Merge pull request 'docs(search): page fetching runs on co-op infrastructure' (#16) from search-fetcher into main

This commit is contained in:
inference-bot committed 2026-11-19 23:07:32 +00:00
commit 7dd072d245
3 files changed
+25 -26

No files matched your search

+11 -14
View File
@@ -92,17 +92,15 @@ retention: deleted when you delete a saved chat, or about an hour after a
Temporary Chat is created. Operational details are in Temporary Chat is created. Operational details are in
[Infrastructure](../operations/infrastructure.md#chat-retention-and-web-search). [Infrastructure](../operations/infrastructure.md#chat-retention-and-web-search).
To read the pages behind the results, LibreChat sends the top result URLs to To read the pages behind the results, our own page-fetch service fetches the
**Keenable**, a third-party page-fetch service. We use Keenable's keyless public top result URLs. It runs on co-op infrastructure at fetch.inference.coop. The
endpoint, so its default data policy applies. Keenable logs and stores the service does not log the URLs or the page text and keeps no copy: the extracted
fetched URL, the page content, the returned results, and our server's IP address text goes to the model for that answer and is not stored by the fetcher. It
and user agent. Keenable's policy sets no fixed retention period. Keenable refuses private, loopback, and internal addresses, so it cannot be used to reach
processes data in the United States and in the countries where its service our own network. Your chat messages and account identity stay with us.
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 Web search is optional. Leave the globe off for sensitive topics. Note that the
search without a third-party page fetch, contact us about alternatives. search engines in §7 still receive your query when you use it.
## 6. What we do NOT do ## 6. What we do NOT do
@@ -118,8 +116,7 @@ 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). - **Open Collective** — handles billing and membership (their own privacy policy applies).
- **Cloudron** — our self-hosted platform; no third-party cloud provider. - **Cloudron** — our self-hosted platform; no third-party cloud provider.
- **Search engines.** DuckDuckGo and Brave 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 Page fetching runs on co-op infrastructure, not at a third party.
(see §5).
## 8. Retention and deletion ## 8. Retention and deletion
@@ -132,8 +129,8 @@ The models we serve are provided by third parties that change over time, each wi
- Self-hosted on Cloudron (sandboxed apps, SSL, backups). - Self-hosted on Cloudron (sandboxed apps, SSL, backups).
- Per-member API keys; access gated on live membership. - Per-member API keys; access gated on live membership.
- Core infrastructure has no external dependencies. Web search uses the - Core infrastructure has no external dependencies. Web search sends queries
third-party services described in §5. to the search engines named in §5; page fetching runs on co-op infrastructure.
## 10. Your rights ## 10. Your rights
+9 -9
View File
@@ -57,8 +57,8 @@ with the account you created in step 1.
zero-data-retention policy). See the [model list](models.md) for the full zero-data-retention policy). See the [model list](models.md) for the full
list. list.
- **Web search.** Click the **globe** next to the message box to base answers - **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 on current web results. Searches use our self-hosted SearXNG instance, and
Keenable, a third-party page-fetch service. See [what happens during a pages are read by our own fetcher. See [what happens during a
search](#what-happens-when-you-use-web-search). search](#what-happens-when-you-use-web-search).
- **File uploads** — attach a document with the **paperclip** and ask the - **File uploads** — attach a document with the **paperclip** and ask the
chat about it. chat about it.
@@ -93,14 +93,14 @@ Web search runs in two stages.
1. Our self-hosted **SearXNG** instance at 1. Our self-hosted **SearXNG** instance at
[search.inference.coop](https://search.inference.coop) sends your query to [search.inference.coop](https://search.inference.coop) sends your query to
**DuckDuckGo** and **Brave**. **DuckDuckGo** and **Brave**.
2. LibreChat sends the top result URLs to **Keenable**, a third-party 2. LibreChat sends the top result URLs to the co-op's **own page fetcher**. It
page-fetch service. Keenable reads each page and extracts its text. The model reads each page and extracts its text. The model receives those passages,
receives those passages, and the answer cites the sources. and the answer cites the sources.
SearXNG runs on co-op infrastructure. Keenable is an external service. The Both SearXNG and the page fetcher run on co-op infrastructure. The fetcher does
[privacy policy](../governance/privacy-policy.md#5-search) describes how not log the URLs or the page text and keeps no copy. The
Keenable handles fetched URLs and page content. Web search is optional. Leave [privacy policy](../governance/privacy-policy.md#5-search) describes this. Web
the globe off if you do not want pages fetched. search is optional. Leave the globe off if you do not want pages fetched.
### Add the chat to your phone ### Add the chat to your phone
+5 -3
View File
@@ -201,9 +201,11 @@ contain query text when an upstream engine request fails; those log lines carry
no member identity or IP, and are retained only briefly. The reverse proxy does no member identity or IP, and are retained only briefly. The reverse proxy does
not log search queries. not log search queries.
LibreChat reads the pages behind the results through **Keenable**, a third-party LibreChat reads the pages behind the results through the co-op's **own
page-fetch service. Keenable's logging and retention are described in the page-fetch service** (`fetch.inference.coop`), a small app on our Cloudron. It
[privacy policy](../governance/privacy-policy.md#5-search). runs with no access log and keeps no copy of URLs or page text; it refuses
private, loopback, and internal addresses. The
[privacy policy](../governance/privacy-policy.md#5-search) describes it.
## Security posture (plain language) ## Security posture (plain language)