local-deep-research 0.4.4__py3-none-any.whl → 0.5.0__py3-none-any.whl

local_deep_research/advanced_search_system/strategies/standard_strategy.py

@@ -19,7 +19,11 @@ class StandardSearchStrategy(BaseSearchStrategy):
     """Standard iterative search strategy that generates follow-up questions."""
 
     def __init__(
-        self, search=None, model=None, citation_handler=None, all_links_of_system=None
+        self,
+        search=None,
+        model=None,
+        citation_handler=None,
+        all_links_of_system=None,
     ):
         """Initialize with optional dependency injection for testing."""
         super().__init__(all_links_of_system=all_links_of_system)
@@ -73,9 +77,7 @@ class StandardSearchStrategy(BaseSearchStrategy):
 
         # Check if search engine is available
         if self.search is None:
-            error_msg = (
-                "Error: No search engine available. Please check your configuration."
-            )
+            error_msg = "Error: No search engine available. Please check your configuration."
             self._update_progress(
                 error_msg,
                 100,
@@ -127,7 +129,9 @@ Iteration: {iteration + 1} of {total_iterations}"""
             )
             for q_idx, question in enumerate(questions):
                 question_progress_base = iteration_progress_base + (
-                    ((q_idx + 1) / question_count) * (100 / total_iterations) * 0.5
+                    ((q_idx + 1) / question_count)
+                    * (100 / total_iterations)
+                    * 0.5
                 )
 
                 self._update_progress(
@@ -156,7 +160,9 @@ Iteration: {iteration + 1} of {total_iterations}"""
                 except Exception as e:
                     error_msg = f"Error during search: {str(e)}"
                     logger.exception(f"SEARCH ERROR: {error_msg}")
-                    self._handle_search_error(error_msg, question_progress_base + 10)
+                    self._handle_search_error(
+                        error_msg, question_progress_base + 10
+                    )
                     search_results = []
 
                 if search_results is None:
@@ -171,7 +177,10 @@ Iteration: {iteration + 1} of {total_iterations}"""
                 self._update_progress(
                     f"Found {len(search_results)} results for question: {question}",
                     int(question_progress_base + 2),
-                    {"phase": "search_complete", "result_count": len(search_results)},
+                    {
+                        "phase": "search_complete",
+                        "result_count": len(search_results),
+                    },
                 )
 
                 logger.info(f"len search: {len(search_results)}")
@@ -240,7 +249,9 @@ Iteration: {iteration + 1} of {total_iterations}"""
                 except Exception as e:
                     error_msg = f"Error analyzing results: {str(e)}"
                     logger.exception(f"ANALYSIS ERROR: {error_msg}")
-                    self._handle_search_error(error_msg, question_progress_base + 10)
+                    self._handle_search_error(
+                        error_msg, question_progress_base + 10
+                    )
 
             iteration += 1
 
@@ -250,11 +261,16 @@ Iteration: {iteration + 1} of {total_iterations}"""
                 {"phase": "knowledge_compression"},
             )
 
-            if knowledge_accumulation == KnowledgeAccumulationApproach.ITERATION.value:
+            if (
+                knowledge_accumulation
+                == KnowledgeAccumulationApproach.ITERATION.value
+            ):
                 try:
                     logger.info("ITERATION - Compressing Knowledge")
-                    current_knowledge = self.knowledge_generator.compress_knowledge(
-                        current_knowledge, query, section_links
+                    current_knowledge = (
+                        self.knowledge_generator.compress_knowledge(
+                            current_knowledge, query, section_links
+                        )
                     )
                     logger.info("FINISHED ITERATION - Compressing Knowledge")
                 except Exception as e:
@@ -271,7 +287,9 @@ Iteration: {iteration + 1} of {total_iterations}"""
             )
 
             # Extract content from findings for synthesis
-            finding_contents = [f["content"] for f in findings if "content" in f]
+            finding_contents = [
+                f["content"] for f in findings if "content" in f
+            ]
 
             # First synthesize findings to get coherent content
             synthesized_content = self.findings_repository.synthesize_findings(
@@ -288,8 +306,10 @@ Iteration: {iteration + 1} of {total_iterations}"""
             )
 
             # Now format the findings with search questions and sources
-            formatted_findings = self.findings_repository.format_findings_to_text(
-                findings, synthesized_content
+            formatted_findings = (
+                self.findings_repository.format_findings_to_text(
+                    findings, synthesized_content
+                )
             )
 
             # Add the synthesized content to the repository

local_deep_research/advanced_search_system/tools/base_tool.py

@@ -75,7 +75,10 @@ class BaseTool(ABC):
                 logger.error(f"Invalid type for parameter {param_name}")
                 return False
 
-            if "enum" in param_schema and param_value not in param_schema["enum"]:
+            if (
+                "enum" in param_schema
+                and param_value not in param_schema["enum"]
+            ):
                 logger.error(f"Invalid value for parameter {param_name}")
                 return False
 
@@ -97,4 +100,6 @@ class BaseTool(ABC):
         Args:
             result: The result of the tool execution
         """
-        logger.info(f"Tool {self.name} execution completed with result: {result}")
+        logger.info(
+            f"Tool {self.name} execution completed with result: {result}"
+        )

local_deep_research/api/benchmark_functions.py

@@ -235,7 +235,9 @@ def compare_configurations(
     import time
 
     timestamp = time.strftime("%Y%m%d_%H%M%S")
-    report_file = os.path.join(output_dir, f"comparison_{dataset_type}_{timestamp}.md")
+    report_file = os.path.join(
+        output_dir, f"comparison_{dataset_type}_{timestamp}.md"
+    )
 
     with open(report_file, "w") as f:
         f.write(f"# Configuration Comparison - {dataset_type.capitalize()}\n\n")
@@ -247,7 +249,9 @@ def compare_configurations(
 
         for result in results:
             accuracy = result.get("metrics", {}).get("accuracy", 0)
-            avg_time = result.get("metrics", {}).get("average_processing_time", 0)
+            avg_time = result.get("metrics", {}).get(
+                "average_processing_time", 0
+            )
             examples = result.get("total_examples", 0)
 
             f.write(

local_deep_research/api/research_functions.py

@@ -21,9 +21,9 @@ def _init_search_system(
     openai_endpoint_url: str | None = None,
     progress_callback: Callable[[str, int, dict], None] | None = None,
     search_tool: Optional[str] = None,
+    search_strategy: str = "source_based",
     iterations: int = 1,
     questions_per_iteration: int = 1,
-    search_strategy: str = "source_based",
 ) -> AdvancedSearchSystem:
     """
     Initializes the advanced search system with specified parameters. This function sets up
@@ -39,6 +39,7 @@ def _init_search_system(
             setting)
         progress_callback: Optional callback function to receive progress updates
         search_tool: Search engine to use (auto, wikipedia, arxiv, etc.). If None, uses default
+        search_strategy: Search strategy to use (modular, source_based, etc.). If None, uses default
         iterations: Number of research cycles to perform
         questions_per_iteration: Number of questions to generate per cycle
         search_strategy: The name of the search strategy to use.
@@ -220,7 +221,9 @@ def analyze_documents(
     # Force reindex if requested
     if force_reindex and hasattr(search, "embedding_manager"):
         for folder_path in search.folder_paths:
-            search.embedding_manager.index_folder(folder_path, force_reindex=True)
+            search.embedding_manager.index_folder(
+                folder_path, force_reindex=True
+            )
 
     # Perform the search
     results = search.run(query)
@@ -235,7 +238,8 @@ def analyze_documents(
 
     docs_text = "\n\n".join(
         [
-            f"Document {i + 1}:" f" {doc.get('content', doc.get('snippet', ''))[:1000]}"
+            f"Document {i + 1}:"
+            f" {doc.get('content', doc.get('snippet', ''))[:1000]}"
             for i, doc in enumerate(results[:5])
         ]
     )  # Limit to first 5 docs and 1000 chars each
@@ -269,7 +273,9 @@ def analyze_documents(
             f.write(f"## Documents Found: {len(results)}\n\n")
 
             for i, doc in enumerate(results):
-                f.write(f"### Document {i + 1}:" f" {doc.get('title', 'Untitled')}\n\n")
+                f.write(
+                    f"### Document {i + 1}: {doc.get('title', 'Untitled')}\n\n"
+                )
                 f.write(f"**Source:** {doc.get('link', 'Unknown')}\n\n")
                 f.write(
                     f"**Content:**\n\n{doc.get('content', doc.get('snippet', 'No content available'))[:1000]}...\n\n"

local_deep_research/benchmarks/__init__.py

@@ -10,21 +10,25 @@ __version__ = "0.2.0"
 # Core benchmark functionality
 from .datasets import get_available_datasets, load_dataset
 from .metrics import (
+    calculate_combined_score,
     calculate_metrics,
     calculate_quality_metrics,
-    calculate_speed_metrics,
     calculate_resource_metrics,
-    calculate_combined_score,
+    calculate_speed_metrics,
     generate_report,
 )
-from .runners import run_benchmark, run_browsecomp_benchmark, run_simpleqa_benchmark
 
 # Optimization functionality
 from .optimization import (
-    optimize_parameters,
+    optimize_for_efficiency,
     optimize_for_quality,
     optimize_for_speed,
-    optimize_for_efficiency,
+    optimize_parameters,
+)
+from .runners import (
+    run_benchmark,
+    run_browsecomp_benchmark,
+    run_simpleqa_benchmark,
 )
 
 __all__ = [
@@ -36,13 +40,11 @@ __all__ = [
     "get_available_datasets",
     "calculate_metrics",
     "generate_report",
-
     # Metrics for optimization
     "calculate_quality_metrics",
     "calculate_speed_metrics",
     "calculate_resource_metrics",
     "calculate_combined_score",
-
     # Optimization functionality
     "optimize_parameters",
     "optimize_for_quality",

local_deep_research/benchmarks/benchmark_functions.py

@@ -300,7 +300,9 @@ def compare_configurations(
     import time
 
     timestamp = time.strftime("%Y%m%d_%H%M%S")
-    report_file = os.path.join(output_dir, f"comparison_{dataset_type}_{timestamp}.md")
+    report_file = os.path.join(
+        output_dir, f"comparison_{dataset_type}_{timestamp}.md"
+    )
 
     with open(report_file, "w") as f:
         f.write(f"# Configuration Comparison - {dataset_type.capitalize()}\n\n")
@@ -312,7 +314,9 @@ def compare_configurations(
 
         for result in results:
             accuracy = result.get("metrics", {}).get("accuracy", 0)
-            avg_time = result.get("metrics", {}).get("average_processing_time", 0)
+            avg_time = result.get("metrics", {}).get(
+                "average_processing_time", 0
+            )
             examples = result.get("total_examples", 0)
 
             f.write(

local_deep_research/benchmarks/cli/benchmark_commands.py

@@ -38,7 +38,10 @@ def setup_benchmark_parser(subparsers):
         help="Number of search iterations (default: 3)",
     )
     benchmark_parent.add_argument(
-        "--questions", type=int, default=3, help="Questions per iteration (default: 3)"
+        "--questions",
+        type=int,
+        default=3,
+        help="Questions per iteration (default: 3)",
     )
     benchmark_parent.add_argument(
         "--search-tool",
@@ -75,15 +78,21 @@ def setup_benchmark_parser(subparsers):
         "--search-model", type=str, help="Model to use for the search system"
     )
     benchmark_parent.add_argument(
-        "--search-provider", type=str, help="Provider to use for the search system"
+        "--search-provider",
+        type=str,
+        help="Provider to use for the search system",
     )
     benchmark_parent.add_argument(
-        "--endpoint-url", type=str, help="Endpoint URL for OpenRouter or other API services"
+        "--endpoint-url",
+        type=str,
+        help="Endpoint URL for OpenRouter or other API services",
     )
     benchmark_parent.add_argument(
-        "--search-strategy", type=str, default="source_based",
+        "--search-strategy",
+        type=str,
+        default="source_based",
         choices=["source_based", "standard", "rapid", "parallel", "iterdrag"],
-        help="Search strategy to use (default: source_based)"
+        help="Search strategy to use (default: source_based)",
     )
 
     # SimpleQA benchmark command
@@ -94,12 +103,16 @@ def setup_benchmark_parser(subparsers):
 
     # BrowseComp benchmark command
     browsecomp_parser = subparsers.add_parser(
-        "browsecomp", parents=[benchmark_parent], help="Run BrowseComp benchmark"
+        "browsecomp",
+        parents=[benchmark_parent],
+        help="Run BrowseComp benchmark",
     )
     browsecomp_parser.set_defaults(func=run_browsecomp_cli)
 
     # List available benchmarks command
-    list_parser = subparsers.add_parser("list", help="List available benchmarks")
+    list_parser = subparsers.add_parser(
+        "list", help="List available benchmarks"
+    )
     list_parser.set_defaults(func=list_benchmarks_cli)
 
     # Compare configurations command
@@ -304,11 +317,14 @@ def main():
     Main entry point for benchmark CLI.
     """
     parser = argparse.ArgumentParser(
-        description="Local Deep Research Benchmarking Tool", prog="ldr-benchmark"
+        description="Local Deep Research Benchmarking Tool",
+        prog="ldr-benchmark",
     )
 
     # Set up logging
-    parser.add_argument("--verbose", action="store_true", help="Enable verbose logging")
+    parser.add_argument(
+        "--verbose", action="store_true", help="Enable verbose logging"
+    )
 
     # Create subparsers
     subparsers = parser.add_subparsers(
@@ -324,7 +340,8 @@ def main():
     # Set up logging
     log_level = logging.DEBUG if args.verbose else logging.INFO
     logging.basicConfig(
-        level=log_level, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+        level=log_level,
+        format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
     )
 
     # Run command

local_deep_research/benchmarks/cli.py

@@ -10,7 +10,6 @@ import logging
 import os
 import sys
 from datetime import datetime
-from typing import Any, Dict, List, Optional
 
 from .comparison import compare_configurations
 from .efficiency import ResourceMonitor, SpeedProfiler
@@ -18,7 +17,8 @@ from .optimization import optimize_parameters
 
 # Configure logging
 logging.basicConfig(
-    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
+    level=logging.INFO,
+    format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
 )
 logger = logging.getLogger(__name__)
 
@@ -44,7 +44,9 @@ Examples:
     subparsers = parser.add_subparsers(dest="command", help="Command to run")
 
     # Optimizer parser
-    optimize_parser = subparsers.add_parser("optimize", help="Optimize parameters")
+    optimize_parser = subparsers.add_parser(
+        "optimize", help="Optimize parameters"
+    )
     optimize_parser.add_argument("query", help="Research query to optimize for")
     optimize_parser.add_argument(
         "--output-dir",
@@ -67,21 +69,32 @@ Examples:
         "--timeout", type=int, help="Maximum seconds to run optimization"
     )
     optimize_parser.add_argument(
-        "--n-jobs", type=int, default=1, help="Number of parallel jobs for optimization"
+        "--n-jobs",
+        type=int,
+        default=1,
+        help="Number of parallel jobs for optimization",
+    )
+    optimize_parser.add_argument(
+        "--study-name", help="Name of the Optuna study"
     )
-    optimize_parser.add_argument("--study-name", help="Name of the Optuna study")
     optimize_parser.add_argument(
         "--speed-focus", action="store_true", help="Focus optimization on speed"
     )
     optimize_parser.add_argument(
-        "--quality-focus", action="store_true", help="Focus optimization on quality"
+        "--quality-focus",
+        action="store_true",
+        help="Focus optimization on quality",
     )
 
     # Comparison parser
-    compare_parser = subparsers.add_parser("compare", help="Compare configurations")
+    compare_parser = subparsers.add_parser(
+        "compare", help="Compare configurations"
+    )
     compare_parser.add_argument("query", help="Research query to compare with")
     compare_parser.add_argument(
-        "--configs", required=True, help="JSON file with configurations to compare"
+        "--configs",
+        required=True,
+        help="JSON file with configurations to compare",
     )
     compare_parser.add_argument(
         "--output-dir",
@@ -99,7 +112,9 @@ Examples:
     )
 
     # Profiling parser
-    profile_parser = subparsers.add_parser("profile", help="Profile resource usage")
+    profile_parser = subparsers.add_parser(
+        "profile", help="Profile resource usage"
+    )
     profile_parser.add_argument("query", help="Research query to profile")
     profile_parser.add_argument(
         "--output-dir",
@@ -203,7 +218,9 @@ def run_comparison(args):
     for i, result in enumerate(
         [r for r in results["results"] if r.get("success", False)]
     ):
-        print(f"{i+1}. {result['name']}: {result.get('overall_score', 0):.4f}")
+        print(
+            f"{i + 1}. {result['name']}: {result.get('overall_score', 0):.4f}"
+        )
 
     print(f"\nResults saved to: {results.get('report_path', args.output_dir)}")
 
@@ -275,12 +292,18 @@ def run_profiling(args):
             if name != "total_duration" and name.endswith("_duration"):
                 component = name.replace("_duration", "")
                 duration = value
-                percent = (duration / total_duration * 100) if total_duration > 0 else 0
+                percent = (
+                    (duration / total_duration * 100)
+                    if total_duration > 0
+                    else 0
+                )
                 print(f"- {component}: {duration:.2f}s ({percent:.1f}%)")
 
         # Resource summary
         print("\nResource Usage Summary:")
-        print(f"Peak memory: {resource_results.get('process_memory_max_mb', 0):.1f} MB")
+        print(
+            f"Peak memory: {resource_results.get('process_memory_max_mb', 0):.1f} MB"
+        )
         print(
             f"Average memory: {resource_results.get('process_memory_avg_mb', 0):.1f} MB"
         )
@@ -308,7 +331,9 @@ def run_profiling(args):
                     "timing_results": timing_results,
                     "resource_results": resource_results,
                     "findings_count": len(results.get("findings", [])),
-                    "knowledge_length": len(results.get("current_knowledge", "")),
+                    "knowledge_length": len(
+                        results.get("current_knowledge", "")
+                    ),
                     "timestamp": timestamp,
                 },
                 f,

local_deep_research/benchmarks/comparison/__init__.py

@@ -5,8 +5,10 @@ This module provides tools for comparing the performance of different
 parameters, models, and search engines.
 """
 
-from local_deep_research.benchmarks.comparison.evaluator import compare_configurations
+from local_deep_research.benchmarks.comparison.evaluator import (
+    compare_configurations,
+)
 
 __all__ = [
-    'compare_configurations',
+    "compare_configurations",
 ]