chunksilo 2.0.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of chunksilo might be problematic. Click here for more details.
- chunksilo-2.0.0/LICENSE +191 -0
- chunksilo-2.0.0/NOTICE +33 -0
- chunksilo-2.0.0/PKG-INFO +366 -0
- chunksilo-2.0.0/README.md +326 -0
- chunksilo-2.0.0/pyproject.toml +43 -0
- chunksilo-2.0.0/requirements.txt +13 -0
- chunksilo-2.0.0/setup.cfg +4 -0
- chunksilo-2.0.0/src/chunksilo/__init__.py +4 -0
- chunksilo-2.0.0/src/chunksilo/__main__.py +3 -0
- chunksilo-2.0.0/src/chunksilo/cfgload.py +163 -0
- chunksilo-2.0.0/src/chunksilo/cli.py +124 -0
- chunksilo-2.0.0/src/chunksilo/confluence_html_formatter.py +96 -0
- chunksilo-2.0.0/src/chunksilo/index.py +1420 -0
- chunksilo-2.0.0/src/chunksilo/search.py +784 -0
- chunksilo-2.0.0/src/chunksilo/server.py +110 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/PKG-INFO +366 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/SOURCES.txt +28 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/dependency_links.txt +1 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/entry_points.txt +3 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/requires.txt +20 -0
- chunksilo-2.0.0/src/chunksilo.egg-info/top_level.txt +1 -0
- chunksilo-2.0.0/test/test_chunk_location.py +399 -0
- chunksilo-2.0.0/test/test_confluence_html_formatter.py +134 -0
- chunksilo-2.0.0/test/test_error_handling.py +221 -0
- chunksilo-2.0.0/test/test_heading_path_integration.py +236 -0
- chunksilo-2.0.0/test/test_incremental_ingest.py +128 -0
- chunksilo-2.0.0/test/test_rag_metrics.py +878 -0
- chunksilo-2.0.0/test/test_retrieval_only.py +100 -0
- chunksilo-2.0.0/test/test_system.py +67 -0
- chunksilo-2.0.0/test/test_utils.py +255 -0
chunksilo-2.0.0/LICENSE
ADDED
|
@@ -0,0 +1,191 @@
|
|
|
1
|
+
|
|
2
|
+
Apache License
|
|
3
|
+
Version 2.0, January 2004
|
|
4
|
+
http://www.apache.org/licenses/
|
|
5
|
+
|
|
6
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
7
|
+
|
|
8
|
+
1. Definitions.
|
|
9
|
+
|
|
10
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
11
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
12
|
+
|
|
13
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
14
|
+
the copyright owner that is granting the License.
|
|
15
|
+
|
|
16
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
17
|
+
other entities that control, are controlled by, or are under common
|
|
18
|
+
control with that entity. For the purposes of this definition,
|
|
19
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
20
|
+
direction or management of such entity, whether by contract or
|
|
21
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
22
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
23
|
+
|
|
24
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
25
|
+
exercising permissions granted by this License.
|
|
26
|
+
|
|
27
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
28
|
+
including but not limited to software source code, documentation
|
|
29
|
+
source, and configuration files.
|
|
30
|
+
|
|
31
|
+
"Object" form shall mean any form resulting from mechanical
|
|
32
|
+
transformation or translation of a Source form, including but
|
|
33
|
+
not limited to compiled object code, generated documentation,
|
|
34
|
+
and conversions to other media types.
|
|
35
|
+
|
|
36
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
37
|
+
Object form, made available under the License, as indicated by a
|
|
38
|
+
copyright notice that is included in or attached to the work
|
|
39
|
+
(an example is provided in the Appendix below).
|
|
40
|
+
|
|
41
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
42
|
+
form, that is based on (or derived from) the Work and for which the
|
|
43
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
44
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
45
|
+
of this License, Derivative Works shall not include works that remain
|
|
46
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
47
|
+
the Work and Derivative Works thereof.
|
|
48
|
+
|
|
49
|
+
"Contribution" shall mean any work of authorship, including
|
|
50
|
+
the original version of the Work and any modifications or additions
|
|
51
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
52
|
+
submitted to the Licensor for inclusion in the Work by the copyright owner
|
|
53
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
54
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
55
|
+
means any form of electronic, verbal, or written communication sent
|
|
56
|
+
to the Licensor or its representatives, including but not limited to
|
|
57
|
+
communication on electronic mailing lists, source code control systems,
|
|
58
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
59
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
60
|
+
excluding communication that is conspicuously marked or otherwise
|
|
61
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
62
|
+
|
|
63
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
64
|
+
on behalf of whom a Contribution has been received by the Licensor and
|
|
65
|
+
subsequently incorporated within the Work.
|
|
66
|
+
|
|
67
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
68
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
69
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
70
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
71
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
72
|
+
Work and such Derivative Works in Source or Object form.
|
|
73
|
+
|
|
74
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
75
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
76
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
77
|
+
(except as stated in this section) patent license to make, have made,
|
|
78
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
79
|
+
where such license applies only to those patent claims licensable
|
|
80
|
+
by such Contributor that are necessarily infringed by their
|
|
81
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
82
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
83
|
+
institute patent litigation against any entity (including a
|
|
84
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
85
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
86
|
+
or contributory patent infringement, then any patent licenses
|
|
87
|
+
granted to You under this License for that Work shall terminate
|
|
88
|
+
as of the date such litigation is filed.
|
|
89
|
+
|
|
90
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
91
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
92
|
+
modifications, and in Source or Object form, provided that You
|
|
93
|
+
meet the following conditions:
|
|
94
|
+
|
|
95
|
+
(a) You must give any other recipients of the Work or
|
|
96
|
+
Derivative Works a copy of this License; and
|
|
97
|
+
|
|
98
|
+
(b) You must cause any modified files to carry prominent notices
|
|
99
|
+
stating that You changed the files; and
|
|
100
|
+
|
|
101
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
102
|
+
that You distribute, all copyright, patent, trademark, and
|
|
103
|
+
attribution notices from the Source form of the Work,
|
|
104
|
+
excluding those notices that do not pertain to any part of
|
|
105
|
+
the Derivative Works; and
|
|
106
|
+
|
|
107
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
108
|
+
distribution, then any Derivative Works that You distribute must
|
|
109
|
+
include a readable copy of the attribution notices contained
|
|
110
|
+
within such NOTICE file, excluding any notices that do not
|
|
111
|
+
pertain to any part of the Derivative Works, in at least one
|
|
112
|
+
of the following places: within a NOTICE text file distributed
|
|
113
|
+
as part of the Derivative Works; within the Source form or
|
|
114
|
+
documentation, if provided along with the Derivative Works; or,
|
|
115
|
+
within a display generated by the Derivative Works, if and
|
|
116
|
+
wherever such third-party notices normally appear. The contents
|
|
117
|
+
of the NOTICE file are for informational purposes only and
|
|
118
|
+
do not modify the License. You may add Your own attribution
|
|
119
|
+
notices within Derivative Works that You distribute, alongside
|
|
120
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
121
|
+
that such additional attribution notices cannot be construed
|
|
122
|
+
as modifying the License.
|
|
123
|
+
|
|
124
|
+
You may add Your own copyright statement to Your modifications and
|
|
125
|
+
may provide additional or different license terms and conditions
|
|
126
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
127
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
128
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
129
|
+
the conditions stated in this License.
|
|
130
|
+
|
|
131
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
132
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
133
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
134
|
+
this License, without any additional terms or conditions.
|
|
135
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
136
|
+
the terms of any separate license agreement you may have executed
|
|
137
|
+
with Licensor regarding such Contributions.
|
|
138
|
+
|
|
139
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
140
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
141
|
+
except as required for reasonable and customary use in describing the
|
|
142
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
143
|
+
|
|
144
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
145
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
146
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
147
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
148
|
+
implied, including, without limitation, any warranties or conditions
|
|
149
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
150
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
151
|
+
appropriateness of using or redistributing the Work and assume any
|
|
152
|
+
risks associated with Your exercise of permissions under this License.
|
|
153
|
+
|
|
154
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
155
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
156
|
+
unless required by applicable law (such as deliberate and grossly
|
|
157
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
158
|
+
liable to You for damages, including any direct, indirect, special,
|
|
159
|
+
incidental, or consequential damages of any character arising as a
|
|
160
|
+
result of this License or out of the use or inability to use the
|
|
161
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
162
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
163
|
+
other commercial damages or losses), even if such Contributor
|
|
164
|
+
has been advised of the possibility of such damages.
|
|
165
|
+
|
|
166
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
167
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
168
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
169
|
+
or other liability obligations and/or rights consistent with this
|
|
170
|
+
License. However, in accepting such obligations, You may act only
|
|
171
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
172
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
173
|
+
defend, and hold each Contributor harmless for any liability
|
|
174
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
175
|
+
of your accepting any such warranty or additional liability.
|
|
176
|
+
|
|
177
|
+
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
Copyright 2026 Fredrik Reveny
|
|
180
|
+
|
|
181
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
182
|
+
you may not use this file except in compliance with the License.
|
|
183
|
+
You may obtain a copy of the License at
|
|
184
|
+
|
|
185
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
186
|
+
|
|
187
|
+
Unless required by applicable law or agreed to in writing, software
|
|
188
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
189
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
190
|
+
See the License for the specific language governing permissions and
|
|
191
|
+
limitations under the License.
|
chunksilo-2.0.0/NOTICE
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
ChunkSilo
|
|
2
|
+
Copyright 2026 Fredrik Reveny
|
|
3
|
+
|
|
4
|
+
This product includes software developed by third parties.
|
|
5
|
+
|
|
6
|
+
The following bundled components are distributed under the Apache License 2.0:
|
|
7
|
+
|
|
8
|
+
- fastembed: Copyright 2024 Qdrant
|
|
9
|
+
- huggingface-hub: Copyright Hugging Face
|
|
10
|
+
- tokenizers: Copyright Hugging Face
|
|
11
|
+
- flashrank: Copyright Prithivi Da
|
|
12
|
+
- nltk: Copyright NLTK Project
|
|
13
|
+
- aiohttp: Copyright aio-libs contributors
|
|
14
|
+
- cryptography: Copyright The Python Cryptographic Authority developers
|
|
15
|
+
- tenacity: Copyright Julien Danjou
|
|
16
|
+
|
|
17
|
+
The following transitive dependency is distributed under the
|
|
18
|
+
GNU Lesser General Public License v3.0 (LGPL-3.0):
|
|
19
|
+
|
|
20
|
+
- svglib: Copyright Dinu Gherman
|
|
21
|
+
Source: https://github.com/deeplook/svglib
|
|
22
|
+
License: https://www.gnu.org/licenses/lgpl-3.0.html
|
|
23
|
+
(Transitive dependency of llama-index-readers-confluence.
|
|
24
|
+
Not modified. Users may replace this library freely via pip.)
|
|
25
|
+
|
|
26
|
+
Bundled models:
|
|
27
|
+
|
|
28
|
+
- BAAI/bge-small-en-v1.5: Copyright Beijing Academy of Artificial Intelligence (MIT License)
|
|
29
|
+
- cross-encoder/ms-marco-MiniLM-L-12-v2: Copyright Nils Reimers (Apache License 2.0)
|
|
30
|
+
|
|
31
|
+
Full license texts for these dependencies are available in their
|
|
32
|
+
respective source distributions or at:
|
|
33
|
+
https://www.apache.org/licenses/LICENSE-2.0
|
chunksilo-2.0.0/PKG-INFO
ADDED
|
@@ -0,0 +1,366 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: chunksilo
|
|
3
|
+
Version: 2.0.0
|
|
4
|
+
Summary: Local RAG-based semantic document search with MCP server interface
|
|
5
|
+
Author: Fredrik Reveny
|
|
6
|
+
License-Expression: Apache-2.0
|
|
7
|
+
Project-URL: Repository, https://github.com/Chetic/chunksilo
|
|
8
|
+
Project-URL: Issues, https://github.com/Chetic/chunksilo/issues
|
|
9
|
+
Keywords: rag,mcp,semantic-search,document-search,llm
|
|
10
|
+
Classifier: Development Status :: 4 - Beta
|
|
11
|
+
Classifier: Programming Language :: Python :: 3
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
15
|
+
Classifier: Topic :: Text Processing :: Indexing
|
|
16
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
17
|
+
Requires-Python: >=3.11
|
|
18
|
+
Description-Content-Type: text/markdown
|
|
19
|
+
License-File: LICENSE
|
|
20
|
+
License-File: NOTICE
|
|
21
|
+
Requires-Dist: llama-index<1,>=0.10.0
|
|
22
|
+
Requires-Dist: llama-index-readers-file<1,>=0.1.0
|
|
23
|
+
Requires-Dist: llama-index-embeddings-fastembed<1,>=0.5.0
|
|
24
|
+
Requires-Dist: llama-index-retrievers-bm25<1,>=0.1.0
|
|
25
|
+
Requires-Dist: pillow<11,>=10.3.0
|
|
26
|
+
Requires-Dist: pypdf<7,>=5.1.0
|
|
27
|
+
Requires-Dist: python-docx<2,>=1.1.0
|
|
28
|
+
Requires-Dist: mcp<2,>=1.0.0
|
|
29
|
+
Requires-Dist: python-dotenv<2,>=1.0.0
|
|
30
|
+
Requires-Dist: huggingface-hub<2,>=0.22.0
|
|
31
|
+
Requires-Dist: flashrank<1,>=0.1.0
|
|
32
|
+
Requires-Dist: fastembed<1,>=0.5.0
|
|
33
|
+
Requires-Dist: pyyaml<7,>=6.0
|
|
34
|
+
Provides-Extra: confluence
|
|
35
|
+
Requires-Dist: llama-index-readers-confluence<1,>=0.6.0; extra == "confluence"
|
|
36
|
+
Provides-Extra: test
|
|
37
|
+
Requires-Dist: pytest<9,>=7.4.0; extra == "test"
|
|
38
|
+
Requires-Dist: requests<3,>=2.31.0; extra == "test"
|
|
39
|
+
Dynamic: license-file
|
|
40
|
+
|
|
41
|
+
# ChunkSilo MCP Server
|
|
42
|
+
|
|
43
|
+
ChunkSilo is like a local Google for your documents. It uses semantic search — matching by meaning rather than exact keywords — so your LLM can find relevant information across all your files even when the wording differs from your query. Point it at your PDFs, Word docs, Markdown, and text files, and it builds a fully searchable index locally on your machine.
|
|
44
|
+
|
|
45
|
+
## Overview
|
|
46
|
+
|
|
47
|
+
- **No permissions headache**: Each user indexes only the files they already have access to. No centralized access-control system to build or maintain — document permissions stay exactly where they are.
|
|
48
|
+
- **No infrastructure required**: Runs entirely on the user's own machine as an MCP server. Nothing to deploy, no servers to manage.
|
|
49
|
+
- **Easy to set up**: Any user with an MCP-compatible LLM client can install, point at their document directories, and have everything indexed and searchable.
|
|
50
|
+
- **Works with what you have**: Supports PDF, DOCX, DOC, Markdown, and TXT from local folders, network drives, or shared mounts.
|
|
51
|
+
|
|
52
|
+
## Features
|
|
53
|
+
|
|
54
|
+
- **Local indexing and search**: All indexing and search runs on your machine with bundled models — ChunkSilo itself makes no external network calls when `offline: true`. Note: search results are passed to your MCP client's LLM, which may be cloud-hosted.
|
|
55
|
+
- **Incremental indexing**: Only reindexes new or changed files, so re-runs are fast even on large document collections.
|
|
56
|
+
- **Heading-aware navigation**: Extracts headings from PDFs, Word docs, and Markdown so results include the full heading path (e.g. "Chapter 3 > Setup > Prerequisites").
|
|
57
|
+
- **Date filtering and recency boost**: Search within a date range or let recent documents rank higher automatically.
|
|
58
|
+
- **Dual retrieval**: Returns both meaning-based chunk matches and keyword-based filename matches separately, so file lookups don't get buried by unrelated content.
|
|
59
|
+
- **Multi-directory with per-folder rules**: Index multiple directories with individual include/exclude glob patterns — useful for shared drives with mixed content.
|
|
60
|
+
- **Confluence integration**: Optionally searches your Confluence instance alongside local files, with results returned in the same format.
|
|
61
|
+
- **Source links**: Each result includes a clickable link back to the source file or Confluence page in supported MCP clients.
|
|
62
|
+
|
|
63
|
+
## Installation
|
|
64
|
+
|
|
65
|
+
### Option A: Install from PyPI (Recommended)
|
|
66
|
+
|
|
67
|
+
Requires Python 3.11 or later. Models are downloaded automatically on first run (~250MB). The first run may appear to pause while models download — this is normal.
|
|
68
|
+
|
|
69
|
+
```bash
|
|
70
|
+
pip install chunksilo
|
|
71
|
+
|
|
72
|
+
# Or with Confluence support:
|
|
73
|
+
pip install chunksilo[confluence]
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
Then:
|
|
77
|
+
1. **Create** a config file at `~/.config/chunksilo/config.yaml` (see [Configuration](#configuration))
|
|
78
|
+
2. **Build** the index: `chunksilo --build-index`
|
|
79
|
+
3. **Configure** your MCP client (see [MCP Client Configuration](#mcp-client-configuration))
|
|
80
|
+
|
|
81
|
+
### Option B: Offline Bundle
|
|
82
|
+
|
|
83
|
+
A self-contained package with pre-downloaded models, ideal for air-gapped environments or systems without Python installed.
|
|
84
|
+
|
|
85
|
+
Download from the [Releases page](https://github.com/Chetic/chunksilo/releases):
|
|
86
|
+
|
|
87
|
+
1. **Download** the `chunksilo-vX.Y.Z-manylinux_2_34_x86_64.tar.gz` file
|
|
88
|
+
2. **Extract** and install:
|
|
89
|
+
|
|
90
|
+
```bash
|
|
91
|
+
tar -xzf chunksilo-vX.Y.Z-manylinux_2_34_x86_64.tar.gz
|
|
92
|
+
cd chunksilo
|
|
93
|
+
./setup.sh
|
|
94
|
+
```
|
|
95
|
+
|
|
96
|
+
3. **Edit** `config.yaml` to set your document directories
|
|
97
|
+
4. **Build** the index: `./venv/bin/chunksilo --build-index`
|
|
98
|
+
5. **Configure** your MCP client (see [MCP Client Configuration](#mcp-client-configuration))
|
|
99
|
+
|
|
100
|
+
## Configuration
|
|
101
|
+
|
|
102
|
+
ChunkSilo uses a single configuration file: `config.yaml`
|
|
103
|
+
|
|
104
|
+
### Configuration File
|
|
105
|
+
|
|
106
|
+
Edit `config.yaml` to configure your settings:
|
|
107
|
+
|
|
108
|
+
```yaml
|
|
109
|
+
# Indexing settings - used by chunksilo --build-index
|
|
110
|
+
indexing:
|
|
111
|
+
directories:
|
|
112
|
+
- "./data"
|
|
113
|
+
- "/mnt/nfs/shared-docs"
|
|
114
|
+
- path: "/mnt/samba/engineering"
|
|
115
|
+
include: ["**/*.pdf", "**/*.md"]
|
|
116
|
+
exclude: ["**/archive/**"]
|
|
117
|
+
chunk_size: 1600
|
|
118
|
+
chunk_overlap: 200
|
|
119
|
+
|
|
120
|
+
# Retrieval settings - used when searching
|
|
121
|
+
retrieval:
|
|
122
|
+
embed_top_k: 20
|
|
123
|
+
rerank_top_k: 5
|
|
124
|
+
score_threshold: 0.1
|
|
125
|
+
|
|
126
|
+
# Confluence integration (optional)
|
|
127
|
+
confluence:
|
|
128
|
+
url: "https://confluence.example.com"
|
|
129
|
+
username: "your-username"
|
|
130
|
+
api_token: "your-api-token"
|
|
131
|
+
|
|
132
|
+
# Storage paths (usually don't need to change)
|
|
133
|
+
storage:
|
|
134
|
+
storage_dir: "./storage"
|
|
135
|
+
model_cache_dir: "./models"
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
All settings are optional and have sensible defaults.
|
|
139
|
+
|
|
140
|
+
### Configuration Reference
|
|
141
|
+
|
|
142
|
+
#### Indexing Settings
|
|
143
|
+
|
|
144
|
+
| Setting | Default | Description |
|
|
145
|
+
| :--- | :--- | :--- |
|
|
146
|
+
| `indexing.directories` | `["./data"]` | List of directories to index (strings or objects) |
|
|
147
|
+
| `indexing.chunk_size` | `1600` | Maximum size of text chunks |
|
|
148
|
+
| `indexing.chunk_overlap` | `200` | Overlap between adjacent chunks |
|
|
149
|
+
|
|
150
|
+
**Per-directory options** (when using object format):
|
|
151
|
+
|
|
152
|
+
| Option | Default | Description |
|
|
153
|
+
| :--- | :--- | :--- |
|
|
154
|
+
| `path` | (required) | Directory path to index |
|
|
155
|
+
| `include` | `["**/*.pdf", "**/*.md", "**/*.txt", "**/*.docx", "**/*.doc"]` | Glob patterns for files to include |
|
|
156
|
+
| `exclude` | `[]` | Glob patterns for files to exclude |
|
|
157
|
+
| `recursive` | `true` | Whether to recurse into subdirectories |
|
|
158
|
+
| `enabled` | `true` | Whether to index this directory |
|
|
159
|
+
|
|
160
|
+
#### Retrieval Settings
|
|
161
|
+
|
|
162
|
+
| Setting | Default | Description |
|
|
163
|
+
| :--- | :--- | :--- |
|
|
164
|
+
| `retrieval.embed_model_name` | `BAAI/bge-small-en-v1.5` | Embedding model for vector search |
|
|
165
|
+
| `retrieval.embed_top_k` | `20` | Candidates from vector search before reranking |
|
|
166
|
+
| `retrieval.rerank_model_name` | `ms-marco-MiniLM-L-12-v2` | Reranker model |
|
|
167
|
+
| `retrieval.rerank_top_k` | `5` | Final results after reranking |
|
|
168
|
+
| `retrieval.rerank_candidates` | `100` | Maximum candidates sent to reranker |
|
|
169
|
+
| `retrieval.score_threshold` | `0.1` | Minimum score (0.0-1.0) for results |
|
|
170
|
+
| `retrieval.recency_boost` | `0.3` | Recency boost weight (0.0-1.0) |
|
|
171
|
+
| `retrieval.recency_half_life_days` | `365` | Days until recency boost halves |
|
|
172
|
+
| `retrieval.bm25_similarity_top_k` | `10` | Files returned by BM25 filename search |
|
|
173
|
+
| `retrieval.offline` | `false` | Prevent ML library network requests |
|
|
174
|
+
|
|
175
|
+
#### Confluence Settings (optional)
|
|
176
|
+
|
|
177
|
+
> **Note:** Confluence integration requires the optional dependency. Install with: `pip install chunksilo[confluence]`
|
|
178
|
+
|
|
179
|
+
| Setting | Default | Description |
|
|
180
|
+
| :--- | :--- | :--- |
|
|
181
|
+
| `confluence.url` | `""` | Confluence base URL (empty = disabled) |
|
|
182
|
+
| `confluence.username` | `""` | Confluence username |
|
|
183
|
+
| `confluence.api_token` | `""` | Confluence API token |
|
|
184
|
+
| `confluence.timeout` | `10.0` | Request timeout in seconds |
|
|
185
|
+
| `confluence.max_results` | `30` | Maximum results per search |
|
|
186
|
+
|
|
187
|
+
#### SSL Settings (optional)
|
|
188
|
+
|
|
189
|
+
| Setting | Default | Description |
|
|
190
|
+
| :--- | :--- | :--- |
|
|
191
|
+
| `ssl.ca_bundle_path` | `""` | Path to custom CA bundle file |
|
|
192
|
+
|
|
193
|
+
#### Storage Settings
|
|
194
|
+
|
|
195
|
+
| Setting | Default | Description |
|
|
196
|
+
| :--- | :--- | :--- |
|
|
197
|
+
| `storage.storage_dir` | `./storage` | Directory for vector index and state |
|
|
198
|
+
| `storage.model_cache_dir` | `./models` | Directory for model cache |
|
|
199
|
+
|
|
200
|
+
## CLI Usage
|
|
201
|
+
|
|
202
|
+
The `chunksilo` command provides indexing, searching, and model management:
|
|
203
|
+
|
|
204
|
+
```bash
|
|
205
|
+
# Build or update the search index
|
|
206
|
+
chunksilo --build-index
|
|
207
|
+
|
|
208
|
+
# Search for documents
|
|
209
|
+
chunksilo "your search query"
|
|
210
|
+
|
|
211
|
+
# Search with date filtering
|
|
212
|
+
chunksilo "quarterly report" --date-from 2024-01-01 --date-to 2024-03-31
|
|
213
|
+
|
|
214
|
+
# Output results as JSON
|
|
215
|
+
chunksilo "search query" --json
|
|
216
|
+
|
|
217
|
+
# Show verbose output (model loading, search stats)
|
|
218
|
+
chunksilo "search query" --verbose
|
|
219
|
+
|
|
220
|
+
# Pre-download ML models (useful before going offline)
|
|
221
|
+
chunksilo --download-models
|
|
222
|
+
|
|
223
|
+
# Use a custom config file
|
|
224
|
+
chunksilo --build-index --config /path/to/config.yaml
|
|
225
|
+
```
|
|
226
|
+
|
|
227
|
+
### CLI Options
|
|
228
|
+
|
|
229
|
+
| Option | Description |
|
|
230
|
+
| :--- | :--- |
|
|
231
|
+
| `query` | Search query text (positional argument) |
|
|
232
|
+
| `--build-index` | Build or update the search index, then exit |
|
|
233
|
+
| `--download-models` | Download required ML models, then exit |
|
|
234
|
+
| `--date-from` | Start date filter (YYYY-MM-DD format, inclusive) |
|
|
235
|
+
| `--date-to` | End date filter (YYYY-MM-DD format, inclusive) |
|
|
236
|
+
| `--json` | Output results as JSON instead of formatted text |
|
|
237
|
+
| `-v, --verbose` | Show diagnostic messages (model loading, search stats) |
|
|
238
|
+
| `--config` | Path to config.yaml (overrides auto-discovery) |
|
|
239
|
+
|
|
240
|
+
## MCP Client Configuration
|
|
241
|
+
|
|
242
|
+
Configure your MCP client to run ChunkSilo. Below are examples for common clients.
|
|
243
|
+
|
|
244
|
+
> **Note:** For PyPI installs, use `chunksilo-mcp` directly. For offline bundles, use the full path `/path/to/chunksilo/venv/bin/chunksilo-mcp`. You can find the PyPI-installed binary location with `which chunksilo-mcp`.
|
|
245
|
+
|
|
246
|
+
### Claude Code
|
|
247
|
+
|
|
248
|
+
Add chunksilo as an MCP server using the CLI:
|
|
249
|
+
|
|
250
|
+
**PyPI install:**
|
|
251
|
+
```bash
|
|
252
|
+
claude mcp add chunksilo --scope user -- chunksilo-mcp --config ~/.config/chunksilo/config.yaml
|
|
253
|
+
```
|
|
254
|
+
|
|
255
|
+
**Offline bundle:**
|
|
256
|
+
```bash
|
|
257
|
+
claude mcp add chunksilo --scope user -- /path/to/chunksilo/venv/bin/chunksilo-mcp --config /path/to/chunksilo/config.yaml
|
|
258
|
+
```
|
|
259
|
+
|
|
260
|
+
Verify it's connected:
|
|
261
|
+
|
|
262
|
+
```bash
|
|
263
|
+
claude mcp list
|
|
264
|
+
```
|
|
265
|
+
|
|
266
|
+
### Claude Desktop
|
|
267
|
+
|
|
268
|
+
Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
|
|
269
|
+
|
|
270
|
+
**PyPI install:**
|
|
271
|
+
```json
|
|
272
|
+
{
|
|
273
|
+
"mcpServers": {
|
|
274
|
+
"chunksilo": {
|
|
275
|
+
"command": "chunksilo-mcp",
|
|
276
|
+
"args": ["--config", "/path/to/config.yaml"]
|
|
277
|
+
}
|
|
278
|
+
}
|
|
279
|
+
}
|
|
280
|
+
```
|
|
281
|
+
|
|
282
|
+
**Offline bundle:**
|
|
283
|
+
```json
|
|
284
|
+
{
|
|
285
|
+
"mcpServers": {
|
|
286
|
+
"chunksilo": {
|
|
287
|
+
"command": "/path/to/chunksilo/venv/bin/chunksilo-mcp",
|
|
288
|
+
"args": ["--config", "/path/to/chunksilo/config.yaml"]
|
|
289
|
+
}
|
|
290
|
+
}
|
|
291
|
+
}
|
|
292
|
+
```
|
|
293
|
+
|
|
294
|
+
### Cline (VS Code Extension)
|
|
295
|
+
|
|
296
|
+
Add to `cline_mcp_settings.json` (typically in `~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/`):
|
|
297
|
+
|
|
298
|
+
**PyPI install:**
|
|
299
|
+
```json
|
|
300
|
+
{
|
|
301
|
+
"mcpServers": {
|
|
302
|
+
"chunksilo": {
|
|
303
|
+
"command": "chunksilo-mcp",
|
|
304
|
+
"args": ["--config", "/path/to/config.yaml"],
|
|
305
|
+
"disabled": false,
|
|
306
|
+
"autoApprove": []
|
|
307
|
+
}
|
|
308
|
+
}
|
|
309
|
+
}
|
|
310
|
+
```
|
|
311
|
+
|
|
312
|
+
**Offline bundle:**
|
|
313
|
+
```json
|
|
314
|
+
{
|
|
315
|
+
"mcpServers": {
|
|
316
|
+
"chunksilo": {
|
|
317
|
+
"command": "/path/to/chunksilo/venv/bin/chunksilo-mcp",
|
|
318
|
+
"args": ["--config", "/path/to/chunksilo/config.yaml"],
|
|
319
|
+
"disabled": false,
|
|
320
|
+
"autoApprove": []
|
|
321
|
+
}
|
|
322
|
+
}
|
|
323
|
+
}
|
|
324
|
+
```
|
|
325
|
+
|
|
326
|
+
### Roo Code (VS Code Extension)
|
|
327
|
+
|
|
328
|
+
Add to `mcp_settings.json` (typically in `~/.config/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/`):
|
|
329
|
+
|
|
330
|
+
**PyPI install:**
|
|
331
|
+
```json
|
|
332
|
+
{
|
|
333
|
+
"mcpServers": {
|
|
334
|
+
"chunksilo": {
|
|
335
|
+
"command": "chunksilo-mcp",
|
|
336
|
+
"args": ["--config", "/path/to/config.yaml"]
|
|
337
|
+
}
|
|
338
|
+
}
|
|
339
|
+
}
|
|
340
|
+
```
|
|
341
|
+
|
|
342
|
+
**Offline bundle:**
|
|
343
|
+
```json
|
|
344
|
+
{
|
|
345
|
+
"mcpServers": {
|
|
346
|
+
"chunksilo": {
|
|
347
|
+
"command": "/path/to/chunksilo/venv/bin/chunksilo-mcp",
|
|
348
|
+
"args": ["--config", "/path/to/chunksilo/config.yaml"]
|
|
349
|
+
}
|
|
350
|
+
}
|
|
351
|
+
}
|
|
352
|
+
```
|
|
353
|
+
|
|
354
|
+
## Troubleshooting
|
|
355
|
+
|
|
356
|
+
- **Index missing**: Run `chunksilo --build-index` (PyPI install) or `./venv/bin/chunksilo --build-index` (offline bundle).
|
|
357
|
+
- **Retrieval errors**: Check paths in your MCP client configuration.
|
|
358
|
+
- **Offline mode**: PyPI installs default to `offline: false` (models auto-download). The offline bundle includes pre-downloaded models and sets `offline: true`. Set `retrieval.offline: true` in `config.yaml` to prevent network calls after initial model download.
|
|
359
|
+
- **Confluence Integration**: Install with `pip install chunksilo[confluence]`, then set `confluence.url`, `confluence.username`, and `confluence.api_token` in `config.yaml`.
|
|
360
|
+
- **Custom CA Bundle**: Set `ssl.ca_bundle_path` in `config.yaml` for custom certificates.
|
|
361
|
+
- **Network mounts**: Unavailable directories are skipped with a warning; indexing continues with available directories.
|
|
362
|
+
- **Legacy .doc files**: Requires LibreOffice to be installed for automatic conversion to .docx. If LibreOffice is not found, .doc files are skipped with a warning. Full heading extraction is supported.
|
|
363
|
+
|
|
364
|
+
## License
|
|
365
|
+
|
|
366
|
+
Apache-2.0. See [LICENSE](LICENSE) for details.
|