@ praisonai train init
 
 ## Required
 
-1. HF_TOKEN
-2. Below config.yaml file in the same directory
+1. Huggingface token
+2. Base model to train on (e.g. unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit)
+3. Dataset to train on (e.g. yahma/alpaca-cleaned)
+4. Huggingface model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
+5. Ollama model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
 
 ## To upload to ollama.com (Linux)
 
@@ -119,4 +122,21 @@ quantization_method:
 
 ```bash
 praisonai train
+```
+
+## wandb
+
+```bash
+wandb login
+```
+
+<Note>
+Get the key from [here](https://wandb.ai/site/login)
+</Note>
+
+```bash
+export PRAISON_WANDB=True
+export WANDB_LOG_MODEL=checkpoint
+export WANDB_PROJECT=praisonai-test
+export PRAISON_WANDB_RUN_NAME=praisonai-train  
 ```

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/2.0.68.tar.gz"
+    url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/2.0.72.tar.gz"
     sha256 "1828fb9227d10f991522c3f24f061943a254b667196b40b1a3e4a54a8d30ce32"  # Replace with actual SHA256 checksum
     license "MIT"
   

praisonai/cli.py

@@ -189,8 +189,7 @@ class PraisonAI:
             package_root = os.path.dirname(os.path.abspath(__file__))
             config_yaml_destination = os.path.join(os.getcwd(), 'config.yaml')
 
-            # Create config.yaml only if it doesn't exist or --model or --dataset is provided
-            if not os.path.exists(config_yaml_destination) or args.model or args.dataset:
+            if not os.path.exists(config_yaml_destination):
                 config = generate_config(
                     model_name=args.model,
                     hf_model_name=args.hf,
@@ -201,6 +200,20 @@ class PraisonAI:
                 )
                 with open('config.yaml', 'w') as f:
                     yaml.dump(config, f, default_flow_style=False, indent=2)
+            elif args.model or args.hf or args.ollama or (args.dataset and args.dataset != "yahma/alpaca-cleaned"):
+                config = generate_config(
+                    model_name=args.model,
+                    hf_model_name=args.hf,
+                    ollama_model_name=args.ollama,
+                    dataset=[{
+                        "name": args.dataset
+                    }]
+                )
+                with open('config.yaml', 'w') as f:
+                    yaml.dump(config, f, default_flow_style=False, indent=2)
+            else:
+                with open(config_yaml_destination, 'r') as f:
+                    config = yaml.safe_load(f)
 
             # Overwrite huggingface_save and ollama_save if --hf or --ollama are provided
             if args.hf:

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==2.0.68 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.72 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

@@ -100,6 +100,6 @@ $PIP_FULL_PATH install "unsloth[colab-new] @ git+https://github.com/unslothai/un
 $PIP_FULL_PATH install --no-deps "trl<0.9.0" peft accelerate bitsandbytes 
 $PIP_FULL_PATH install unsloth_zoo
 $PIP_FULL_PATH install cut_cross_entropy
-$PIP_FULL_PATH install sentencepiece protobuf datasets huggingface_hub hf_transfer
+$PIP_FULL_PATH install sentencepiece protobuf datasets huggingface_hub hf_transfer wandb
 
 echo "Setup completed successfully!"

praisonai/train.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 """
-This script finetunes a model using Unsloth’s fast training framework.
+This script finetunes a model using Unsloth's fast training framework.
 It supports both ShareGPT and Alpaca‑style datasets by converting raw conversation
 data into plain-text prompts using a chat template, then pre‑tokenizing the prompts.
 Extra debug logging is added to help trace the root cause of errors.
@@ -27,7 +27,7 @@ from functools import partial
 #####################################
 def formatting_prompts_func(examples, tokenizer):
     """
-    Converts each example’s conversation into a single plain-text prompt.
+    Converts each example's conversation into a single plain-text prompt.
     If the example has a "conversations" field, process it as ShareGPT-style.
     Otherwise, assume Alpaca-style data with "instruction", "input", and "output" fields.
     """
@@ -230,7 +230,9 @@ class TrainModel:
             lr_scheduler_type="linear",
             seed=3407,
             output_dir="outputs",
-            report_to="none",
+            report_to="none" if not os.getenv("PRAISON_WANDB") else "wandb",
+            save_steps=100 if os.getenv("PRAISON_WANDB") else None,
+            run_name=os.getenv("PRAISON_WANDB_RUN_NAME", "praisonai-train") if os.getenv("PRAISON_WANDB") else None,
             remove_unused_columns=False,
         )
         # Since the dataset is pre-tokenized, we supply a dummy dataset_text_field.
@@ -511,8 +513,6 @@ class TrainModel:
     {system_line}{num_ctx_line}{stop_params}
     """
 
-
-
     def create_and_push_ollama_model(self):
         modelfile_content = self.prepare_modelfile_content()
         with open("Modelfile", "w") as file:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.68"
+version = "2.0.72"
 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 = "2.0.68"
+version = "2.0.72"
 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 = "2.0.68"
+version = "2.0.72"
 source = { editable = "." }
 dependencies = [
     { name = "instructor" },