From 9b3b21b1a4d8814d74af6b9a60394350f450617e Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Fri, 10 Jul 2026 11:22:23 +0300
Subject: [PATCH] Document ingestion observability; drop stale logfire install
 extra

---
 docs/ingester.md         | 16 +++++++++++++++-
 haiku_rag_slim/README.md |  2 +-
 2 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/docs/ingester.md b/docs/ingester.md
index 9cd295f8..fdb7fa51 100644
--- a/docs/ingester.md
+++ b/docs/ingester.md
@@ -640,7 +640,21 @@ INFO     Processing upsert file:///.../a.md (job 5d9a...)
 INFO     Job 5d9a... succeeded in 0.34s: file:///.../a.md
 ```
 
-When `LOGFIRE_TOKEN` is set, spans are also shipped to Logfire.
+When `LOGFIRE_TOKEN` is set, spans are also shipped to Logfire. Spans carry
+`service.name` (`haiku-ingester`) and `service.version`. To tell concurrent
+ingestions apart in Logfire, give each process a distinct name via the standard
+`OTEL_SERVICE_NAME` (or `LOGFIRE_SERVICE_NAME`) environment variable, which
+overrides the default:
+
+```bash
+OTEL_SERVICE_NAME=ingester-tenant-a haiku-ingester serve
+```
+
+The span tree is `ingester.poller.sweep` -> `ingester.job` (tagged with
+`source_id` and `uri`) -> `document.convert` / `document.chunk`. When a source
+uses docling-serve, each request emits a `docling_serve.request` span carrying
+the instance `url` and `attempt`, so a failed conversion can be traced to the
+exact instance that served it.
 
 ### Operating against the API
 
diff --git a/haiku_rag_slim/README.md b/haiku_rag_slim/README.md
index 8e20df0c..12529a80 100644
--- a/haiku_rag_slim/README.md
+++ b/haiku_rag_slim/README.md
@@ -52,7 +52,7 @@ Adds support for 40+ file formats including PDF, DOCX, HTML, and more.
 ```bash
 # Common combinations
 uv pip install haiku.rag-slim[docling,anthropic,mxbai]
-uv pip install haiku.rag-slim[docling,groq,logfire]
+uv pip install haiku.rag-slim[docling,groq]
 ```
 
 ## Usage