sqlalchemy-haystack 0.1.0__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.
- sqlalchemy_haystack-0.1.0/.gitignore +146 -0
- sqlalchemy_haystack-0.1.0/CHANGELOG.md +7 -0
- sqlalchemy_haystack-0.1.0/LICENSE.txt +201 -0
- sqlalchemy_haystack-0.1.0/PKG-INFO +106 -0
- sqlalchemy_haystack-0.1.0/README.md +79 -0
- sqlalchemy_haystack-0.1.0/pydoc/config_docusaurus.yml +13 -0
- sqlalchemy_haystack-0.1.0/pyproject.toml +164 -0
- sqlalchemy_haystack-0.1.0/src/haystack_integrations/components/retrievers/py.typed +0 -0
- sqlalchemy_haystack-0.1.0/src/haystack_integrations/components/retrievers/sqlalchemy/__init__.py +7 -0
- sqlalchemy_haystack-0.1.0/src/haystack_integrations/components/retrievers/sqlalchemy/sqlalchemy_table_retriever.py +184 -0
- sqlalchemy_haystack-0.1.0/tests/__init__.py +3 -0
- sqlalchemy_haystack-0.1.0/tests/test_sqlalchemy_table_retriever.py +173 -0
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
# Byte-compiled / optimized / DLL files
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[cod]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# C extensions
|
|
7
|
+
*.so
|
|
8
|
+
|
|
9
|
+
# Distribution / packaging
|
|
10
|
+
.Python
|
|
11
|
+
build/
|
|
12
|
+
develop-eggs/
|
|
13
|
+
dist/
|
|
14
|
+
downloads/
|
|
15
|
+
eggs/
|
|
16
|
+
.eggs/
|
|
17
|
+
lib/
|
|
18
|
+
lib64/
|
|
19
|
+
parts/
|
|
20
|
+
sdist/
|
|
21
|
+
var/
|
|
22
|
+
wheels/
|
|
23
|
+
pip-wheel-metadata/
|
|
24
|
+
share/python-wheels/
|
|
25
|
+
*.egg-info/
|
|
26
|
+
.installed.cfg
|
|
27
|
+
*.egg
|
|
28
|
+
MANIFEST
|
|
29
|
+
|
|
30
|
+
# PyInstaller
|
|
31
|
+
# Usually these files are written by a python script from a template
|
|
32
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
33
|
+
*.manifest
|
|
34
|
+
*.spec
|
|
35
|
+
|
|
36
|
+
# Installer logs
|
|
37
|
+
pip-log.txt
|
|
38
|
+
pip-delete-this-directory.txt
|
|
39
|
+
|
|
40
|
+
# Unit test / coverage reports
|
|
41
|
+
htmlcov/
|
|
42
|
+
.tox/
|
|
43
|
+
.nox/
|
|
44
|
+
.coverage
|
|
45
|
+
.coverage.*
|
|
46
|
+
.cache
|
|
47
|
+
nosetests.xml
|
|
48
|
+
coverage.xml
|
|
49
|
+
*.cover
|
|
50
|
+
*.py,cover
|
|
51
|
+
.hypothesis/
|
|
52
|
+
.pytest_cache/
|
|
53
|
+
volumes/
|
|
54
|
+
|
|
55
|
+
# Translations
|
|
56
|
+
*.mo
|
|
57
|
+
*.pot
|
|
58
|
+
|
|
59
|
+
# Django stuff:
|
|
60
|
+
*.log
|
|
61
|
+
local_settings.py
|
|
62
|
+
db.sqlite3
|
|
63
|
+
db.sqlite3-journal
|
|
64
|
+
|
|
65
|
+
# Flask stuff:
|
|
66
|
+
instance/
|
|
67
|
+
.webassets-cache
|
|
68
|
+
|
|
69
|
+
# Scrapy stuff:
|
|
70
|
+
.scrapy
|
|
71
|
+
|
|
72
|
+
# Sphinx documentation
|
|
73
|
+
docs/_build/
|
|
74
|
+
|
|
75
|
+
# PyBuilder
|
|
76
|
+
target/
|
|
77
|
+
|
|
78
|
+
# Jupyter Notebook
|
|
79
|
+
.ipynb_checkpoints
|
|
80
|
+
|
|
81
|
+
# IPython
|
|
82
|
+
profile_default/
|
|
83
|
+
ipython_config.py
|
|
84
|
+
|
|
85
|
+
# pyenv
|
|
86
|
+
.python-version
|
|
87
|
+
|
|
88
|
+
# pipenv
|
|
89
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
90
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
91
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
92
|
+
# install all needed dependencies.
|
|
93
|
+
#Pipfile.lock
|
|
94
|
+
|
|
95
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow
|
|
96
|
+
__pypackages__/
|
|
97
|
+
|
|
98
|
+
# Celery stuff
|
|
99
|
+
celerybeat-schedule
|
|
100
|
+
celerybeat.pid
|
|
101
|
+
|
|
102
|
+
# SageMath parsed files
|
|
103
|
+
*.sage.py
|
|
104
|
+
|
|
105
|
+
# Environments
|
|
106
|
+
.env
|
|
107
|
+
.venv
|
|
108
|
+
env/
|
|
109
|
+
venv/
|
|
110
|
+
ENV/
|
|
111
|
+
env.bak/
|
|
112
|
+
venv.bak/
|
|
113
|
+
|
|
114
|
+
# Spyder project settings
|
|
115
|
+
.spyderproject
|
|
116
|
+
.spyproject
|
|
117
|
+
|
|
118
|
+
# Rope project settings
|
|
119
|
+
.ropeproject
|
|
120
|
+
|
|
121
|
+
# mkdocs documentation
|
|
122
|
+
/site
|
|
123
|
+
|
|
124
|
+
# mypy
|
|
125
|
+
.mypy_cache/
|
|
126
|
+
.dmypy.json
|
|
127
|
+
dmypy.json
|
|
128
|
+
|
|
129
|
+
# Pyre type checker
|
|
130
|
+
.pyre/
|
|
131
|
+
|
|
132
|
+
# IDEs
|
|
133
|
+
.vscode
|
|
134
|
+
|
|
135
|
+
# Docs generation artifacts
|
|
136
|
+
_readme_*.md
|
|
137
|
+
.idea
|
|
138
|
+
|
|
139
|
+
# macOS
|
|
140
|
+
.DS_Store
|
|
141
|
+
|
|
142
|
+
# http cache (requests-cache)
|
|
143
|
+
**/http_cache.sqlite
|
|
144
|
+
|
|
145
|
+
# ruff
|
|
146
|
+
.ruff_cache
|
|
@@ -0,0 +1,201 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2025 deepset GmbH
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
@@ -0,0 +1,106 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: sqlalchemy-haystack
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: A SQLAlchemy integration for the Haystack framework.
|
|
5
|
+
Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/sqlalchemy#readme
|
|
6
|
+
Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
|
|
7
|
+
Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/sqlalchemy
|
|
8
|
+
Author-email: deepset GmbH <info@deepset.ai>
|
|
9
|
+
License-Expression: Apache-2.0
|
|
10
|
+
License-File: LICENSE.txt
|
|
11
|
+
Classifier: Development Status :: 4 - Beta
|
|
12
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
13
|
+
Classifier: Programming Language :: Python
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
16
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
19
|
+
Classifier: Programming Language :: Python :: Implementation :: CPython
|
|
20
|
+
Classifier: Programming Language :: Python :: Implementation :: PyPy
|
|
21
|
+
Requires-Python: >=3.10
|
|
22
|
+
Requires-Dist: haystack-ai>=2.22.0
|
|
23
|
+
Requires-Dist: pandas>=2.2.3; python_version < '3.11'
|
|
24
|
+
Requires-Dist: pandas>=3.0.0; python_version >= '3.11'
|
|
25
|
+
Requires-Dist: sqlalchemy>=2.0.36
|
|
26
|
+
Description-Content-Type: text/markdown
|
|
27
|
+
|
|
28
|
+
# sqlalchemy-haystack
|
|
29
|
+
|
|
30
|
+
[](https://pypi.org/project/sqlalchemy-haystack)
|
|
31
|
+
[](https://pypi.org/project/sqlalchemy-haystack)
|
|
32
|
+
|
|
33
|
+
- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/sqlalchemy/CHANGELOG.md)
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
A Haystack integration for querying SQL databases via [SQLAlchemy](https://www.sqlalchemy.org/).
|
|
38
|
+
Provides a `SQLAlchemyTableRetriever` component that connects to any SQLAlchemy-supported database,
|
|
39
|
+
executes a SQL query, and returns results as a Pandas DataFrame and an optional Markdown table.
|
|
40
|
+
|
|
41
|
+
## Installation
|
|
42
|
+
|
|
43
|
+
```bash
|
|
44
|
+
pip install sqlalchemy-haystack
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
You also need to install the appropriate database driver for your backend:
|
|
48
|
+
|
|
49
|
+
| Backend | Driver package |
|
|
50
|
+
|---------|---------------|
|
|
51
|
+
| PostgreSQL | `psycopg2-binary` or `psycopg[binary]` |
|
|
52
|
+
| MySQL / MariaDB | `pymysql` or `mysqlclient` |
|
|
53
|
+
| SQLite | built-in (no extra package needed) |
|
|
54
|
+
| MSSQL | `pyodbc` |
|
|
55
|
+
| Oracle | `cx_oracle` or `oracledb` |
|
|
56
|
+
|
|
57
|
+
## Usage
|
|
58
|
+
|
|
59
|
+
```python
|
|
60
|
+
from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
|
|
61
|
+
|
|
62
|
+
# SQLite in-memory example (no driver needed)
|
|
63
|
+
retriever = SQLAlchemyTableRetriever(
|
|
64
|
+
drivername="sqlite",
|
|
65
|
+
database=":memory:",
|
|
66
|
+
init_script=[
|
|
67
|
+
"CREATE TABLE products (id INTEGER, name TEXT, price REAL)",
|
|
68
|
+
"INSERT INTO products VALUES (1, 'Widget', 9.99)",
|
|
69
|
+
"INSERT INTO products VALUES (2, 'Gadget', 19.99)",
|
|
70
|
+
],
|
|
71
|
+
)
|
|
72
|
+
retriever.warm_up()
|
|
73
|
+
|
|
74
|
+
result = retriever.run(query="SELECT * FROM products WHERE price < 15")
|
|
75
|
+
print(result["dataframe"])
|
|
76
|
+
print(result["table"])
|
|
77
|
+
```
|
|
78
|
+
|
|
79
|
+
For PostgreSQL:
|
|
80
|
+
|
|
81
|
+
```python
|
|
82
|
+
from haystack.utils import Secret
|
|
83
|
+
|
|
84
|
+
retriever = SQLAlchemyTableRetriever(
|
|
85
|
+
drivername="postgresql+psycopg2",
|
|
86
|
+
host="localhost",
|
|
87
|
+
port=5432,
|
|
88
|
+
database="mydb",
|
|
89
|
+
username="myuser",
|
|
90
|
+
password=Secret.from_env_var("DB_PASSWORD"),
|
|
91
|
+
)
|
|
92
|
+
```
|
|
93
|
+
|
|
94
|
+
## Security
|
|
95
|
+
|
|
96
|
+
This component executes raw SQL queries passed at runtime. Keep the following in mind:
|
|
97
|
+
|
|
98
|
+
- **Never pass unsanitised user input** directly as a query — this exposes you to SQL injection.
|
|
99
|
+
- **Use a read-only database user.** This is the most effective mitigation. Even if a malicious
|
|
100
|
+
query is executed, a read-only user cannot modify or delete data.
|
|
101
|
+
- **Restrict database permissions** to the minimum required — specific tables and schemas only,
|
|
102
|
+
no DDL privileges (no `CREATE`, `DROP`, `ALTER`).
|
|
103
|
+
|
|
104
|
+
## Contributing
|
|
105
|
+
|
|
106
|
+
Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
|
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
# sqlalchemy-haystack
|
|
2
|
+
|
|
3
|
+
[](https://pypi.org/project/sqlalchemy-haystack)
|
|
4
|
+
[](https://pypi.org/project/sqlalchemy-haystack)
|
|
5
|
+
|
|
6
|
+
- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/sqlalchemy/CHANGELOG.md)
|
|
7
|
+
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
A Haystack integration for querying SQL databases via [SQLAlchemy](https://www.sqlalchemy.org/).
|
|
11
|
+
Provides a `SQLAlchemyTableRetriever` component that connects to any SQLAlchemy-supported database,
|
|
12
|
+
executes a SQL query, and returns results as a Pandas DataFrame and an optional Markdown table.
|
|
13
|
+
|
|
14
|
+
## Installation
|
|
15
|
+
|
|
16
|
+
```bash
|
|
17
|
+
pip install sqlalchemy-haystack
|
|
18
|
+
```
|
|
19
|
+
|
|
20
|
+
You also need to install the appropriate database driver for your backend:
|
|
21
|
+
|
|
22
|
+
| Backend | Driver package |
|
|
23
|
+
|---------|---------------|
|
|
24
|
+
| PostgreSQL | `psycopg2-binary` or `psycopg[binary]` |
|
|
25
|
+
| MySQL / MariaDB | `pymysql` or `mysqlclient` |
|
|
26
|
+
| SQLite | built-in (no extra package needed) |
|
|
27
|
+
| MSSQL | `pyodbc` |
|
|
28
|
+
| Oracle | `cx_oracle` or `oracledb` |
|
|
29
|
+
|
|
30
|
+
## Usage
|
|
31
|
+
|
|
32
|
+
```python
|
|
33
|
+
from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
|
|
34
|
+
|
|
35
|
+
# SQLite in-memory example (no driver needed)
|
|
36
|
+
retriever = SQLAlchemyTableRetriever(
|
|
37
|
+
drivername="sqlite",
|
|
38
|
+
database=":memory:",
|
|
39
|
+
init_script=[
|
|
40
|
+
"CREATE TABLE products (id INTEGER, name TEXT, price REAL)",
|
|
41
|
+
"INSERT INTO products VALUES (1, 'Widget', 9.99)",
|
|
42
|
+
"INSERT INTO products VALUES (2, 'Gadget', 19.99)",
|
|
43
|
+
],
|
|
44
|
+
)
|
|
45
|
+
retriever.warm_up()
|
|
46
|
+
|
|
47
|
+
result = retriever.run(query="SELECT * FROM products WHERE price < 15")
|
|
48
|
+
print(result["dataframe"])
|
|
49
|
+
print(result["table"])
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
For PostgreSQL:
|
|
53
|
+
|
|
54
|
+
```python
|
|
55
|
+
from haystack.utils import Secret
|
|
56
|
+
|
|
57
|
+
retriever = SQLAlchemyTableRetriever(
|
|
58
|
+
drivername="postgresql+psycopg2",
|
|
59
|
+
host="localhost",
|
|
60
|
+
port=5432,
|
|
61
|
+
database="mydb",
|
|
62
|
+
username="myuser",
|
|
63
|
+
password=Secret.from_env_var("DB_PASSWORD"),
|
|
64
|
+
)
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
## Security
|
|
68
|
+
|
|
69
|
+
This component executes raw SQL queries passed at runtime. Keep the following in mind:
|
|
70
|
+
|
|
71
|
+
- **Never pass unsanitised user input** directly as a query — this exposes you to SQL injection.
|
|
72
|
+
- **Use a read-only database user.** This is the most effective mitigation. Even if a malicious
|
|
73
|
+
query is executed, a read-only user cannot modify or delete data.
|
|
74
|
+
- **Restrict database permissions** to the minimum required — specific tables and schemas only,
|
|
75
|
+
no DDL privileges (no `CREATE`, `DROP`, `ALTER`).
|
|
76
|
+
|
|
77
|
+
## Contributing
|
|
78
|
+
|
|
79
|
+
Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
|
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
loaders:
|
|
2
|
+
- modules:
|
|
3
|
+
- haystack_integrations.components.retrievers.sqlalchemy.sqlalchemy_table_retriever
|
|
4
|
+
search_path: [../src]
|
|
5
|
+
processors:
|
|
6
|
+
- type: filter
|
|
7
|
+
documented_only: true
|
|
8
|
+
skip_empty_modules: true
|
|
9
|
+
renderer:
|
|
10
|
+
description: SQLAlchemy integration for Haystack
|
|
11
|
+
id: integrations-sqlalchemy
|
|
12
|
+
filename: sqlalchemy.md
|
|
13
|
+
title: SQLAlchemy
|
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
[build-system]
|
|
2
|
+
requires = ["hatchling", "hatch-vcs"]
|
|
3
|
+
build-backend = "hatchling.build"
|
|
4
|
+
|
|
5
|
+
[project]
|
|
6
|
+
name = "sqlalchemy-haystack"
|
|
7
|
+
dynamic = ["version"]
|
|
8
|
+
description = 'A SQLAlchemy integration for the Haystack framework.'
|
|
9
|
+
readme = "README.md"
|
|
10
|
+
requires-python = ">=3.10"
|
|
11
|
+
license = "Apache-2.0"
|
|
12
|
+
keywords = []
|
|
13
|
+
authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
|
|
14
|
+
classifiers = [
|
|
15
|
+
"License :: OSI Approved :: Apache Software License",
|
|
16
|
+
"Development Status :: 4 - Beta",
|
|
17
|
+
"Programming Language :: Python",
|
|
18
|
+
"Programming Language :: Python :: 3.10",
|
|
19
|
+
"Programming Language :: Python :: 3.11",
|
|
20
|
+
"Programming Language :: Python :: 3.12",
|
|
21
|
+
"Programming Language :: Python :: 3.13",
|
|
22
|
+
"Programming Language :: Python :: 3.14",
|
|
23
|
+
"Programming Language :: Python :: Implementation :: CPython",
|
|
24
|
+
"Programming Language :: Python :: Implementation :: PyPy",
|
|
25
|
+
]
|
|
26
|
+
dependencies = [
|
|
27
|
+
"haystack-ai>=2.22.0",
|
|
28
|
+
"sqlalchemy>=2.0.36",
|
|
29
|
+
"pandas>=2.2.3; python_version < '3.11'",
|
|
30
|
+
"pandas>=3.0.0; python_version >= '3.11'",
|
|
31
|
+
]
|
|
32
|
+
|
|
33
|
+
[project.urls]
|
|
34
|
+
Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/sqlalchemy#readme"
|
|
35
|
+
Issues = "https://github.com/deepset-ai/haystack-core-integrations/issues"
|
|
36
|
+
Source = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/sqlalchemy"
|
|
37
|
+
|
|
38
|
+
[tool.hatch.build.targets.wheel]
|
|
39
|
+
packages = ["src/haystack_integrations"]
|
|
40
|
+
|
|
41
|
+
[tool.hatch.version]
|
|
42
|
+
source = "vcs"
|
|
43
|
+
tag-pattern = 'integrations\/sqlalchemy-v(?P<version>.*)'
|
|
44
|
+
|
|
45
|
+
[tool.hatch.version.raw-options]
|
|
46
|
+
root = "../.."
|
|
47
|
+
git_describe_command = 'git describe --tags --match="integrations/sqlalchemy-v[0-9]*"'
|
|
48
|
+
|
|
49
|
+
[tool.hatch.envs.default]
|
|
50
|
+
installer = "uv"
|
|
51
|
+
dependencies = ["haystack-pydoc-tools", "ruff"]
|
|
52
|
+
|
|
53
|
+
[tool.hatch.envs.default.scripts]
|
|
54
|
+
docs = ["haystack-pydoc pydoc/config_docusaurus.yml"]
|
|
55
|
+
fmt = "ruff check --fix {args}; ruff format {args}"
|
|
56
|
+
fmt-check = "ruff check {args} && ruff format --check {args}"
|
|
57
|
+
|
|
58
|
+
[tool.hatch.envs.test]
|
|
59
|
+
dependencies = [
|
|
60
|
+
"pytest",
|
|
61
|
+
"pytest-asyncio",
|
|
62
|
+
"pytest-cov",
|
|
63
|
+
"pytest-rerunfailures",
|
|
64
|
+
"mypy",
|
|
65
|
+
"pip",
|
|
66
|
+
"pandas-stubs",
|
|
67
|
+
]
|
|
68
|
+
|
|
69
|
+
[tool.hatch.envs.test.scripts]
|
|
70
|
+
unit = 'pytest -m "not integration" {args:tests}'
|
|
71
|
+
integration = 'pytest -m "integration" {args:tests}'
|
|
72
|
+
all = 'pytest {args:tests}'
|
|
73
|
+
unit-cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x -m "not integration" {args:tests}'
|
|
74
|
+
integration-cov-append-retry = 'pytest --cov=haystack_integrations --cov-append --reruns 3 --reruns-delay 30 -x -m "integration" {args:tests}'
|
|
75
|
+
|
|
76
|
+
types = "mypy -p haystack_integrations.components.retrievers.sqlalchemy {args}"
|
|
77
|
+
|
|
78
|
+
[tool.mypy]
|
|
79
|
+
install_types = true
|
|
80
|
+
non_interactive = true
|
|
81
|
+
check_untyped_defs = true
|
|
82
|
+
disallow_incomplete_defs = true
|
|
83
|
+
|
|
84
|
+
[tool.ruff]
|
|
85
|
+
line-length = 120
|
|
86
|
+
|
|
87
|
+
[tool.ruff.lint]
|
|
88
|
+
select = [
|
|
89
|
+
"A",
|
|
90
|
+
"ANN",
|
|
91
|
+
"ARG",
|
|
92
|
+
"B",
|
|
93
|
+
"C",
|
|
94
|
+
"D102",
|
|
95
|
+
"D103",
|
|
96
|
+
"D205",
|
|
97
|
+
"D209",
|
|
98
|
+
"D213",
|
|
99
|
+
"D417",
|
|
100
|
+
"D419",
|
|
101
|
+
"DTZ",
|
|
102
|
+
"E",
|
|
103
|
+
"EM",
|
|
104
|
+
"F",
|
|
105
|
+
"FBT",
|
|
106
|
+
"I",
|
|
107
|
+
"ICN",
|
|
108
|
+
"ISC",
|
|
109
|
+
"N",
|
|
110
|
+
"PLC",
|
|
111
|
+
"PLE",
|
|
112
|
+
"PLR",
|
|
113
|
+
"PLW",
|
|
114
|
+
"Q",
|
|
115
|
+
"RUF",
|
|
116
|
+
"S",
|
|
117
|
+
"T",
|
|
118
|
+
"TID",
|
|
119
|
+
"UP",
|
|
120
|
+
"W",
|
|
121
|
+
"YTT",
|
|
122
|
+
]
|
|
123
|
+
ignore = [
|
|
124
|
+
# Allow non-abstract empty methods in abstract base classes
|
|
125
|
+
"B027",
|
|
126
|
+
# Allow Any in type annotations at dynamic boundaries
|
|
127
|
+
"ANN401",
|
|
128
|
+
# Allow boolean positional values in function calls, like `dict.get(... True)`
|
|
129
|
+
"FBT003",
|
|
130
|
+
# Ignore checks for possible passwords
|
|
131
|
+
"S105",
|
|
132
|
+
"S106",
|
|
133
|
+
"S107",
|
|
134
|
+
# Ignore complexity
|
|
135
|
+
"C901",
|
|
136
|
+
"PLR0911",
|
|
137
|
+
"PLR0912",
|
|
138
|
+
"PLR0913",
|
|
139
|
+
"PLR0915",
|
|
140
|
+
# Ignore SQL injection warning (user-provided queries are expected)
|
|
141
|
+
"S608",
|
|
142
|
+
# Unused method argument
|
|
143
|
+
"ARG002",
|
|
144
|
+
]
|
|
145
|
+
|
|
146
|
+
[tool.ruff.lint.isort]
|
|
147
|
+
known-first-party = ["haystack_integrations"]
|
|
148
|
+
|
|
149
|
+
[tool.ruff.lint.flake8-tidy-imports]
|
|
150
|
+
ban-relative-imports = "parents"
|
|
151
|
+
|
|
152
|
+
[tool.ruff.lint.per-file-ignores]
|
|
153
|
+
"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
|
|
154
|
+
|
|
155
|
+
[tool.coverage.run]
|
|
156
|
+
source = ["haystack_integrations"]
|
|
157
|
+
branch = true
|
|
158
|
+
relative_files = true
|
|
159
|
+
parallel = false
|
|
160
|
+
|
|
161
|
+
[tool.coverage.report]
|
|
162
|
+
omit = ["*/tests/*", "*/__init__.py"]
|
|
163
|
+
show_missing = true
|
|
164
|
+
exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
|
|
File without changes
|
|
@@ -0,0 +1,184 @@
|
|
|
1
|
+
# SPDX-FileCopyrightText: 2025-present deepset GmbH <info@deepset.ai>
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
|
|
5
|
+
from typing import Any
|
|
6
|
+
|
|
7
|
+
from haystack import component, default_from_dict, default_to_dict, logging
|
|
8
|
+
from haystack.utils import Secret, deserialize_secrets_inplace
|
|
9
|
+
from pandas import DataFrame
|
|
10
|
+
|
|
11
|
+
from sqlalchemy import create_engine, text
|
|
12
|
+
from sqlalchemy.engine import URL, Engine
|
|
13
|
+
from sqlalchemy.exc import SQLAlchemyError
|
|
14
|
+
from sqlalchemy.pool import StaticPool
|
|
15
|
+
|
|
16
|
+
logger = logging.getLogger(__name__)
|
|
17
|
+
|
|
18
|
+
MAX_SYS_ROWS = 10_000
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
@component
|
|
22
|
+
class SQLAlchemyTableRetriever:
|
|
23
|
+
"""
|
|
24
|
+
Connects to any SQLAlchemy-supported database and executes a SQL query.
|
|
25
|
+
|
|
26
|
+
Returns results as a Pandas DataFrame and an optional Markdown-formatted table string.
|
|
27
|
+
Supports any database backend that SQLAlchemy supports, including PostgreSQL, MySQL,
|
|
28
|
+
SQLite, and MSSQL.
|
|
29
|
+
|
|
30
|
+
### Usage example:
|
|
31
|
+
|
|
32
|
+
```python
|
|
33
|
+
from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
|
|
34
|
+
|
|
35
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
36
|
+
retriever.warm_up()
|
|
37
|
+
result = retriever.run(query="SELECT 1 AS value")
|
|
38
|
+
print(result["dataframe"])
|
|
39
|
+
print(result["table"])
|
|
40
|
+
```
|
|
41
|
+
"""
|
|
42
|
+
|
|
43
|
+
def __init__(
|
|
44
|
+
self,
|
|
45
|
+
drivername: str,
|
|
46
|
+
username: str | None = None,
|
|
47
|
+
password: Secret | None = None,
|
|
48
|
+
host: str | None = None,
|
|
49
|
+
port: int | None = None,
|
|
50
|
+
database: str | None = None,
|
|
51
|
+
init_script: list[str] | None = None,
|
|
52
|
+
) -> None:
|
|
53
|
+
"""
|
|
54
|
+
Initialize SQLAlchemyTableRetriever.
|
|
55
|
+
|
|
56
|
+
:param drivername: The SQLAlchemy driver name (e.g., ``"sqlite"``,
|
|
57
|
+
``"postgresql+psycopg2"``).
|
|
58
|
+
:param username: Database username.
|
|
59
|
+
:param password: Database password as a Haystack ``Secret``.
|
|
60
|
+
:param host: Database host.
|
|
61
|
+
:param port: Database port.
|
|
62
|
+
:param database: Database name or path (e.g., ``":memory:"`` for SQLite in-memory).
|
|
63
|
+
:param init_script: Optional list of SQL statements executed once on ``warm_up()``
|
|
64
|
+
(e.g., to create tables or insert seed data). Each statement should be a
|
|
65
|
+
separate string in the list.
|
|
66
|
+
"""
|
|
67
|
+
self.drivername = drivername
|
|
68
|
+
self.username = username
|
|
69
|
+
self.password = password
|
|
70
|
+
self.host = host
|
|
71
|
+
self.port = port
|
|
72
|
+
self.database = database
|
|
73
|
+
self.init_script = init_script
|
|
74
|
+
self._engine: Engine | None = None
|
|
75
|
+
self._warmed_up = False
|
|
76
|
+
|
|
77
|
+
def warm_up(self) -> None:
|
|
78
|
+
"""
|
|
79
|
+
Initialize the database engine and execute ``init_script`` if provided.
|
|
80
|
+
|
|
81
|
+
Called automatically by ``run()`` on first invocation if not already warmed up.
|
|
82
|
+
"""
|
|
83
|
+
if self._warmed_up:
|
|
84
|
+
return
|
|
85
|
+
|
|
86
|
+
url = URL.create(
|
|
87
|
+
drivername=self.drivername,
|
|
88
|
+
username=self.username,
|
|
89
|
+
password=self.password.resolve_value() if self.password else None,
|
|
90
|
+
host=self.host,
|
|
91
|
+
port=self.port,
|
|
92
|
+
database=self.database,
|
|
93
|
+
)
|
|
94
|
+
|
|
95
|
+
engine_kwargs: dict[str, Any] = {}
|
|
96
|
+
if url.drivername.startswith("sqlite") and url.database in (":memory:", "", None):
|
|
97
|
+
engine_kwargs["connect_args"] = {"check_same_thread": False}
|
|
98
|
+
engine_kwargs["poolclass"] = StaticPool
|
|
99
|
+
|
|
100
|
+
self._engine = create_engine(url, **engine_kwargs)
|
|
101
|
+
|
|
102
|
+
if self.init_script:
|
|
103
|
+
with self._engine.connect() as conn:
|
|
104
|
+
for stmt in self.init_script:
|
|
105
|
+
stripped = stmt.strip()
|
|
106
|
+
if stripped:
|
|
107
|
+
conn.execute(text(stripped))
|
|
108
|
+
conn.commit()
|
|
109
|
+
|
|
110
|
+
self._warmed_up = True
|
|
111
|
+
|
|
112
|
+
def to_dict(self) -> dict[str, Any]:
|
|
113
|
+
"""
|
|
114
|
+
Serialize the component to a dictionary.
|
|
115
|
+
|
|
116
|
+
:returns: Dictionary with serialized data.
|
|
117
|
+
"""
|
|
118
|
+
return default_to_dict(
|
|
119
|
+
self,
|
|
120
|
+
drivername=self.drivername,
|
|
121
|
+
username=self.username,
|
|
122
|
+
password=self.password.to_dict() if self.password else None,
|
|
123
|
+
host=self.host,
|
|
124
|
+
port=self.port,
|
|
125
|
+
database=self.database,
|
|
126
|
+
init_script=self.init_script,
|
|
127
|
+
)
|
|
128
|
+
|
|
129
|
+
@classmethod
|
|
130
|
+
def from_dict(cls, data: dict[str, Any]) -> "SQLAlchemyTableRetriever":
|
|
131
|
+
"""
|
|
132
|
+
Deserialize the component from a dictionary.
|
|
133
|
+
|
|
134
|
+
:param data: Dictionary to deserialize from.
|
|
135
|
+
:returns: Deserialized component.
|
|
136
|
+
"""
|
|
137
|
+
deserialize_secrets_inplace(data.get("init_parameters", {}), ["password"])
|
|
138
|
+
return default_from_dict(cls, data)
|
|
139
|
+
|
|
140
|
+
@staticmethod
|
|
141
|
+
def _df_to_markdown(df: DataFrame) -> str:
|
|
142
|
+
if df.empty:
|
|
143
|
+
return ""
|
|
144
|
+
header = "| " + " | ".join(str(c) for c in df.columns) + " |"
|
|
145
|
+
separator = "| " + " | ".join("---" for _ in df.columns) + " |"
|
|
146
|
+
rows = ["| " + " | ".join(str(v) for v in row) + " |" for row in df.itertuples(index=False)]
|
|
147
|
+
return "\n".join([header, separator, *rows])
|
|
148
|
+
|
|
149
|
+
@component.output_types(dataframe=DataFrame, table=str, error=str)
|
|
150
|
+
def run(self, query: str) -> dict[str, Any]:
|
|
151
|
+
"""
|
|
152
|
+
Execute a SQL query and return the results.
|
|
153
|
+
|
|
154
|
+
:param query: The SQL query to execute.
|
|
155
|
+
:returns: A dictionary with:
|
|
156
|
+
|
|
157
|
+
- ``dataframe``: A Pandas DataFrame with the query results.
|
|
158
|
+
- ``table``: A Markdown-formatted string of the results.
|
|
159
|
+
- ``error``: An error message if the query failed, otherwise an empty string.
|
|
160
|
+
"""
|
|
161
|
+
if not isinstance(query, str):
|
|
162
|
+
logger.warning("Query is not a string, returning empty DataFrame")
|
|
163
|
+
return {"dataframe": DataFrame(), "table": "", "error": "query is not a string"}
|
|
164
|
+
|
|
165
|
+
if not query.strip():
|
|
166
|
+
return {"dataframe": DataFrame(), "table": "", "error": "empty query"}
|
|
167
|
+
|
|
168
|
+
if not self._warmed_up:
|
|
169
|
+
self.warm_up()
|
|
170
|
+
|
|
171
|
+
if self._engine is None: # pragma: no cover
|
|
172
|
+
msg = "Engine is not initialized."
|
|
173
|
+
raise RuntimeError(msg)
|
|
174
|
+
|
|
175
|
+
try:
|
|
176
|
+
with self._engine.connect() as conn:
|
|
177
|
+
result = conn.execute(text(query))
|
|
178
|
+
rows = result.fetchmany(MAX_SYS_ROWS)
|
|
179
|
+
columns = list(result.keys())
|
|
180
|
+
df = DataFrame(rows, columns=columns)
|
|
181
|
+
return {"dataframe": df, "table": self._df_to_markdown(df), "error": ""}
|
|
182
|
+
except SQLAlchemyError as e:
|
|
183
|
+
logger.warning("Error executing query: {error}", error=str(e))
|
|
184
|
+
return {"dataframe": DataFrame(), "table": "", "error": str(e)}
|
|
@@ -0,0 +1,173 @@
|
|
|
1
|
+
# SPDX-FileCopyrightText: 2025-present deepset GmbH <info@deepset.ai>
|
|
2
|
+
#
|
|
3
|
+
# SPDX-License-Identifier: Apache-2.0
|
|
4
|
+
|
|
5
|
+
import pytest
|
|
6
|
+
from haystack.utils import Secret
|
|
7
|
+
|
|
8
|
+
import haystack_integrations.components.retrievers.sqlalchemy.sqlalchemy_table_retriever as module
|
|
9
|
+
from haystack_integrations.components.retrievers.sqlalchemy import SQLAlchemyTableRetriever
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
class TestSQLAlchemyTableRetrieverInit:
|
|
13
|
+
def test_init_defaults(self):
|
|
14
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite")
|
|
15
|
+
assert retriever.drivername == "sqlite"
|
|
16
|
+
assert retriever.username is None
|
|
17
|
+
assert retriever.password is None
|
|
18
|
+
assert retriever.host is None
|
|
19
|
+
assert retriever.port is None
|
|
20
|
+
assert retriever.database is None
|
|
21
|
+
assert retriever.init_script is None
|
|
22
|
+
|
|
23
|
+
def test_init_all_params(self):
|
|
24
|
+
password = Secret.from_token("secret")
|
|
25
|
+
retriever = SQLAlchemyTableRetriever(
|
|
26
|
+
drivername="postgresql+psycopg2",
|
|
27
|
+
username="user",
|
|
28
|
+
password=password,
|
|
29
|
+
host="localhost",
|
|
30
|
+
port=5432,
|
|
31
|
+
database="mydb",
|
|
32
|
+
init_script=["CREATE TABLE t (x INTEGER)"],
|
|
33
|
+
)
|
|
34
|
+
assert retriever.drivername == "postgresql+psycopg2"
|
|
35
|
+
assert retriever.username == "user"
|
|
36
|
+
assert retriever.password is password
|
|
37
|
+
assert retriever.host == "localhost"
|
|
38
|
+
assert retriever.port == 5432
|
|
39
|
+
assert retriever.database == "mydb"
|
|
40
|
+
assert retriever.init_script == ["CREATE TABLE t (x INTEGER)"]
|
|
41
|
+
|
|
42
|
+
|
|
43
|
+
class TestSQLAlchemyTableRetrieverSerialization:
|
|
44
|
+
def test_to_dict(self):
|
|
45
|
+
password = Secret.from_env_var("DB_PASSWORD")
|
|
46
|
+
init_script = ["CREATE TABLE t (x INTEGER)", "INSERT INTO t VALUES (1)"]
|
|
47
|
+
retriever = SQLAlchemyTableRetriever(
|
|
48
|
+
drivername="sqlite",
|
|
49
|
+
database=":memory:",
|
|
50
|
+
password=password,
|
|
51
|
+
init_script=init_script,
|
|
52
|
+
)
|
|
53
|
+
d = retriever.to_dict()
|
|
54
|
+
expected_type = (
|
|
55
|
+
"haystack_integrations.components.retrievers.sqlalchemy.sqlalchemy_table_retriever.SQLAlchemyTableRetriever"
|
|
56
|
+
)
|
|
57
|
+
assert d["type"] == expected_type
|
|
58
|
+
params = d["init_parameters"]
|
|
59
|
+
assert params["drivername"] == "sqlite"
|
|
60
|
+
assert params["database"] == ":memory:"
|
|
61
|
+
assert params["password"]["type"] == "env_var"
|
|
62
|
+
assert params["init_script"] == init_script
|
|
63
|
+
|
|
64
|
+
def test_from_dict(self, monkeypatch):
|
|
65
|
+
monkeypatch.setenv("DB_PASSWORD", "secret")
|
|
66
|
+
password = Secret.from_env_var("DB_PASSWORD")
|
|
67
|
+
init_script = ["CREATE TABLE t (x INTEGER)", "INSERT INTO t VALUES (1)"]
|
|
68
|
+
retriever = SQLAlchemyTableRetriever(
|
|
69
|
+
drivername="sqlite",
|
|
70
|
+
database=":memory:",
|
|
71
|
+
password=password,
|
|
72
|
+
init_script=init_script,
|
|
73
|
+
)
|
|
74
|
+
d = retriever.to_dict()
|
|
75
|
+
restored = SQLAlchemyTableRetriever.from_dict(d)
|
|
76
|
+
assert restored.drivername == "sqlite"
|
|
77
|
+
assert restored.database == ":memory:"
|
|
78
|
+
assert restored.password is not None
|
|
79
|
+
assert restored.password.resolve_value() == "secret"
|
|
80
|
+
assert restored.init_script == init_script
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
class TestSQLAlchemyTableRetrieverRun:
|
|
84
|
+
@pytest.fixture()
|
|
85
|
+
def retriever_with_data(self):
|
|
86
|
+
init_sql = [
|
|
87
|
+
"CREATE TABLE employees (id INTEGER PRIMARY KEY, name TEXT NOT NULL,"
|
|
88
|
+
" department TEXT NOT NULL, salary INTEGER NOT NULL)",
|
|
89
|
+
"INSERT INTO employees VALUES (1, 'Alice', 'Engineering', 95000)",
|
|
90
|
+
"INSERT INTO employees VALUES (2, 'Bob', 'Marketing', 72000)",
|
|
91
|
+
"INSERT INTO employees VALUES (3, 'Carol', 'Engineering', 88000)",
|
|
92
|
+
]
|
|
93
|
+
retriever = SQLAlchemyTableRetriever(
|
|
94
|
+
drivername="sqlite",
|
|
95
|
+
database=":memory:",
|
|
96
|
+
init_script=init_sql,
|
|
97
|
+
)
|
|
98
|
+
retriever.warm_up()
|
|
99
|
+
return retriever
|
|
100
|
+
|
|
101
|
+
def test_run_non_string_query(self):
|
|
102
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
103
|
+
result = retriever.run(query=123) # type: ignore[arg-type]
|
|
104
|
+
assert result["error"] == "query is not a string"
|
|
105
|
+
assert result["dataframe"].empty
|
|
106
|
+
assert result["table"] == ""
|
|
107
|
+
|
|
108
|
+
@pytest.mark.parametrize("query", ["", " ", "\t", "\n"])
|
|
109
|
+
def test_run_empty_query(self, query):
|
|
110
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
111
|
+
result = retriever.run(query=query)
|
|
112
|
+
assert result["error"] == "empty query"
|
|
113
|
+
assert result["dataframe"].empty
|
|
114
|
+
assert result["table"] == ""
|
|
115
|
+
|
|
116
|
+
def test_run_returns_dataframe(self, retriever_with_data):
|
|
117
|
+
result = retriever_with_data.run(query="SELECT * FROM employees ORDER BY id")
|
|
118
|
+
df = result["dataframe"]
|
|
119
|
+
assert result["error"] == ""
|
|
120
|
+
assert list(df.columns) == ["id", "name", "department", "salary"]
|
|
121
|
+
assert len(df) == 3
|
|
122
|
+
assert df.iloc[0]["name"] == "Alice"
|
|
123
|
+
assert df.iloc[1]["department"] == "Marketing"
|
|
124
|
+
assert df.iloc[2]["salary"] == 88000
|
|
125
|
+
|
|
126
|
+
def test_run_returns_markdown(self, retriever_with_data):
|
|
127
|
+
result = retriever_with_data.run(query="SELECT * FROM employees ORDER BY id")
|
|
128
|
+
expected = (
|
|
129
|
+
"| id | name | department | salary |\n"
|
|
130
|
+
"| --- | --- | --- | --- |\n"
|
|
131
|
+
"| 1 | Alice | Engineering | 95000 |\n"
|
|
132
|
+
"| 2 | Bob | Marketing | 72000 |\n"
|
|
133
|
+
"| 3 | Carol | Engineering | 88000 |"
|
|
134
|
+
)
|
|
135
|
+
assert result["table"] == expected
|
|
136
|
+
|
|
137
|
+
def test_run_sql_error(self):
|
|
138
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
139
|
+
retriever.warm_up()
|
|
140
|
+
result = retriever.run(query="SELECT * FROM nonexistent_table_xyz")
|
|
141
|
+
assert result["error"] != ""
|
|
142
|
+
assert result["dataframe"].empty
|
|
143
|
+
|
|
144
|
+
def test_max_row_limit(self, monkeypatch):
|
|
145
|
+
init_sql = [
|
|
146
|
+
"CREATE TABLE t (x INTEGER)",
|
|
147
|
+
"INSERT INTO t VALUES (1)",
|
|
148
|
+
"INSERT INTO t VALUES (2)",
|
|
149
|
+
"INSERT INTO t VALUES (3)",
|
|
150
|
+
]
|
|
151
|
+
retriever = SQLAlchemyTableRetriever(
|
|
152
|
+
drivername="sqlite",
|
|
153
|
+
database=":memory:",
|
|
154
|
+
init_script=init_sql,
|
|
155
|
+
)
|
|
156
|
+
monkeypatch.setattr(module, "MAX_SYS_ROWS", 2)
|
|
157
|
+
retriever.warm_up()
|
|
158
|
+
result = retriever.run(query="SELECT * FROM t")
|
|
159
|
+
assert len(result["dataframe"]) == 2
|
|
160
|
+
|
|
161
|
+
def test_warm_up_idempotent(self):
|
|
162
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
163
|
+
retriever.warm_up()
|
|
164
|
+
engine = retriever._engine
|
|
165
|
+
retriever.warm_up()
|
|
166
|
+
assert retriever._engine is engine
|
|
167
|
+
|
|
168
|
+
def test_run_calls_warm_up_automatically(self):
|
|
169
|
+
retriever = SQLAlchemyTableRetriever(drivername="sqlite", database=":memory:")
|
|
170
|
+
assert not retriever._warmed_up
|
|
171
|
+
result = retriever.run(query="SELECT 1 AS x")
|
|
172
|
+
assert retriever._warmed_up
|
|
173
|
+
assert not result["dataframe"].empty
|