ragaai-catalyst 2.1.5.1b2__tar.gz → 2.1.5.1b3__tar.gz

{ragaai_catalyst-2.1.5.1b2/ragaai_catalyst.egg-info → ragaai_catalyst-2.1.5.1b3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ragaai_catalyst
-Version: 2.1.5.1b2
+Version: 2.1.5.1b3
 Summary: RAGA AI CATALYST
 Author-email: Kiran Scaria <kiran.scaria@raga.ai>, Kedar Gaikwad <kedar.gaikwad@raga.ai>, Dushyant Mahajan <dushyant.mahajan@raga.ai>, Siddhartha Kosti <siddhartha.kosti@raga.ai>, Ritika Goel <ritika.goel@raga.ai>, Vijay Chaurasia <vijay.chaurasia@raga.ai>, Tushar Kumar <tushar.kumar@raga.ai>
 Requires-Python: <3.13,>=3.9
@@ -22,7 +22,7 @@ Requires-Dist: langchain>=0.2.11
 Requires-Dist: openai>=1.57.0
 Requires-Dist: pandas
 Requires-Dist: groq>=0.11.0
-Requires-Dist: PyPDF2>=3.0.1
+Requires-Dist: pypdf>=5.3.1
 Requires-Dist: google-generativeai>=0.8.2
 Requires-Dist: google-genai>=1.3.0
 Requires-Dist: Markdown>=3.7

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3}/pyproject.toml

@@ -8,7 +8,7 @@ description = "RAGA AI CATALYST"
 readme = "README.md"
 requires-python = ">=3.9,<3.13"
 # license = {file = "LICENSE"}
-version = "2.1.5.1.b2"
+version = "2.1.5.1.b3"
 authors = [
     {name = "Kiran Scaria", email = "kiran.scaria@raga.ai"},
     {name = "Kedar Gaikwad", email = "kedar.gaikwad@raga.ai"},
@@ -36,7 +36,7 @@ dependencies = [
     "openai>=1.57.0",
     "pandas",
     "groq>=0.11.0",
-    "PyPDF2>=3.0.1",
+    "pypdf>=5.3.1",
     "google-generativeai>=0.8.2",
     "google-genai>=1.3.0",
     "Markdown>=3.7",  

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3}/ragaai_catalyst/synthetic_data_generation.py

@@ -3,7 +3,7 @@ import ast
 import csv
 import json
 import random
-import PyPDF2
+import pypdf
 import markdown
 import pandas as pd
 from tqdm import tqdm
@@ -105,6 +105,9 @@ class SyntheticDataGeneration:
                     raise Exception(f"{e}")
 
                 else:
+                    if "'utf-8' codec can't encode characters" in str(e):
+                        print('Encountered non utf charactes, retrying with processed text')
+                        text = str(text.encode('utf-8',errors='ignore'))
                     print(f"Retrying...")
                     continue
         
@@ -469,7 +472,7 @@ class SyntheticDataGeneration:
         """
         text = ""
         with open(file_path, 'rb') as file:
-            pdf_reader = PyPDF2.PdfReader(file)
+            pdf_reader = pypdf.PdfReader(file)
             for page in pdf_reader.pages:
                 text += page.extract_text()
         return text

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3/ragaai_catalyst.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ragaai_catalyst
-Version: 2.1.5.1b2
+Version: 2.1.5.1b3
 Summary: RAGA AI CATALYST
 Author-email: Kiran Scaria <kiran.scaria@raga.ai>, Kedar Gaikwad <kedar.gaikwad@raga.ai>, Dushyant Mahajan <dushyant.mahajan@raga.ai>, Siddhartha Kosti <siddhartha.kosti@raga.ai>, Ritika Goel <ritika.goel@raga.ai>, Vijay Chaurasia <vijay.chaurasia@raga.ai>, Tushar Kumar <tushar.kumar@raga.ai>
 Requires-Python: <3.13,>=3.9
@@ -22,7 +22,7 @@ Requires-Dist: langchain>=0.2.11
 Requires-Dist: openai>=1.57.0
 Requires-Dist: pandas
 Requires-Dist: groq>=0.11.0
-Requires-Dist: PyPDF2>=3.0.1
+Requires-Dist: pypdf>=5.3.1
 Requires-Dist: google-generativeai>=0.8.2
 Requires-Dist: google-genai>=1.3.0
 Requires-Dist: Markdown>=3.7

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3}/ragaai_catalyst.egg-info/SOURCES.txt

@@ -167,5 +167,4 @@ test/test_catalyst/autonomous_research_agent/agents/base_agent.py
 test/test_catalyst/autonomous_research_agent/agents/coordinator.py
 test/test_catalyst/autonomous_research_agent/agents/discovery.py
 test/test_catalyst/autonomous_research_agent/agents/synthesis.py
-test/test_catalyst/autonomous_research_agent/utils/llm.py
-tests/test_examples_runner.py
+test/test_catalyst/autonomous_research_agent/utils/llm.py

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3}/ragaai_catalyst.egg-info/requires.txt

@@ -14,7 +14,7 @@ langchain>=0.2.11
 openai>=1.57.0
 pandas
 groq>=0.11.0
-PyPDF2>=3.0.1
+pypdf>=5.3.1
 google-generativeai>=0.8.2
 google-genai>=1.3.0
 Markdown>=3.7

{ragaai_catalyst-2.1.5.1b2 → ragaai_catalyst-2.1.5.1b3}/requirements.txt

@@ -68,7 +68,7 @@ pyasn1_modules==0.4.1
 pydantic==2.10.4
 pydantic_core==2.27.2
 pyparsing==3.2.0
-PyPDF2==3.0.1
+pypdf==5.3.1
 python-dateutil==2.9.0.post0
 python-dotenv==1.0.1
 pytz==2024.2

ragaai_catalyst-2.1.5.1b2/tests/test_examples_runner.py

@@ -1,158 +0,0 @@
-import os
-import sys
-import pytest
-import importlib.util
-from pathlib import Path
-import logging
-import traceback
-from unittest.mock import patch
-
-# Configure logging
-logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-logger = logging.getLogger(__name__)
-
-# Get the root directory of the project
-ROOT_DIR = Path(__file__).parent.parent
-EXAMPLES_DIR = ROOT_DIR / "examples"
-
-# Test configurations with different datasets and project names
-TEST_CONFIGS = [
-    {"dataset_name": "test_dataset_1", "project_name": "test_project_1"},
-    {"dataset_name": "test_dataset_2", "project_name": "test_project_2"},
-]
-
-class ExampleRunner:
-    """Class to run examples with different configurations."""
-    
-    def __init__(self):
-        self.examples = self._discover_examples()
-    
-    def _discover_examples(self):
-        """Find all example Python files in the examples directory."""
-        examples = []
-        for root, _, files in os.walk(EXAMPLES_DIR):
-            for file in files:
-                if file.endswith(".py") and not file.startswith("__"):
-                    file_path = Path(root) / file
-                    # Determine the framework based on the directory structure
-                    framework = self._get_framework(file_path)
-                    examples.append({
-                        "path": str(file_path),
-                        "framework": framework,
-                        "name": file_path.stem,
-                        "relative_path": str(file_path.relative_to(ROOT_DIR))
-                    })
-        return examples
-    
-    def _get_framework(self, file_path):
-        """Determine the framework based on the file path."""
-        path_str = str(file_path)
-        if "langgraph" in path_str:
-            return "langgraph"
-        # elif "autogen" in path_str:
-        #     return "autogen"
-        # elif "crewai" in path_str:
-        #     return "crewai"
-        # elif "langchain" in path_str:
-        #     return "langchain"
-        # elif "llamaindex_examples" in path_str:
-        #     return "llamaindex"
-        # elif "smolagents" in path_str:
-        #     return "smolagents"
-        # elif "haystack" in path_str:
-        #     return "haystack"
-        # elif "custom_agents" in path_str:
-        #     return "custom"
-        return "unknown"
-    
-    def get_env_vars(self, config):
-        """Create environment variables for testing."""
-        return {
-            "DATASET_NAME": config["dataset_name"],
-            "PROJECT_NAME": config["project_name"]
-        }
-    
-    def run_example(self, example, config):
-        """Run an example with the given configuration."""
-        logger.info(f"Running example: {example['name']} ({example['framework']})")
-        
-        # Add the example's directory to sys.path temporarily
-        example_dir = os.path.dirname(example['path'])
-        
-        # Save original environment
-        original_env = os.environ.copy()
-        
-        # Set environment variables
-        env_vars = self.get_env_vars(config)
-        for key, value in env_vars.items():
-            os.environ[key] = value
-        
-        try:
-            # Execute the Python file directly as a script using subprocess
-            try:
-                import subprocess
-                
-                # Get the current Python executable
-                python_executable = sys.executable
-                
-                # Create environment with the necessary variables
-                subprocess_env = os.environ.copy()
-                
-                # Run the example file as a subprocess
-                logger.info(f"Executing {example['path']} as a subprocess")
-                result = subprocess.run(
-                    [python_executable, example['path']],
-                    env=subprocess_env,
-                    capture_output=True,
-                    text=True,
-                    check=False,
-                    cwd=example_dir  # Set the working directory to the example directory
-                )
-                
-                # Log the output regardless of success or failure
-                if result.stdout.strip():
-                    logger.info(f"STDOUT from {example['name']}:\n{result.stdout}")
-                if result.stderr.strip():
-                    logger.warning(f"STDERR from {example['name']}:\n{result.stderr}")
-                
-                # Check if the execution was successful
-                if result.returncode == 0:
-                    logger.info(f"Successfully ran example: {example['name']}")
-                    return True
-                else:
-                    logger.error(f"Error running example {example['path']}: Exit code {result.returncode}")
-                    return False
-            except Exception as e:
-                logger.error(f"Error running example {example['path']}: {str(e)}")
-                logger.error(traceback.format_exc())
-                return False
-        finally:
-            # Restore original environment
-            os.environ.clear()
-            os.environ.update(original_env)
-
-# Generate test ids for better reporting
-def idfn(val):
-    if isinstance(val, dict):
-        if 'name' in val:
-            return f"{val['name']}_{val['framework']}"
-        elif 'dataset_name' in val:
-            return f"{val['dataset_name']}_{val['project_name']}"
-    return str(val)
-
-# Create the runner
-runner = ExampleRunner()
-
-# Parametrize the test with examples and configurations
-@pytest.mark.parametrize("example", runner.examples, ids=idfn)
-@pytest.mark.parametrize("config", TEST_CONFIGS, ids=idfn)
-def test_example_with_config(example, config):
-    """Test each example with different configurations."""
-    logger.info(f"Testing {example['name']} with dataset={config['dataset_name']}, project={config['project_name']}")
-    
-    # Run the example and assert it completes without errors
-    result = runner.run_example(example, config)
-    assert result, f"Example {example['path']} failed with dataset={config['dataset_name']}, project={config['project_name']}"
-
-if __name__ == "__main__":
-    pytest.main(["-xvs", __file__])