local-deep-research 0.3.9__tar.gz → 0.3.11__tar.gz

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: local-deep-research
-Version: 0.3.9
+Version: 0.3.11
 Summary: AI-powered research assistant with deep, iterative analysis using LLMs and web searches
 Author-Email: LearningCircuit <185559241+LearningCircuit@users.noreply.github.com>, HashedViking <6432677+HashedViking@users.noreply.github.com>
 License: MIT License
@@ -108,34 +108,42 @@ Local Deep Research combines the power of large language models with intelligent
 
 ### Option 1: Docker (Recommended)
 
+LDR uses Docker compose to bundle the web app and all it's dependencies so
+you can get up and running quickly.
+
+### Prerequisites
+
+- [Docker](https://docs.docker.com/engine/install/)
+- [Docker Compose](https://docs.docker.com/compose/install/)
+- `cookiecutter`: Run `pip install --user cookiecutter`
+
+Clone the repository:
+
 ```bash
-# Step 1: Pull and run SearXNG for optimal search results
-docker pull searxng/searxng
-docker run -d -p 8080:8080 --name searxng searxng/searxng
+git clone https://github.com/LearningCircuit/local-deep-research.git
+cd local-deep-research
+```
 
-# Step 2: Pull and run Local Deep Research
-docker pull localdeepresearch/local-deep-research
-docker run -d -p 5000:5000 --name local-deep-research localdeepresearch/local-deep-research
+### Configuring with Docker Compose
 
-# Optional 3a: For connecting to already installed local Ollama (https://ollama.com/download) or other local services
-# docker run -d -p 5000:5000 --network host --name local-deep-research localdeepresearch/local-deep-research
+In the LDR repository, run the following command
+to do generate the compose file:
 
-# Optional 3b (recommended): Pull and run Ollama for local LLM capabilities
-# docker pull ollama/ollama
-# docker run -d -p 11434:11434 --name ollama ollama/ollama
-# docker exec -it ollama ollama pull gemma3:12b
+```bash
+cookiecutter cookiecutter-docker/
+```
 
-# Start containers - Required after each reboot (can be automated with this flag --restart unless-stopped in run)
-docker start searxng
-docker start local-deep-research
-# docker start ollama
+This will prompt you to answer a series of questions. Hit Enter repeatedly
+to accept the default values. It should generate a file in the repository called `docker-compose.default.yml`. To run LDR, use the following command:
+
+```bash
+docker compose -f docker-compose.default.yml up
 ```
 
 Then visit `http://127.0.0.1:5000` to start researching!
 
-> **Note**: If you need to connect to local services (like Ollama), add `--network host` to the command.
->
-> **Don't have Docker? It's installed in a few clicks: [Install Docker here](https://www.docker.com/get-started/)**
+See [here](https://github.com/LearningCircuit/local-deep-research/wiki/Installation#docker-installation-recommended) for more information about
+using Docker.
 
 ### Option 2: Python Package (mostly for programmatic access)
 

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/README.md

@@ -37,34 +37,42 @@ Local Deep Research combines the power of large language models with intelligent
 
 ### Option 1: Docker (Recommended)
 
+LDR uses Docker compose to bundle the web app and all it's dependencies so
+you can get up and running quickly.
+
+### Prerequisites
+
+- [Docker](https://docs.docker.com/engine/install/)
+- [Docker Compose](https://docs.docker.com/compose/install/)
+- `cookiecutter`: Run `pip install --user cookiecutter`
+
+Clone the repository:
+
 ```bash
-# Step 1: Pull and run SearXNG for optimal search results
-docker pull searxng/searxng
-docker run -d -p 8080:8080 --name searxng searxng/searxng
+git clone https://github.com/LearningCircuit/local-deep-research.git
+cd local-deep-research
+```
 
-# Step 2: Pull and run Local Deep Research
-docker pull localdeepresearch/local-deep-research
-docker run -d -p 5000:5000 --name local-deep-research localdeepresearch/local-deep-research
+### Configuring with Docker Compose
 
-# Optional 3a: For connecting to already installed local Ollama (https://ollama.com/download) or other local services
-# docker run -d -p 5000:5000 --network host --name local-deep-research localdeepresearch/local-deep-research
+In the LDR repository, run the following command
+to do generate the compose file:
 
-# Optional 3b (recommended): Pull and run Ollama for local LLM capabilities
-# docker pull ollama/ollama
-# docker run -d -p 11434:11434 --name ollama ollama/ollama
-# docker exec -it ollama ollama pull gemma3:12b
+```bash
+cookiecutter cookiecutter-docker/
+```
 
-# Start containers - Required after each reboot (can be automated with this flag --restart unless-stopped in run)
-docker start searxng
-docker start local-deep-research
-# docker start ollama
+This will prompt you to answer a series of questions. Hit Enter repeatedly
+to accept the default values. It should generate a file in the repository called `docker-compose.default.yml`. To run LDR, use the following command:
+
+```bash
+docker compose -f docker-compose.default.yml up
 ```
 
 Then visit `http://127.0.0.1:5000` to start researching!
 
-> **Note**: If you need to connect to local services (like Ollama), add `--network host` to the command.
->
-> **Don't have Docker? It's installed in a few clicks: [Install Docker here](https://www.docker.com/get-started/)**
+See [here](https://github.com/LearningCircuit/local-deep-research/wiki/Installation#docker-installation-recommended) for more information about
+using Docker.
 
 ### Option 2: Python Package (mostly for programmatic access)
 

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/pyproject.toml

@@ -57,7 +57,7 @@ dependencies = [
     "setuptools>=78.1.0",
     "flask-wtf>=1.2.2",
 ]
-version = "0.3.9"
+version = "0.3.11"
 
 [project.license]
 file = "LICENSE"
@@ -93,6 +93,14 @@ distribution = true
 source = "file"
 path = "src/local_deep_research/__version__.py"
 
+[[tool.pdm.source]]
+url = "https://download.pytorch.org/whl/cpu"
+name = "torch"
+include_packages = [
+    "torch",
+    "torch*",
+]
+
 [dependency-groups]
 dev = [
     "isort>=6.0.1",
@@ -100,4 +108,5 @@ dev = [
     "pre-commit>=4.2.0",
     "flake8>=7.1.2",
     "jupyter>=1.1.1",
+    "cookiecutter>=2.6.0",
 ]

local_deep_research-0.3.11/src/local_deep_research/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.3.11"

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/src/local_deep_research/defaults/default_settings.json

@@ -3029,16 +3029,29 @@
     },
     "search.engine.web.searxng.default_params.safe_search": {
         "category": "searxng",
-        "description": "Setting for searxng.default_params.safe_search",
+        "description": "Configure the safe search level",
         "editable": true,
         "max_value": null,
         "min_value": null,
         "name": "Safe Search",
-        "options": null,
+        "options": [
+            {
+                "label": "Off",
+                "value": "OFF"
+            },
+            {
+                "label": "Moderate",
+                "value": "MODERATE"
+            },
+            {
+                "label": "Strict",
+                "value": "STRICT"
+            }
+        ],
         "step": null,
         "type": "SEARCH",
-        "ui_element": "checkbox",
-        "value": 1,
+        "ui_element": "select",
+        "value": "OFF",
         "visible": true
     },
     "search.engine.web.searxng.full_search_class": {

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/src/local_deep_research/web/services/research_service.py

@@ -530,7 +530,7 @@ def run_research_process(
                     report_path = os.path.join(
                         OUTPUT_DIR,
                         f"quick_summary_{safe_query}_"
-                        f"{datetime.now().isoformat()}.md",
+                        f"{int(datetime.now().timestamp())}.md",
                     )
 
                     # Send progress update for writing to file
@@ -643,7 +643,7 @@ def run_research_process(
             safe_query = safe_query.replace(" ", "_").lower()
             report_path = os.path.join(
                 OUTPUT_DIR,
-                f"detailed_report_{safe_query}_{datetime.now().isoformat()}.md",
+                f"detailed_report_{safe_query}_{int(datetime.now().timestamp())}.md",
             )
 
             with open(report_path, "w", encoding="utf-8") as f:

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/src/local_deep_research/web_search_engines/engines/full_search.py

@@ -25,7 +25,7 @@ class FullSearchResults:
         max_results: int = 10,
         region: str = "wt-wt",
         time: str = "y",
-        safesearch: str = "Moderate",
+        safesearch: str | int = "Moderate",
     ):
         self.llm = llm
         self.output_format = output_format

{local_deep_research-0.3.9 → local_deep_research-0.3.11}/src/local_deep_research/web_search_engines/engines/search_engine_searxng.py

@@ -1,3 +1,4 @@
+import enum
 import logging
 import os
 import time
@@ -15,6 +16,17 @@ logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
+@enum.unique
+class SafeSearchSetting(enum.IntEnum):
+    """
+    Acceptable settings for safe search.
+    """
+
+    OFF = 0
+    MODERATE = 1
+    STRICT = 2
+
+
 class SearXNGSearchEngine(BaseSearchEngine):
     """
     SearXNG search engine implementation that requires an instance URL provided via
@@ -29,7 +41,7 @@ class SearXNGSearchEngine(BaseSearchEngine):
         categories: Optional[List[str]] = None,
         engines: Optional[List[str]] = None,
         language: str = "en",
-        safe_search: int = 1,
+        safe_search: str = SafeSearchSetting.OFF.name,
         time_range: Optional[str] = None,
         delay_between_requests: float = 0.0,
         llm: Optional[BaseLLM] = None,
@@ -89,7 +101,14 @@ class SearXNGSearchEngine(BaseSearchEngine):
         self.categories = categories or ["general"]
         self.engines = engines
         self.language = language
-        self.safe_search = safe_search
+        try:
+            self.safe_search = SafeSearchSetting[safe_search]
+        except ValueError:
+            logger.error(
+                "'{}' is not a valid safe search setting. Disabling safe search",
+                safe_search,
+            )
+            self.safe_search = SafeSearchSetting.OFF
         self.time_range = time_range
 
         self.delay_between_requests = float(
@@ -114,11 +133,7 @@ class SearXNGSearchEngine(BaseSearchEngine):
                 max_results=max_results,
                 region="wt-wt",
                 time="y",
-                safesearch=(
-                    "Moderate"
-                    if safe_search == 1
-                    else "Off" if safe_search == 0 else "Strict"
-                ),
+                safesearch=self.safe_search.value,
             )
 
         self.last_request_time = 0
@@ -177,7 +192,7 @@ class SearXNGSearchEngine(BaseSearchEngine):
                 "language": self.language,
                 "format": "html",  # Use HTML format instead of JSON
                 "pageno": 1,
-                "safesearch": self.safe_search,
+                "safesearch": self.safe_search.value,
                 "count": self.max_results,
             }
 

local_deep_research-0.3.9/src/local_deep_research/__main__.py

@@ -1,16 +0,0 @@
-"""
-Main entry point when running the package with `python -m local_deep_research`.
-This avoids circular imports by directly importing the main function after
-the package is fully loaded.
-"""
-
-
-def main():
-    # Only import main after the whole package has been initialized
-    from .main import main as main_func
-
-    main_func()
-
-
-if __name__ == "__main__":
-    main()

local_deep_research-0.3.9/src/local_deep_research/__version__.py

@@ -1 +0,0 @@
-__version__ = "0.3.9"

local_deep_research-0.3.9/src/local_deep_research/main.py

@@ -1,215 +0,0 @@
-import logging
-import sys
-from typing import Dict
-
-from . import get_advanced_search_system, get_report_generator
-from .config.config_files import settings
-from .utilities.db_utils import get_db_setting
-
-
-def print_report(report: Dict):
-    """Print and save the report in a readable format"""
-
-    # Print to console in readable format
-    print("\n=== GENERATED REPORT ===\n")
-
-    # Print content
-    print(report["content"])
-
-    # Save to file in markdown format
-    with open("report.md", "w", encoding="utf-8") as markdown_file:
-        # Write content
-        markdown_file.write(report["content"])
-
-        # Write metadata at the end of the file
-        markdown_file.write("\n\n---\n\n")
-        markdown_file.write("## Report Metadata\n")
-
-        markdown_file.write(f"- Query: {report['metadata']['query']}\n")
-
-    print("\nReport has been saved to report.md")
-
-
-# Create the report generator lazily to avoid circular imports
-def get_report_generator_instance():
-    return get_report_generator()
-
-
-# report_generator = IntegratedReportGenerator()
-report_generator = None  # Will be initialized when needed
-
-
-def main():
-    import logging
-
-    from .utilities.setup_utils import setup_user_directories
-
-    # Configure logging
-    logging.basicConfig(level=logging.INFO)
-    logger = logging.getLogger(__name__)
-    search_iterations = get_db_setting("search.iterations", settings.search.iterations)
-    questions_per_iteration = get_db_setting(
-        "search.questions_per_iteration", settings.search.questions_per_iteration
-    )
-    logger.info(
-        f"Starting with settings: iterations={search_iterations}, "
-        f"questions_per_iteration={questions_per_iteration}"
-    )
-
-    # Explicitly run setup
-    logger.info("Initializing configuration...")
-    setup_user_directories()
-
-    system = get_advanced_search_system()
-
-    print("Welcome to the Advanced Research System")
-    print("Type 'quit' to exit")
-
-    while True:
-        print("\nSelect output type:")
-        print("1) Quick Summary (Generated in a few minutes)")
-        print(
-            "2) Detailed Research Report (Recommended for deeper analysis - may take several hours)"
-        )
-        choice = input("Enter number (1 or 2): ").strip()
-
-        while choice not in ["1", "2"]:
-            print("\nInvalid input. Please enter 1 or 2:")
-            print("1) Quick Summary (Generated in a few minutes)")
-            print(
-                "2) Detailed Research Report (Recommended for deeper analysis - may take several hours)"
-            )
-            choice = input("Enter number (1 or 2): ").strip()
-
-        query = input("\nEnter your research query: ").strip()
-
-        if query.lower() == "quit":
-            break
-
-        # System will automatically use updated configuration
-        # through the automatic reloading in get_llm() and get_search()
-
-        if choice == "1":
-            print("\nResearching... This may take a few minutes.\n")
-        else:
-            print(
-                "\nGenerating detailed report... This may take several hours. Please be patient as this enables deeper analysis.\n"
-            )
-
-        results = system.analyze_topic(query)
-        if results:
-            if choice == "1":
-                # Quick Summary
-                print("\n=== QUICK SUMMARY ===")
-                if results["findings"] and len(results["findings"]) > 0:
-                    initial_analysis = [
-                        finding["content"] for finding in results["findings"]
-                    ]
-                    print(initial_analysis)
-
-            else:
-                # Full Report
-                # Initialize report_generator if not already done
-                global report_generator
-                if report_generator is None:
-                    report_generator = get_report_generator()
-
-                final_report = report_generator.generate_report(results, query)
-                print("\n=== RESEARCH REPORT ===")
-                print_report(final_report)
-
-                print("\n=== RESEARCH METRICS ===")
-                print(f"Search Iterations: {results['iterations']}")
-
-        else:
-            print("Research failed. Please try again.")
-
-
-# Add command for database migration
-if __name__ == "__main__":
-    import argparse
-
-    parser = argparse.ArgumentParser(description="Local Deep Research")
-    parser.add_argument("--web", action="store_true", help="Start the web server")
-    parser.add_argument(
-        "--migrate-db", action="store_true", help="Migrate legacy databases to ldr.db"
-    )
-    parser.add_argument("--debug", action="store_true", help="Enable debug mode")
-    parser.add_argument(
-        "--test-migration",
-        action="store_true",
-        help="Test migration by checking database contents",
-    )
-    parser.add_argument(
-        "--schema-upgrade",
-        action="store_true",
-        help="Run schema upgrades on the database (e.g., remove redundant tables)",
-    )
-
-    args = parser.parse_args()
-
-    if args.debug:
-        logging.basicConfig(level=logging.DEBUG)
-    else:
-        logging.basicConfig(level=logging.INFO)
-
-    if args.migrate_db:
-        try:
-            # First ensure data directory exists
-            from src.local_deep_research.setup_data_dir import setup_data_dir
-
-            setup_data_dir()
-
-            # Then run the migration
-            from src.local_deep_research.web.database.migrate_to_ldr_db import (
-                migrate_to_ldr_db,
-            )
-
-            print("Starting database migration...")
-            success = migrate_to_ldr_db()
-            if success:
-                print("Database migration completed successfully")
-                sys.exit(0)
-            else:
-                print("Database migration failed")
-                sys.exit(1)
-        except Exception as e:
-            print(f"Error running database migration: {e}")
-            sys.exit(1)
-
-    if args.test_migration:
-        try:
-            from src.local_deep_research.test_migration import main as test_main
-
-            sys.exit(test_main())
-        except Exception as e:
-            print(f"Error running migration test: {e}")
-            sys.exit(1)
-
-    if args.schema_upgrade:
-        try:
-            from src.local_deep_research.web.database.schema_upgrade import (
-                run_schema_upgrades,
-            )
-
-            print("Running database schema upgrades...")
-            success = run_schema_upgrades()
-            if success:
-                print("Schema upgrades completed successfully")
-                sys.exit(0)
-            else:
-                print("Schema upgrades failed")
-                sys.exit(1)
-        except Exception as e:
-            print(f"Error running schema upgrades: {e}")
-            sys.exit(1)
-
-    if args.web:
-        from src.local_deep_research.web.app import main as web_main
-
-        web_main()
-    else:
-        # Default to web if no command specified
-        from src.local_deep_research.web.app import main as web_main
-
-        web_main()