PraisonAI 2.0.71__tar.gz → 2.0.73__tar.gz

{praisonai-2.0.71 → praisonai-2.0.73}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: PraisonAI
-Version: 2.0.71
+Version: 2.0.73
 Summary: 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.
 Author: Mervin Praison
 Requires-Python: >=3.10,<3.13

{praisonai-2.0.71 → praisonai-2.0.73}/praisonai/cli.py

@@ -189,8 +189,18 @@ 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,
+                    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)
+            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,
@@ -202,7 +212,6 @@ class PraisonAI:
                 with open('config.yaml', 'w') as f:
                     yaml.dump(config, f, default_flow_style=False, indent=2)
             else:
-                # Load existing config
                 with open(config_yaml_destination, 'r') as f:
                     config = yaml.safe_load(f)
 

{praisonai-2.0.71 → praisonai-2.0.73}/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==2.0.71 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==2.0.73 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

{praisonai-2.0.71 → praisonai-2.0.73}/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.
     """
@@ -217,23 +217,23 @@ class TrainModel:
         tokenized_dataset = self.tokenize_dataset(raw_dataset)
         print("DEBUG: Dataset tokenization complete.")
         training_args = TrainingArguments(
-            per_device_train_batch_size=2,
-            gradient_accumulation_steps=4,
-            warmup_steps=5,
-            max_steps=60,
-            learning_rate=2e-4,
-            fp16=not is_bfloat16_supported(),
-            bf16=is_bfloat16_supported(),
-            logging_steps=1,
-            optim="adamw_8bit",
-            weight_decay=0.01,
-            lr_scheduler_type="linear",
-            seed=3407,
-            output_dir="outputs",
+            per_device_train_batch_size=self.config.get("per_device_train_batch_size", 2),
+            gradient_accumulation_steps=self.config.get("gradient_accumulation_steps", 2),
+            warmup_steps=self.config.get("warmup_steps", 50),
+            max_steps=self.config.get("max_steps", 2800),
+            learning_rate=self.config.get("learning_rate", 2e-4),
+            fp16=self.config.get("fp16", not is_bfloat16_supported()),
+            bf16=self.config.get("bf16", is_bfloat16_supported()),
+            logging_steps=self.config.get("logging_steps", 15),
+            optim=self.config.get("optim", "adamw_8bit"),
+            weight_decay=self.config.get("weight_decay", 0.01),
+            lr_scheduler_type=self.config.get("lr_scheduler_type", "linear"),
+            seed=self.config.get("seed", 3407),
+            output_dir=self.config.get("output_dir", "outputs"),
             report_to="none" if not os.getenv("PRAISON_WANDB") else "wandb",
-            save_steps=100 if os.getenv("PRAISON_WANDB") else None,
+            save_steps=self.config.get("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,
+            remove_unused_columns=self.config.get("remove_unused_columns", False),
         )
         # Since the dataset is pre-tokenized, we supply a dummy dataset_text_field.
         trainer = SFTTrainer(
@@ -513,8 +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:
@@ -549,13 +547,7 @@ def main():
     args = parser.parse_args()
 
     if args.command == "train":
-        # Check if any command line args are provided that would override config
-        if any([args.model, args.hf, args.ollama, args.dataset]):
-            # Use CLI provided arguments
-            trainer_obj = TrainModel(config_path=args.config)
-        else:
-            # Use existing config.yaml without modification
-            trainer_obj = TrainModel("config.yaml")
+        trainer_obj = TrainModel(config_path=args.config)
         trainer_obj.run()
 
 if __name__ == "__main__":

{praisonai-2.0.71 → praisonai-2.0.73}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "PraisonAI"
-version = "2.0.71"
+version = "2.0.73"
 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 = "2.0.71"
+version = "2.0.73"
 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 = ""