local-deep-research 0.2.3__py3-none-any.whl → 0.3.1__py3-none-any.whl

local_deep_research/defaults/local_collections.toml

@@ -1,53 +0,0 @@
-# Project Documents Collection
-[project_docs]
-name = "Project Documents"
-description = "Project documentation and specifications"
-paths = ["@format ${DOCS_DIR}/project_documents"]
-enabled = true
-embedding_model = "all-MiniLM-L6-v2"
-embedding_device = "cpu"
-embedding_model_type = "sentence_transformers"
-max_results = 20
-max_filtered_results = 5
-chunk_size = 1000
-chunk_overlap = 200
-cache_dir = "__CACHE_DIR__/local_search/project_docs"
-strengths = ["project documentation", "specifications", "internal documents"]
-weaknesses = ["no external information", "limited to organizational knowledge"]
-reliability = 0.9
-
-# Research Papers Collection
-[research_papers]
-name = "Research Papers"
-description = "Academic research papers and articles"
-paths = ["@format ${DOCS_DIR}/research_papers"]
-enabled = true
-embedding_model = "all-MiniLM-L6-v2"
-embedding_device = "cpu"
-embedding_model_type = "sentence_transformers"
-max_results = 20
-max_filtered_results = 5
-chunk_size = 800
-chunk_overlap = 150
-cache_dir = "__CACHE_DIR__/local_search/research_papers"
-strengths = ["academic research", "scientific papers", "scholarly content"]
-weaknesses = ["potentially outdated", "limited to collected papers"]
-reliability = 0.85
-
-# Personal Notes Collection
-[personal_notes]
-name = "Personal Notes"
-description = "Personal notes and documents"
-paths = ["@format ${DOCS_DIR}/personal_notes"]
-enabled = true
-embedding_model = "all-MiniLM-L6-v2"
-embedding_device = "cpu"
-embedding_model_type = "sentence_transformers"
-max_results = 30
-max_filtered_results = 10
-chunk_size = 500
-chunk_overlap = 100
-cache_dir = "__CACHE_DIR__/local_search/personal_notes"
-strengths = ["personal knowledge", "notes", "private documents"]
-weaknesses = ["subjective content", "informal information"]
-reliability = 0.75

local_deep_research/defaults/main.toml

@@ -1,80 +0,0 @@
-
-# Main configuration for Local Deep Research
-
-[web]
-port = 5000
-host = "0.0.0.0"
-debug = true
-
-[llm]
-# LLM provider (one of: ollama, openai, anthropic, vllm, openai_endpoint, lmstudio, llamacpp)
-provider = "ollama"
-# Model name
-model = "gemma3:12b"
-# Temperature
-temperature = 0.7
-# Maximum tokens
-max_tokens = 30000
-# OpenAI-compatible endpoint URL
-openai_endpoint_url = "https://openrouter.ai/api/v1"
-# LM Studio URL (default: http://localhost:1234)
-lmstudio_url = "http://localhost:1234"
-# LlamaCpp model path
-llamacpp_model_path = ""
-# LlamaCpp parameters
-llamacpp_n_gpu_layers = 1
-llamacpp_n_batch = 512
-llamacpp_f16_kv = true
-
-[general]
-# Directory for research outputs (relative to user data directory)
-output_dir = "research_outputs"
-# Knowledge accumulation approach (NONE, QUESTION, or ITERATION)
-knowledge_accumulation = "ITERATION"
-# Maximum context size for knowledge accumulation
-knowledge_accumulation_context_limit = 2000000
-# Enable fact checking (experimental, works better with large LLMs)
-enable_fact_checking = false
-
-
-[search]
-# Search tool to use (auto, wikipedia, arxiv, duckduckgo, serpapi, google_pse,etc.)
-# "auto" intelligently selects based on query content (recommended)
-# "local_all" searches only local document collections
-tool = "auto"
-
-# Number of research cycles
-iterations = 2
-
-# Questions generated per cycle
-questions_per_iteration = 2
-
-# Searches per report section
-searches_per_section = 2
-
-# Results per search query
-max_results = 50
-
-# Results after relevance filtering
-max_filtered_results = 5
-
-# Search region
-region = "us"
-
-# Time period (d=day, w=week, m=month, y=year)
-time_period = "y"
-
-# Enable safe search
-safe_search = true
-
-# Search language
-search_language = "English"
-
-# Return only snippets, not full content (faster but less detailed)
-snippets_only = true
-
-# Skip relevance filtering (return all results)
-skip_relevance_filter = false
-
-# Check URL quality
-quality_check_urls = true

local_deep_research/defaults/search_engines.toml

@@ -1,291 +0,0 @@
-# Search Engines Configuration for Local Deep Research
-# This file defines all available search engines and their properties
-
-[wikipedia]
-module_path = ".engines.search_engine_wikipedia"
-class_name = "WikipediaSearchEngine"
-requires_api_key = false
-reliability = 0.95
-strengths = [
-    "factual information", "general knowledge", "definitions",
-    "historical facts", "biographies", "overview information"
-]
-weaknesses = ["recent events", "specialized academic topics", "product comparisons"]
-
-[wikipedia.default_params]
-max_results = 20
-include_content = true
-
-[arxiv]
-module_path = ".engines.search_engine_arxiv"
-class_name = "ArXivSearchEngine"
-requires_api_key = false
-reliability = 0.9
-strengths = [
-    "scientific papers", "academic research", "physics", "computer science",
-    "mathematics", "statistics", "machine learning", "preprints"
-]
-weaknesses = ["non-academic topics", "consumer products", "news", "general information"]
-
-[arxiv.default_params]
-max_results = 20
-sort_by = "relevance"
-sort_order = "descending"
-
-[pubmed]
-module_path = ".engines.search_engine_pubmed"
-class_name = "PubMedSearchEngine"
-requires_api_key = false
-api_key_env = "NCBI_API_KEY"
-reliability = 0.98
-strengths = [
-    "biomedical literature", "medical research", "clinical studies",
-    "life sciences", "health information", "scientific papers"
-]
-weaknesses = [
-    "non-medical topics", "very recent papers may be missing",
-    "limited to published research"
-]
-requires_llm = true
-
-[pubmed.default_params]
-max_results = 20
-get_abstracts = true
-get_full_text = false
-full_text_limit = 3
-days_limit = 0
-optimize_queries = true
-
-[github]
-module_path = ".engines.search_engine_github"
-class_name = "GitHubSearchEngine"
-requires_api_key = false
-reliability = 0.99
-strengths = [
-    "code repositories", "software documentation", "open source projects",
-    "programming issues", "developer information", "technical documentation"
-]
-weaknesses = ["non-technical content", "content outside GitHub", "rate limits without API key"]
-supports_full_search = true
-
-[github.default_params]
-max_results = 15
-search_type = "repositories"
-include_readme = true
-include_issues = false
-
-[serpapi]
-module_path = ".engines.search_engine_serpapi"
-class_name = "SerpAPISearchEngine"
-requires_api_key = true
-api_key_env = "SERP_API_KEY"
-reliability = 0.6
-strengths = [
-    "comprehensive web search", "product information", "reviews",
-    "recent content", "news", "broad coverage"
-]
-weaknesses = ["requires API key with usage limits", "not specialized for academic content"]
-supports_full_search = true
-full_search_module = "local_deep_research.web_search_engines.engines.full_serp_search_results_old"
-full_search_class = "FullSerpAPISearchResults"
-
-[serpapi.default_params]
-region = "us"
-time_period = "y"
-safe_search = true
-search_language = "English"
-
-[searxng]
-module_path = ".engines.search_engine_searxng"
-class_name = "SearXNGSearchEngine"
-requires_api_key = false
-api_key_env = "SEARXNG_INSTANCE"
-reliability = 0.9
-strengths = [
-    "privacy-focused", "metasearch engine", "self-hosted",
-    "no tracking", "configurable", "multiple engines in one"
-]
-weaknesses = [
-    "requires self-hosting", "depends on other search engines",
-    "may be rate limited by underlying engines"
-]
-supports_full_search = true
-full_search_module = ".engines.full_search"
-full_search_class = "FullSearchResults"
-
-[searxng.default_params]
-max_results = 15
-categories = ["general"]
-language = "en"
-safe_search = 1
-delay_between_requests = 0.0
-include_full_content = true
-
-[google_pse]
-module_path = ".engines.search_engine_google_pse"
-class_name = "GooglePSESearchEngine"
-requires_api_key = true
-api_key_env = "GOOGLE_PSE_API_KEY"
-reliability = 0.9
-strengths = [
-    "custom search scope", "high-quality results", "domain-specific search",
-    "configurable search experience", "control over search index"
-]
-weaknesses = [
-    "requires API key with usage limits",
-    "limited to 10,000 queries/day on free tier",
-    "requires search engine configuration in Google Control Panel"
-]
-supports_full_search = true
-full_search_module = ".engines.full_search"
-full_search_class = "FullSearchResults"
-
-[google_pse.default_params]
-region = "us"
-safe_search = true
-search_language = "English"
-
-[brave]
-module_path = ".engines.search_engine_brave"
-class_name = "BraveSearchEngine"
-requires_api_key = true
-api_key_env = "BRAVE_API_KEY"
-reliability = 0.7
-strengths = [
-    "privacy-focused web search", "product information", "reviews",
-    "recent content", "news", "broad coverage"
-]
-weaknesses = ["requires API key with usage limits", "smaller index than Google"]
-supports_full_search = true
-full_search_module = "local_deep_research.web_search_engines.engines.full_search"
-full_search_class = "FullSearchResults"
-
-[brave.default_params]
-region = "US"
-time_period = "y"
-safe_search = true
-search_language = "English"
-
-[wayback]
-module_path = ".engines.search_engine_wayback"
-class_name = "WaybackSearchEngine"
-requires_api_key = false
-reliability = 0.5
-strengths = [
-    "historical web content", "archived websites", "content verification",
-    "deleted or changed web pages", "website evolution tracking"
-]
-weaknesses = [
-    "limited to previously archived content", "may miss recent changes",
-    "archiving quality varies"
-]
-supports_full_search = true
-
-[wayback.default_params]
-max_results = 15
-max_snapshots_per_url = 3
-closest_only = false
-language = "English"
-
-[auto]
-module_path = ".engines.meta_search_engine"
-class_name = "MetaSearchEngine"
-requires_api_key = false
-reliability = 0.85
-strengths = [
-    "intelligent engine selection", "adaptable to query type",
-    "fallback capabilities"
-]
-weaknesses = ["slightly slower due to LLM analysis"]
-requires_llm = true
-
-[auto.default_params]
-use_api_key_services = true
-max_engines_to_try = 3
-
-[local_all]
-module_path = ".engines.search_engine_local_all"
-class_name = "LocalAllSearchEngine"
-requires_api_key = false
-reliability = 0.85
-strengths = ["searches all local collections", "personal documents", "offline access"]
-weaknesses = ["may return too many results", "requires indexing"]
-requires_llm = true
-
-#[semantic_scholar]
-#module_path = ".engines.search_engine_semantic_scholar"
-#class_name = "SemanticScholarSearchEngine"
-#requires_api_key = false
-#api_key_env = "S2_API_KEY"
-#reliability = 0.87
-#strengths = [
-#    "comprehensive scientific literature",
-#    "extensive citation network",
-#    "AI-generated summaries (TLDRs)",
-#    "academic paper metadata",
-#    "cross-disciplinary coverage",
-#    "200M+ papers across all fields",
-#    "usable without API key"
-#]
-#weaknesses = [
-#    "rate limited (1000 requests/day) without API key",
-#    "limited to academic content"
-#]
-#supports_full_search = true
-#requires_llm = false
-
-#[semantic_scholar.default_params]
-#max_results = 20
-#get_abstracts = true
-#get_tldr = true
-#get_references = false
-#get_citations = false
-#get_embeddings = false
-#citation_limit = 10
-#reference_limit = 10
-#optimize_queries = true
-#max_retries = 5
-#retry_backoff_factor = 1.0
-
-# Default search engine to use if none specified
-DEFAULT_SEARCH_ENGINE = "wikipedia"
-
-
-
-
-
-# Additional search engines can be added below
-# Uncomment and modify these templates as needed
-
-# [duckduckgo]
-# module_path = ".engines.search_engine_ddg"
-# class_name = "DuckDuckGoSearchEngine"
-# requires_api_key = false
-# reliability = 0.4
-# strengths = [
-#     "web search", "product information", "reviews", "recent information",
-#     "news", "general queries", "broad coverage"
-# ]
-# weaknesses = ["inconsistent due to rate limits", "not specialized for academic content"]
-# supports_full_search = true
-# full_search_module = "local_deep_research.web_search_engines.engines.full_search"
-# full_search_class = "FullSearchResults"
-#
-# [duckduckgo.default_params]
-# region = "us"
-# safe_search = true
-
-# [guardian]
-# module_path = ".engines.search_engine_guardian"
-# class_name = "GuardianSearchEngine"
-# requires_api_key = true
-# api_key_env = "GUARDIAN_API_KEY"
-# reliability = 0.5
-# strengths = [
-#     "news articles", "current events", "opinion pieces", "journalism",
-#     "UK and global news", "political analysis"
-# ]
-# weaknesses = ["primarily focused on news", "limited historical content pre-1999"]
-#
-# [guardian.default_params]
-# order_by = "relevance"