local-deep-research 0.1.15__py3-none-any.whl → 0.1.17__py3-none-any.whl

local_deep_research/citation_handler.py

@@ -50,7 +50,6 @@ class CitationHandler:
 
         documents = self._create_documents(search_results)
         formatted_sources = self._format_sources(documents)
-        print(formatted_sources)
         prompt = f"""Analyze the following information concerning the question and include citations using numbers in square brackets [1], [2], etc. When citing, use the source number provided at the start of each source.
 
 Question: {query}
@@ -75,7 +74,6 @@ Provide a detailed analysis with citations and always keep URLS. Never make up s
         """Process follow-up analysis with citations."""
         documents = self._create_documents(search_results, nr_of_links=nr_of_links)
         formatted_sources = self._format_sources(documents)
-        print(formatted_sources)
         # Add fact-checking step
         fact_check_prompt = f"""Analyze these sources for factual consistency:
         1. Cross-reference major claims between sources

local_deep_research/config.py

@@ -20,7 +20,7 @@ def get_config_dir():
         from platformdirs import user_config_dir
         config_dir = Path(user_config_dir("local_deep_research", "LearningCircuit"))
     
-    print(f"Looking for config in: {config_dir}")
+    logger.info(f"Looking for config in: {config_dir}")
     return config_dir
 # Define config paths
 CONFIG_DIR = get_config_dir() / "config"
@@ -31,9 +31,6 @@ LLM_CONFIG_FILE = CONFIG_DIR / "llm_config.py"
 SEARCH_ENGINES_FILE = CONFIG_DIR / "search_engines.toml"
 
 LOCAL_COLLECTIONS_FILE = CONFIG_DIR / "local_collections.toml"
-print("CONFIGDIR:", CONFIG_DIR)
-print("SECRETS_FILE:", SECRETS_FILE)
-print("SETTINGS_FILE:", SETTINGS_FILE)
 
 
 # Set environment variable for Dynaconf to use

local_deep_research/defaults/llm_config.py

@@ -34,7 +34,7 @@ class ModelProvider(Enum):
 DEFAULT_PROVIDER = ModelProvider.OLLAMA  # Change this to your preferred provider
 
 # Set your default model name here
-DEFAULT_MODEL = "mistral"  # Your default model
+DEFAULT_MODEL = "gemma3:12b"  # Your default model
 
 # Set default model parameters
 DEFAULT_TEMPERATURE = 0.7
@@ -210,7 +210,7 @@ def is_anthropic_available():
 
 def is_openai_endpoint_available():
     """Check if OpenAI endpoint is available"""
-    print(os.getenv("OPENAI_ENDPOINT_API_KEY"))
+    
     try:
         api_key = settings.OPENAI_ENDPOINT_API_KEY
         return bool(api_key) 

local_deep_research/defaults/main.toml

@@ -26,13 +26,13 @@ debug = true
 tool = "auto"
 
 # Number of research cycles
-iterations = 3
+iterations = 2
 
 # Questions generated per cycle
-questions_per_iteration = 3
+questions_per_iteration = 2
 
 # Searches per report section
-searches_per_section = 3
+searches_per_section = 2
 
 # Results per search query
 max_results = 50

local_deep_research/defaults/search_engines.toml

@@ -37,7 +37,7 @@ module_path = "local_deep_research.web_search_engines.engines.search_engine_pubm
 class_name = "PubMedSearchEngine"
 requires_api_key = false
 api_key_env = "NCBI_API_KEY"
-reliability = 0.95
+reliability = 0.98
 strengths = [
     "biomedical literature", "medical research", "clinical studies", 
     "life sciences", "health information", "scientific papers"
@@ -191,7 +191,7 @@ module_path = "local_deep_research.web_search_engines.engines.search_engine_sema
 class_name = "SemanticScholarSearchEngine"
 requires_api_key = false
 api_key_env = "S2_API_KEY"
-reliability = 0.95
+reliability = 0.87
 strengths = [
     "comprehensive scientific literature", 
     "extensive citation network", 

local_deep_research/report_generator.py

@@ -15,10 +15,6 @@ class IntegratedReportGenerator:
             searches_per_section  # Control search depth per section
         )
 
-    def _remove_think_tags(self, text: str) -> str:
-        print(text)
-        return re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL).strip()
-
     def generate_report(self, initial_findings: Dict, query: str) -> Dict:
         """Generate a complete research report with section-specific research."""
 
@@ -63,7 +59,7 @@ class IntegratedReportGenerator:
         Each subsection must include its purpose after the | symbol.
         """
 
-        response = self._remove_think_tags(self.model.invoke(prompt).content)
+        response = search_utilities.remove_think_tags(self.model.invoke(prompt).content)
 
         # Parse the structure
         structure = []

local_deep_research/search_system.py

@@ -1,6 +1,6 @@
 from typing import Dict, List, Optional, Callable
 from datetime import datetime
-from .utilties.search_utilities import remove_think_tags, format_findings_to_text, print_search_results, format_links
+from .utilties.search_utilities import remove_think_tags, format_findings_to_text, format_links
 import os
 from .utilties.enums import KnowledgeAccumulationApproach
 from .config import settings, get_llm, get_search 
@@ -28,7 +28,7 @@ class AdvancedSearchSystem:
         
         # Check if search is available, log warning if not
         if self.search is None:
-            print("WARNING: Search system initialized with no search engine! Research will not be effective.")
+            logger.info("WARNING: Search system initialized with no search engine! Research will not be effective.")
             self._update_progress("WARNING: No search engine available", None, {"error": "No search engine configured properly"})
 
         
@@ -101,7 +101,7 @@ class AdvancedSearchSystem:
         self._update_progress("Knowledge compression complete", None)
         response = remove_think_tags(response.content)
         response = str(response) #+ "\n\n" + str(formatted_links)
-        print(response)
+
         return response
 
     def analyze_topic(self, query: str) -> Dict:
@@ -165,7 +165,7 @@ class AdvancedSearchSystem:
                         search_results = self.search.run(question)
                 except Exception as e:
                     error_msg = f"Error during search: {str(e)}"
-                    print(f"SEARCH ERROR: {error_msg}")
+                    logger.info(f"SEARCH ERROR: {error_msg}")
                     self._update_progress(error_msg, 
                                         int(question_progress_base + 2),
                                         {"phase": "search_error", "error": str(e)})
@@ -190,7 +190,7 @@ class AdvancedSearchSystem:
                 self._update_progress(f"Analyzing results for: {question}", 
                                      int(question_progress_base + 5),
                                      {"phase": "analysis"})
-                print("NR OF SOURCES: ", len(self.all_links_of_system))
+
 
                 try:
                     result = self.citation_handler.analyze_followup(
@@ -203,7 +203,7 @@ class AdvancedSearchSystem:
                     if links:
                         formatted_links=format_links(links=links)
                     
-                    logger.debug(f"Generated questions: {formatted_links}")                           
+                    logger.info(f"Generated questions: {formatted_links}")                           
                     if result is not None:
                         results_with_links = str(result["content"])
                         findings.append(
@@ -219,7 +219,6 @@ class AdvancedSearchSystem:
                         if settings.general.knowledge_accumulation != str(KnowledgeAccumulationApproach.NO_KNOWLEDGE.value):
                             current_knowledge = current_knowledge + "\n\n\n New: \n" + results_with_links
                         
-                        logger.info(settings.general.knowledge_accumulation)
                         if settings.general.knowledge_accumulation == str(KnowledgeAccumulationApproach.QUESTION.value):
                             logger.info("Compressing knowledge")
                             self._update_progress(f"Compress Knowledge for: {question}", 
@@ -232,7 +231,7 @@ class AdvancedSearchSystem:
                                             {"phase": "analysis_complete"})
                 except Exception as e:
                     error_msg = f"Error analyzing results: {str(e)}"
-                    print(f"ANALYSIS ERROR: {error_msg}")
+                    logger.info(f"ANALYSIS ERROR: {error_msg}")
                     self._update_progress(error_msg, 
                                         int(question_progress_base + 10),
                                         {"phase": "analysis_error", "error": str(e)})
@@ -251,7 +250,7 @@ class AdvancedSearchSystem:
                     logger.info("FINISHED ITERATION - Compressing Knowledge")
                 except Exception as e:
                     error_msg = f"Error compressing knowledge: {str(e)}"
-                    print(f"COMPRESSION ERROR: {error_msg}")
+                    logger.info(f"COMPRESSION ERROR: {error_msg}")
                     self._update_progress(error_msg, 
                                         int((iteration / total_iterations) * 100 - 3),
                                         {"phase": "compression_error", "error": str(e)})
@@ -266,7 +265,7 @@ class AdvancedSearchSystem:
                 formatted_findings = self._save_findings(findings, current_knowledge, query)
             except Exception as e:
                 error_msg = f"Error saving findings: {str(e)}"
-                print(f"SAVE ERROR: {error_msg}")
+                logger.info(f"SAVE ERROR: {error_msg}")
                 self._update_progress(error_msg, 
                                     int((iteration / total_iterations) * 100),
                                     {"phase": "save_error", "error": str(e)})

local_deep_research/utilties/search_utilities.py

@@ -3,7 +3,6 @@ import re
 
 def remove_think_tags(text: str) -> str:
     text = re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL).strip()
-    print(text)
     return text
 
 
@@ -17,13 +16,13 @@ def extract_links_from_search_results(search_results: list) -> list:
     """
     links = []
     for result in search_results:
-        #print(result)
+
         try:
             
             title = result.get("title", "").strip()
             url = result.get("link", "").strip()
             index = result.get("index", "").strip()
-            print("INDEX:",index)
+            
             if title and url:
                 links.append({"title": title, "url": url, "index": index})
         except Exception:
@@ -111,5 +110,5 @@ def print_search_results(search_results):
     links = extract_links_from_search_results(search_results)
     if links:
         formatted_text=format_links(links=links)
-    print(formatted_text)
+    logger.info(formatted_text)
 

local_deep_research/web_search_engines/engines/full_search.py

@@ -7,6 +7,9 @@ import json, os
 from .utilties.search_utilities import remove_think_tags
 from datetime import datetime
 from local_deep_research import config
+import logging
+logger = logging.getLogger(__name__)
+
 
 class FullSearchResults:
     def __init__(
@@ -57,13 +60,12 @@ class FullSearchResults:
         try:
             # Get LLM's evaluation
             response = self.llm.invoke(prompt)
-            # print(response)
             good_indices = json.loads(remove_think_tags(response.content))
 
             # Return only the results with good URLs
             return [r for i, r in enumerate(results) if i in good_indices]
         except Exception as e:
-            print(f"URL filtering error: {e}")
+            logger.error(f"URL filtering error: {e}")
             return []  
 
     def remove_boilerplate(self, html: str) -> str:
@@ -75,9 +77,8 @@ class FullSearchResults:
 
     def run(self, query: str):
         nr_full_text = 0
-        # Step 1: Get search results from DuckDuckGo
+        # Step 1: Get search results 
         search_results = self.web_search.invoke(query)
-        #print(type(search_results))
         if not isinstance(search_results, list):
             raise ValueError("Expected the search results in list format.")
 
@@ -89,9 +90,9 @@ class FullSearchResults:
 
         # Extract URLs from filtered results
         urls = [result.get("link") for result in filtered_results if result.get("link")]
-        print(urls)
+
         if not urls:
-            print("\n === NO VALID LINKS ===\n")
+            logger.error("\n === NO VALID LINKS ===\n")
             return []
 
         # Step 3: Download the full HTML pages for filtered URLs
@@ -117,8 +118,8 @@ class FullSearchResults:
             link = result.get("link")
             result["full_content"] = url_to_content.get(link, None)
 
-        print("FULL SEARCH WITH FILTERED URLS")
-        print("Full text retrieved: ", nr_full_text)
+        logger.info("FULL SEARCH WITH FILTERED URLS")
+        logger.info("Full text retrieved: ", nr_full_text)
         return filtered_results
 
     def invoke(self, query: str):

local_deep_research/web_search_engines/engines/search_engine_arxiv.py

@@ -121,7 +121,7 @@ class ArXivSearchEngine(BaseSearchEngine):
             return previews
             
         except Exception as e:
-            print(f"Error getting arXiv previews: {e}")
+            logger.error(f"Error getting arXiv previews: {e}")
             return []
     
     def _get_full_content(self, relevant_items: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
@@ -138,10 +138,10 @@ class ArXivSearchEngine(BaseSearchEngine):
         """
         # Check if we should get full content
         if hasattr(config, 'SEARCH_SNIPPETS_ONLY') and config.SEARCH_SNIPPETS_ONLY:
-            print("Snippet-only mode, skipping full content retrieval")
+            logger.info("Snippet-only mode, skipping full content retrieval")
             return relevant_items
             
-        print("Getting full content for relevant arXiv papers")
+        logger.info("Getting full content for relevant arXiv papers")
         
         results = []
         pdf_count = 0  # Track number of PDFs processed
@@ -198,7 +198,7 @@ class ArXivSearchEngine(BaseSearchEngine):
                                     if pdf_text.strip():  # Only use if we got meaningful text
                                         result["content"] = pdf_text
                                         result["full_content"] = pdf_text
-                                        print(f"Successfully extracted text from PDF using PyPDF2")
+                                        logger.info(f"Successfully extracted text from PDF using PyPDF2")
                             except (ImportError, Exception) as e1:
                                 # Fall back to pdfplumber
                                 try:
@@ -211,20 +211,20 @@ class ArXivSearchEngine(BaseSearchEngine):
                                         if pdf_text.strip():  # Only use if we got meaningful text
                                             result["content"] = pdf_text
                                             result["full_content"] = pdf_text
-                                            print(f"Successfully extracted text from PDF using pdfplumber")
+                                            logger.info(f"Successfully extracted text from PDF using pdfplumber")
                                 except (ImportError, Exception) as e2:
-                                    print(f"PDF text extraction failed: {str(e1)}, then {str(e2)}")
-                                    print(f"Using paper summary as content instead")
+                                    logger.error(f"PDF text extraction failed: {str(e1)}, then {str(e2)}")
+                                    logger.error(f"Using paper summary as content instead")
                         except Exception as e:
-                            print(f"Error extracting text from PDF: {e}")
-                            print(f"Using paper summary as content instead")
+                            logger.error(f"Error extracting text from PDF: {e}")
+                            logger.error(f"Using paper summary as content instead")
                     except Exception as e:
-                        print(f"Error downloading paper {paper.title}: {e}")
+                        logger.error(f"Error downloading paper {paper.title}: {e}")
                         result["pdf_path"] = None
                         pdf_count -= 1  # Decrement counter if download fails
                 elif self.include_full_text and self.download_dir and pdf_count >= self.max_full_text:
                     # Reached PDF limit
-                    print(f"Maximum number of PDFs ({self.max_full_text}) reached. Skipping remaining PDFs.")
+                    logger.info(f"Maximum number of PDFs ({self.max_full_text}) reached. Skipping remaining PDFs.")
                     result["content"] = paper.summary
                     result["full_content"] = paper.summary
             
@@ -242,7 +242,7 @@ class ArXivSearchEngine(BaseSearchEngine):
         Returns:
             List of search results
         """
-        print("---Execute a search using arXiv---")
+        logger.info("---Execute a search using arXiv---")
         
         # Use the implementation from the parent class which handles all phases
         results = super().run(query)
@@ -308,12 +308,12 @@ class ArXivSearchEngine(BaseSearchEngine):
                         paper_path = paper.download_pdf(dirpath=self.download_dir)
                         result["pdf_path"] = str(paper_path)
                     except Exception as e:
-                        print(f"Error downloading paper: {e}")
+                        logger.error(f"Error downloading paper: {e}")
             
             return result
             
         except Exception as e:
-            print(f"Error getting paper details: {e}")
+            logger.error(f"Error getting paper details: {e}")
             return {}
     
     def search_by_author(self, author_name: str, max_results: Optional[int] = None) -> List[Dict[str, Any]]:

local_deep_research/web_search_engines/engines/search_engine_brave.py

@@ -5,7 +5,8 @@ from langchain_core.language_models import BaseLLM
 
 from local_deep_research.web_search_engines.search_engine_base import BaseSearchEngine
 from local_deep_research import config
-
+import logging
+logger = logging.getLogger(__name__)
 
 class BraveSearchEngine(BaseSearchEngine):
     """Brave search engine implementation with two-phase approach"""
@@ -100,7 +101,7 @@ class BraveSearchEngine(BaseSearchEngine):
                     safesearch=brave_safe_search
                 )
             except ImportError:
-                print("Warning: FullSearchResults not available. Full content retrieval disabled.")
+                logger.warning("Warning: FullSearchResults not available. Full content retrieval disabled.")
                 self.include_full_content = False
     
     def _get_previews(self, query: str) -> List[Dict[str, Any]]:
@@ -113,7 +114,7 @@ class BraveSearchEngine(BaseSearchEngine):
         Returns:
             List of preview dictionaries
         """
-        print("Getting search results from Brave Search")
+        logger.info("Getting search results from Brave Search")
         
         try:
             # Get search results from Brave Search
@@ -125,7 +126,7 @@ class BraveSearchEngine(BaseSearchEngine):
                     import json
                     raw_results = json.loads(raw_results)
                 except json.JSONDecodeError:
-                    print("Error: Unable to parse BraveSearch response as JSON.")
+                    logger.error("Error: Unable to parse BraveSearch response as JSON.")
                     return []
             
             # Format results as previews
@@ -151,7 +152,7 @@ class BraveSearchEngine(BaseSearchEngine):
             return previews
             
         except Exception as e:
-            print(f"Error getting Brave Search results: {e}")
+            logger.error(f"Error getting Brave Search results: {e}")
             return []
     
     def _get_full_content(self, relevant_items: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
@@ -168,7 +169,7 @@ class BraveSearchEngine(BaseSearchEngine):
         """
         # Check if we should get full content
         if hasattr(config, 'SEARCH_SNIPPETS_ONLY') and config.SEARCH_SNIPPETS_ONLY:
-            print("Snippet-only mode, skipping full content retrieval")
+            logger.info("Snippet-only mode, skipping full content retrieval")
             
             # Return the relevant items with their full Brave information
             results = []
@@ -188,7 +189,7 @@ class BraveSearchEngine(BaseSearchEngine):
             
         # If full content retrieval is enabled
         if self.include_full_content and hasattr(self, 'full_search'):
-            print("Retrieving full webpage content")
+            logger.info("Retrieving full webpage content")
             
             try:
                 # Extract only the links from relevant items
@@ -200,7 +201,7 @@ class BraveSearchEngine(BaseSearchEngine):
                 return results_with_content
                 
             except Exception as e:
-                print(f"Error retrieving full content: {e}")
+                logger.error(f"Error retrieving full content: {e}")
                 # Fall back to returning the items without full content
         
         # Return items with their full Brave information
@@ -231,7 +232,7 @@ class BraveSearchEngine(BaseSearchEngine):
         Returns:
             List of search results
         """
-        print("---Execute a search using Brave Search---")
+        logger.info("---Execute a search using Brave Search---")
         
         # Use the implementation from the parent class which handles all phases
         results = super().run(query)

local_deep_research/web_search_engines/engines/search_engine_ddg.py

@@ -4,6 +4,8 @@ from langchain_core.language_models import BaseLLM
 
 from local_deep_research.web_search_engines.search_engine_base import BaseSearchEngine
 from local_deep_research.web_search_engines.engines.full_search import FullSearchResults  # Import the FullSearchResults class
+import logging
+logger = logging.getLogger(__name__)
 
 class DuckDuckGoSearchEngine(BaseSearchEngine):
     """DuckDuckGo search engine implementation with two-phase retrieval"""
@@ -66,7 +68,7 @@ class DuckDuckGoSearchEngine(BaseSearchEngine):
         Returns:
             List of search results
         """
-        print("---Execute a search using DuckDuckGo---")
+        logger.info("---Execute a search using DuckDuckGo---")
         
         # Implementation of the two-phase approach (from parent class)
         return super().run(query)
@@ -103,7 +105,7 @@ class DuckDuckGoSearchEngine(BaseSearchEngine):
             return previews
             
         except Exception as e:
-            print(f"Error getting DuckDuckGo previews: {e}")
+            logger.error(f"Error getting DuckDuckGo previews: {e}")
             return []
     
     def _get_full_content(self, relevant_items: List[Dict[str, Any]]) -> List[Dict[str, Any]]:

local_deep_research/web_search_engines/engines/search_engine_local.py

@@ -764,7 +764,7 @@ class LocalSearchEngine(BaseSearchEngine):
         
         # Phase 3: Get full content for relevant items
         if hasattr(config, 'SEARCH_SNIPPETS_ONLY') and config.SEARCH_SNIPPETS_ONLY:
-            print("Returning snippet-only results as per config")
+            logger.info("Returning snippet-only results as per config")
             results = relevant_items
         else:
             results = self._get_full_content(relevant_items)