From dad815e6c56eb8ee356de0ff9a0a507033fa87a4 Mon Sep 17 00:00:00 2001 From: Ed Summers Date: Thu, 19 Nov 2026 14:23:27 -0500 Subject: [PATCH] docs(search): describe the search and fetch pipeline Explain the two stages: SearXNG queries DuckDuckGo and Brave, then Keenable fetches the top result pages. Name the SearXNG instance URL and disclose Keenable's logging, retention, processing location, and training use. Correct the claim that web search has no external dependency. --- governance/privacy-policy.md | 29 ++++++++++++++++++++++++----- guides/getting-started.md | 22 ++++++++++++++++++++-- operations/infrastructure.md | 15 ++++++++++++++- 3 files changed, 58 insertions(+), 8 deletions(-) diff --git a/governance/privacy-policy.md b/governance/privacy-policy.md index 94e4f75..241831c 100644 --- a/governance/privacy-policy.md +++ b/governance/privacy-policy.md @@ -83,13 +83,29 @@ Our server software keeps standard operational logs (dates, error messages, and ## 5. Search -Web search runs through our self-hosted search instance. Search queries are forwarded to the underlying search engines (e.g. DuckDuckGo), which may see them. This is inherent to how web search works. +Our self-hosted **SearXNG** instance at +[search.inference.coop](https://search.inference.coop) handles web search. It +forwards queries to **DuckDuckGo** and **Brave**, which handle them under their +own policies. + +To read the pages behind the results, LibreChat sends the top result URLs to +**Keenable**, a third-party page-fetch service. We use Keenable's keyless public +endpoint, so its default data policy applies. Keenable logs and stores the +fetched URL, the page content, the returned results, and our server's IP address +and user agent. Keenable's policy sets no fixed retention period. Keenable +processes data in the United States and in the countries where its service +providers operate. Keenable may use content and usage data to improve and train +its products. Your chat messages and account identity stay with us. + +Web search is optional. Leave the globe off for sensitive topics. If you need +search without a third-party page fetch, contact us about alternatives. ## 6. What we do NOT do - We do **not** train models on your data. -- We do **not** sell, rent, or share your data. -- We do **not** use your data for advertising or profiling. +- We do **not** sell or rent your data. +- We do **not** share data for advertising or profiling. The service providers + in §5 and §7 process data to run the service. ## 7. Third parties @@ -97,7 +113,9 @@ The models we serve are provided by third parties that change over time, each wi - **Open Collective** — handles billing and membership (their own privacy policy applies). - **Cloudron** — our self-hosted platform; no third-party cloud provider. -- **Search engines** — receive your search queries (see §5). +- **Search engines.** DuckDuckGo and Brave receive your search queries (see §5). +- **Keenable.** This page-fetch service receives result URLs and page content + (see §5). ## 8. Retention and deletion @@ -110,7 +128,8 @@ The models we serve are provided by third parties that change over time, each wi - Self-hosted on Cloudron (sandboxed apps, SSL, backups). - Per-member API keys; access gated on live membership. -- No external dependencies for core infrastructure. +- Core infrastructure has no external dependencies. Web search uses the + third-party services described in §5. ## 10. Your rights diff --git a/guides/getting-started.md b/guides/getting-started.md index 66e7970..db0e0d8 100644 --- a/guides/getting-started.md +++ b/guides/getting-started.md @@ -56,8 +56,10 @@ with the account you created in step 1. (GreenPT and Regolo, 100% renewable energy — Regolo adds a written zero-data-retention policy). See the [model list](models.md) for the full list. -- **Web search** — click the **globe** next to the message box to ground - answers in current web results (self-hosted search, no external dependency). +- **Web search.** Click the **globe** next to the message box to base answers + on current web results. Searches use our self-hosted SearXNG instance and + Keenable, a third-party page-fetch service. See [what happens during a + search](#what-happens-when-you-use-web-search). - **File uploads** — attach a document with the **paperclip** and ask the chat about it. - **Tools** — the **Tools menu** next to the message box lists everything the @@ -84,6 +86,22 @@ see "Your allowance" below. > — your full history is here in the new chat, but files you attached in the > old one are still accessible only there. +### What happens when you use web search + +Web search runs in two stages. + +1. Our self-hosted **SearXNG** instance at + [search.inference.coop](https://search.inference.coop) sends your query to + **DuckDuckGo** and **Brave**. +2. LibreChat sends the top result URLs to **Keenable**, a third-party + page-fetch service. Keenable reads each page and extracts its text. The model + receives those passages, and the answer cites the sources. + +SearXNG runs on co-op infrastructure. Keenable is an external service. The +[privacy policy](../governance/privacy-policy.md#5-search) describes how +Keenable handles fetched URLs and page content. Web search is optional. Leave +the globe off if you do not want pages fetched. + ### Add the chat to your phone The chat works like an app on your phone — no app store needed. Open diff --git a/operations/infrastructure.md b/operations/infrastructure.md index b1f72a0..e00f505 100644 --- a/operations/infrastructure.md +++ b/operations/infrastructure.md @@ -73,8 +73,21 @@ The co-op's software behind all of these is open source — see [The code](#the-code) below for where each piece lives. Open Collective (billing and fiscal sponsorship) is the one external service in -the flow — see +the membership flow. See [opencollective.com/inference-cooperative](https://opencollective.com/inference-cooperative). +Web search uses external services: DuckDuckGo and Brave receive queries, and +Keenable fetches page content. See [Web search](#web-search). + +### Web search + +LibreChat's web search runs in two stages. A self-hosted **SearXNG** instance at +[search.inference.coop](https://search.inference.coop) sends the query to +DuckDuckGo and Brave. It returns candidate results. LibreChat sends the top +result URLs to **Keenable**, a third-party page-fetch service. +Keenable extracts text from each page. The model uses that text as context for +the answer. SearXNG runs on co-op infrastructure. Keenable is an external +service, and the [privacy policy](../governance/privacy-policy.md#5-search) +describes its logging and retention. ## Mail