From e6e3273caefcd69a5628d8c6a53d8fd047181014 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Wed, 29 Oct 2025 10:50:25 +0200
Subject: [PATCH] Document include/exclude patterns in FileMonitor

---
 docs/configuration.md | 56 +++++++++++++++++++++++++++++++++++++++++++
 docs/server.md        | 27 +++++++++++++++++++++
 2 files changed, 83 insertions(+)

diff --git a/docs/configuration.md b/docs/configuration.md
index c03640af..a22c0428 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -58,6 +58,8 @@ storage:
   monitor_directories:
     - /path/to/documents
     - /another/path
+  monitor_ignore_patterns: []  # Gitignore-style patterns to exclude
+  monitor_include_patterns: []  # Gitignore-style patterns to include
   disable_autocreate: false
   vacuum_retention_seconds: 60
 
@@ -167,6 +169,60 @@ storage:
     - /another_path/to/documents
 ```
 
+### Filtering Monitored Files
+
+Use gitignore-style patterns to control which files are monitored:
+
+```yaml
+storage:
+  monitor_directories:
+    - /path/to/documents
+
+  # Exclude specific files or directories
+  monitor_ignore_patterns:
+    - "*draft*"         # Ignore files with "draft" in the name
+    - "temp/"           # Ignore temp directory
+    - "**/archive/**"   # Ignore all archive directories
+    - "*.backup"        # Ignore backup files
+
+  # Only include specific files (whitelist mode)
+  monitor_include_patterns:
+    - "*.md"            # Only markdown files
+    - "*.pdf"           # Only PDF files
+    - "**/docs/**"      # Only files in docs directories
+```
+
+**How patterns work:**
+
+1. **Extension filtering** - Only supported file types are considered
+2. **Include patterns** - If specified, only matching files are included (whitelist)
+3. **Ignore patterns** - Matching files are excluded (blacklist)
+4. **Combining both** - Include patterns are applied first, then ignore patterns
+
+**Common patterns:**
+
+```yaml
+# Only monitor markdown documentation, but ignore drafts
+monitor_include_patterns:
+  - "*.md"
+monitor_ignore_patterns:
+  - "*draft*"
+  - "*WIP*"
+
+# Monitor all supported files except in specific directories
+monitor_ignore_patterns:
+  - "node_modules/"
+  - ".git/"
+  - "**/test/**"
+  - "**/temp/**"
+```
+
+Patterns follow [gitignore syntax](https://git-scm.com/docs/gitignore#_pattern_format):
+- `*` matches anything except `/`
+- `**` matches zero or more directories
+- `?` matches any single character
+- `[abc]` matches any character in the set
+
 ## Embedding Providers
 
 If you use Ollama, you can use any pulled model that supports embeddings.
diff --git a/docs/server.md b/docs/server.md
index 0558654b..ef79e7f9 100644
--- a/docs/server.md
+++ b/docs/server.md
@@ -66,6 +66,33 @@ haiku-rag serve --monitor
 - **File Added/Modified**: Automatically parses and updates documents
 - **File Deleted**: Removes corresponding documents from database
 
+### Filtering Files
+
+You can filter which files to monitor using gitignore-style patterns:
+
+```yaml
+storage:
+  monitor_directories:
+    - /path/to/documents
+
+  # Ignore patterns (exclude files)
+  monitor_ignore_patterns:
+    - "*draft*"         # Ignore draft files
+    - "temp/"           # Ignore temp directory
+    - "**/archive/**"   # Ignore archive directories
+
+  # Include patterns (whitelist files)
+  monitor_include_patterns:
+    - "*.md"           # Only markdown files
+    - "**/docs/**"     # Files in docs directories
+```
+
+**Pattern behavior:**
+- Extension filtering is applied first (only supported file types)
+- Include patterns create a whitelist (if specified)
+- Ignore patterns exclude files
+- Both can be combined for fine-grained control
+
 ### Supported Formats
 
 The server can parse 40+ file formats including: