From 4e9c66ee25ed77858985765382f41d0cf22ea588 Mon Sep 17 00:00:00 2001 From: tanaka takashi Date: Tue, 20 Oct 2026 02:03:54 +0900 Subject: Improve web search region selection and normalize provider results Update ddgs to 9.16.0 and keep backend="auto" while preserving the LLM-facing query/max_results inputs and title/href/body result schema. Implementation: - Add OLLAMA_WEB_SEARCH_REGION with auto/us-en/jp-jp values, normalized configuration input, and a clear startup error for unsupported values. - In auto mode, detect kana after NFKC normalization and exclusion of URLs and site:/filetype: tokens. Select jp-jp for kana and us-en otherwise, without modifying the original query or sharing per-call region state. - Preserve href/url and body/snippet fallbacks and normalize None values. - Reject malformed HTTP(S) URLs without DNS lookups or extra requests. - Unwrap known Yahoo redirect URLs before excluding Bing aclick ads. - Represent missing and URL-only titles as empty strings rather than inventing titles from snippets. Preserve remaining provider order and allow fewer results after filtering, without additional searches. - Preserve provider exception propagation and identify ddgs in error logs. Coverage and documentation: - Add 72 regression cases for configuration, region routing, concurrency, public schemas, title/URL/ad boundaries, limits, and search_and_fetch continuation. Update existing provider mocks and log assertions. - Document the region environment setting and result semantics in both READMEs and tools-schema.md; update the changelog. - Keep only a short backend availability caveat in tools-schema.md and remove the temporary backend comparison, design, and validation docs. Validation: - pytest: 222 passed; ruff check . and mypy src/ passed. - uv lock --check and git diff --check passed. - Initial live acceptance: 56 searches plus 3 registry smoke checks; default-region auto succeeded 8/18 times and real ad filtering removed two ads. Stable relevance/title quality targets remain unmet because provider acquisition is unreliable. - Follow-up backend study: 234 comparative searches plus 3 Yahoo response diagnostics. Yahoo led individual backends at 9/18; restricted multi- backend combinations did not outperform the contemporaneous auto control. Authentication, access restrictions, temporary upstream failures, and Yahoo HTML/parser mismatches were observed. Do not claim search reliability is fixed or add backend configuration, custom retries, ranking changes, or challenge bypasses. Running app processes were not restarted; restart is needed to load the changes. --- src/ollama_web/config.py | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'src/ollama_web/config.py') diff --git a/src/ollama_web/config.py b/src/ollama_web/config.py index fa07384..484038a 100644 --- a/src/ollama_web/config.py +++ b/src/ollama_web/config.py @@ -12,6 +12,13 @@ def _csv_env(name: str) -> list[str]: return [part.strip() for part in raw.split(",") if part.strip()] +def _search_region_env() -> str: + region = os.environ.get("OLLAMA_WEB_SEARCH_REGION", "auto").strip().lower() + if region not in {"auto", "us-en", "jp-jp"}: + raise ValueError("OLLAMA_WEB_SEARCH_REGION must be one of: auto, us-en, jp-jp") + return region + + @dataclass class Settings: """Runtime settings resolved from environment variables.""" @@ -48,6 +55,7 @@ class Settings: scrape_timeout: float = 15.0 scrape_max_chars: int = 4000 search_max_results: int = 5 + search_region: str = field(default_factory=_search_region_env) fetch_max_results: int = 3 fetch_max_chars: int = 8000 max_fetch_mb: int = 10 -- cgit v1.2.3