sie-haystack 0.1.7__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.
@@ -0,0 +1,256 @@
1
+ # Byte-compiled / optimized / DLL files
2
+ __pycache__/
3
+ *.py[codz]
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
+ share/python-wheels/
24
+ *.egg-info/
25
+ .installed.cfg
26
+ *.egg
27
+ MANIFEST
28
+
29
+ # PyInstaller
30
+ # Usually these files are written by a python script from a template
31
+ # before PyInstaller builds the exe, so as to inject date/other infos into it.
32
+ *.manifest
33
+ *.spec
34
+
35
+ # Installer logs
36
+ pip-log.txt
37
+ pip-delete-this-directory.txt
38
+
39
+ # Unit test / coverage reports
40
+ htmlcov/
41
+ .tox/
42
+ .nox/
43
+ .coverage
44
+ .coverage.*
45
+ .cache
46
+ nosetests.xml
47
+ coverage.xml
48
+ *.cover
49
+ *.py.cover
50
+ .hypothesis/
51
+ .pytest_cache/
52
+ cover/
53
+
54
+ # Translations
55
+ *.mo
56
+ *.pot
57
+
58
+ # Django stuff:
59
+ *.log
60
+ local_settings.py
61
+ db.sqlite3
62
+ db.sqlite3-journal
63
+
64
+ # Flask stuff:
65
+ instance/
66
+ .webassets-cache
67
+
68
+ # Scrapy stuff:
69
+ .scrapy
70
+
71
+ # Sphinx documentation
72
+ docs/_build/
73
+
74
+ # PyBuilder
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
+ # For a library or package, you might want to ignore these files since the code is
87
+ # intended to run in multiple environments; otherwise, check them in:
88
+ # .python-version
89
+
90
+ # pipenv
91
+ # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92
+ # However, in case of collaboration, if having platform-specific dependencies or dependencies
93
+ # having no cross-platform support, pipenv may install dependencies that don't work, or not
94
+ # install all needed dependencies.
95
+ #Pipfile.lock
96
+
97
+ # UV
98
+ # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
99
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
100
+ # commonly ignored for libraries.
101
+ #uv.lock
102
+
103
+ # poetry
104
+ # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
105
+ # This is especially recommended for binary packages to ensure reproducibility, and is more
106
+ # commonly ignored for libraries.
107
+ # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
108
+ #poetry.lock
109
+ #poetry.toml
110
+
111
+ # pdm
112
+ # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
113
+ # pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
114
+ # https://pdm-project.org/en/latest/usage/project/#working-with-version-control
115
+ #pdm.lock
116
+ #pdm.toml
117
+ .pdm-python
118
+ .pdm-build/
119
+
120
+ # pixi
121
+ # Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
122
+ #pixi.lock
123
+ # Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
124
+ # in the .venv directory. It is recommended not to include this directory in version control.
125
+ .pixi
126
+
127
+ # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
128
+ __pypackages__/
129
+
130
+ # Celery stuff
131
+ celerybeat-schedule
132
+ celerybeat.pid
133
+
134
+ # SageMath parsed files
135
+ *.sage.py
136
+
137
+ # Environments
138
+ .env
139
+ .venv
140
+ env/
141
+ venv/
142
+ ENV/
143
+ env.bak/
144
+ venv.bak/
145
+
146
+ # Spyder project settings
147
+ .spyderproject
148
+ .spyproject
149
+
150
+ # Rope project settings
151
+ .ropeproject
152
+
153
+ # mkdocs documentation
154
+ /site
155
+
156
+ # Pyre type checker
157
+ .pyre/
158
+
159
+ # pytype static type analyzer
160
+ .pytype/
161
+
162
+ # Cython debug symbols
163
+ cython_debug/
164
+
165
+ # PyCharm
166
+ # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
167
+ # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
168
+ # and can be added to the global gitignore or merged into this file. For a more nuclear
169
+ # option (not recommended) you can uncomment the following to ignore the entire idea folder.
170
+ #.idea/
171
+
172
+ # Abstra
173
+ # Abstra is an AI-powered process automation framework.
174
+ # Ignore directories containing user credentials, local state, and settings.
175
+ # Learn more at https://abstra.io/docs
176
+ .abstra/
177
+
178
+ # Visual Studio Code
179
+ # Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
180
+ # that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
181
+ # and can be added to the global gitignore or merged into this file. However, if you prefer,
182
+ # you could uncomment the following to ignore the entire vscode folder
183
+ # .vscode/
184
+
185
+ # Ruff stuff:
186
+ .ruff_cache/
187
+
188
+ # PyPI configuration file
189
+ .pypirc
190
+
191
+ # Cursor
192
+ # Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
193
+ # exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
194
+ # refer to https://docs.cursor.com/context/ignore-files
195
+ .cursorignore
196
+ .cursorindexingignore
197
+
198
+ # vcscode
199
+ .vscode
200
+
201
+ # Marimo
202
+ marimo/_static/
203
+ marimo/_lsp/
204
+ __marimo__/
205
+
206
+ # SIE specific
207
+ # Model weights cache
208
+ .cache/
209
+ *.safetensors
210
+ *.bin
211
+
212
+ # Secrets (never commit)
213
+ *.pem
214
+ *.key
215
+ credentials.json
216
+ *-key.json
217
+
218
+ # Terraform
219
+ # Local .terraform directories (cached providers/modules)
220
+ **/.terraform/*
221
+ .terraform.lock*
222
+ # State files (contain sensitive data)
223
+ *.tfstate
224
+ *.tfstate.*
225
+ # Crash log files
226
+ crash.log
227
+ crash.*.log
228
+ # Override files (local developer overrides)
229
+ override.tf
230
+ override.tf.json
231
+ *_override.tf
232
+ *_override.tf.json
233
+ # tfvars files may contain secrets
234
+ *.tfvars
235
+ *.tfvars.json
236
+ # Keep .terraform.lock.hcl for reproducibility (provider versions)
237
+
238
+ # Node.js
239
+ node_modules/
240
+
241
+ # OS
242
+ .DS_Store
243
+ Thumbs.db
244
+
245
+ # VIM
246
+ *.swp
247
+
248
+ # Worktree metadata
249
+ .base-branch
250
+
251
+ # Temporary files
252
+ tmp/
253
+ .tmp/
254
+ .local/
255
+
256
+ .requirements-modal.txt
@@ -0,0 +1,57 @@
1
+ Metadata-Version: 2.4
2
+ Name: sie-haystack
3
+ Version: 0.1.7
4
+ Summary: SIE integration for Haystack
5
+ Author-email: Superlinked <dev@superlinked.com>
6
+ License: Apache-2.0
7
+ Classifier: Development Status :: 4 - Beta
8
+ Classifier: License :: OSI Approved :: Apache Software License
9
+ Classifier: Programming Language :: Python :: 3
10
+ Classifier: Programming Language :: Python :: 3.10
11
+ Classifier: Programming Language :: Python :: 3.11
12
+ Classifier: Programming Language :: Python :: 3.12
13
+ Requires-Python: >=3.10
14
+ Requires-Dist: haystack-ai>=2.0.0
15
+ Requires-Dist: sie-sdk>=0.1.0
16
+ Provides-Extra: dev
17
+ Requires-Dist: chroma-haystack>=2.0.0; extra == 'dev'
18
+ Requires-Dist: chromadb>=0.4.0; extra == 'dev'
19
+ Requires-Dist: pytest-asyncio>=0.23.0; extra == 'dev'
20
+ Requires-Dist: pytest>=8.0.0; extra == 'dev'
21
+ Description-Content-Type: text/markdown
22
+
23
+ # sie-haystack
24
+
25
+ SIE integration for Haystack.
26
+
27
+ ## Installation
28
+
29
+ ```bash
30
+ pip install sie-haystack
31
+ ```
32
+
33
+ ## Usage
34
+
35
+ ```python
36
+ from haystack import Document
37
+ from sie_haystack import SIETextEmbedder, SIEDocumentEmbedder, SIERanker
38
+
39
+ # Embed a query
40
+ text_embedder = SIETextEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
41
+ result = text_embedder.run(text="What is machine learning?")
42
+ query_embedding = result["embedding"]
43
+
44
+ # Embed documents
45
+ doc_embedder = SIEDocumentEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
46
+ docs = [Document(content="Python is a programming language.")]
47
+ result = doc_embedder.run(documents=docs)
48
+ embedded_docs = result["documents"]
49
+
50
+ # Rerank documents
51
+ ranker = SIERanker(
52
+ base_url="http://localhost:8080",
53
+ model="jinaai/jina-reranker-v2-base-multilingual"
54
+ )
55
+ result = ranker.run(query="What is Python?", documents=embedded_docs, top_k=3)
56
+ ranked_docs = result["documents"]
57
+ ```
@@ -0,0 +1,35 @@
1
+ # sie-haystack
2
+
3
+ SIE integration for Haystack.
4
+
5
+ ## Installation
6
+
7
+ ```bash
8
+ pip install sie-haystack
9
+ ```
10
+
11
+ ## Usage
12
+
13
+ ```python
14
+ from haystack import Document
15
+ from sie_haystack import SIETextEmbedder, SIEDocumentEmbedder, SIERanker
16
+
17
+ # Embed a query
18
+ text_embedder = SIETextEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
19
+ result = text_embedder.run(text="What is machine learning?")
20
+ query_embedding = result["embedding"]
21
+
22
+ # Embed documents
23
+ doc_embedder = SIEDocumentEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
24
+ docs = [Document(content="Python is a programming language.")]
25
+ result = doc_embedder.run(documents=docs)
26
+ embedded_docs = result["documents"]
27
+
28
+ # Rerank documents
29
+ ranker = SIERanker(
30
+ base_url="http://localhost:8080",
31
+ model="jinaai/jina-reranker-v2-base-multilingual"
32
+ )
33
+ result = ranker.run(query="What is Python?", documents=embedded_docs, top_k=3)
34
+ ranked_docs = result["documents"]
35
+ ```
@@ -0,0 +1,41 @@
1
+ [project]
2
+ name = "sie-haystack"
3
+ version = "0.1.7"
4
+ description = "SIE integration for Haystack"
5
+ readme = "README.md"
6
+ requires-python = ">=3.10"
7
+ license = { text = "Apache-2.0" }
8
+ authors = [{ name = "Superlinked", email = "dev@superlinked.com" }]
9
+ classifiers = [
10
+ "Development Status :: 4 - Beta",
11
+ "Programming Language :: Python :: 3",
12
+ "Programming Language :: Python :: 3.10",
13
+ "Programming Language :: Python :: 3.11",
14
+ "Programming Language :: Python :: 3.12",
15
+ "License :: OSI Approved :: Apache Software License",
16
+ ]
17
+
18
+ dependencies = [
19
+ "sie-sdk>=0.1.0",
20
+ "haystack-ai>=2.0.0",
21
+ ]
22
+
23
+ [project.optional-dependencies]
24
+ dev = [
25
+ "pytest>=8.0.0",
26
+ "pytest-asyncio>=0.23.0",
27
+ "chromadb>=0.4.0",
28
+ "chroma-haystack>=2.0.0"
29
+ ]
30
+
31
+ [build-system]
32
+ requires = ["hatchling"]
33
+ build-backend = "hatchling.build"
34
+
35
+ [tool.hatch.build.targets.wheel]
36
+ packages = ["src/sie_haystack"]
37
+
38
+ [tool.pytest.ini_options]
39
+ asyncio_mode = "auto"
40
+ addopts = "-v --tb=short -m 'not integration'"
41
+ markers = ["integration: marks tests as integration tests (require running server)"]
@@ -0,0 +1,62 @@
1
+ """SIE integration for Haystack.
2
+
3
+ This package provides Haystack components that use SIE for inference:
4
+
5
+ Dense Embedders:
6
+ - SIETextEmbedder: Embeds single text strings (queries)
7
+ - SIEDocumentEmbedder: Embeds documents and stores embeddings on them
8
+
9
+ Sparse Embedders (for hybrid search):
10
+ - SIESparseTextEmbedder: Sparse embeddings for queries
11
+ - SIESparseDocumentEmbedder: Sparse embeddings for documents
12
+
13
+ Rankers and Extractors:
14
+ - SIERanker: Reranks documents by relevance to a query
15
+ - SIEExtractor: Extracts entities from text
16
+
17
+ Example usage:
18
+ from haystack import Document
19
+ from sie_haystack import SIETextEmbedder, SIEDocumentEmbedder, SIERanker
20
+
21
+ # Embed a query
22
+ text_embedder = SIETextEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
23
+ result = text_embedder.run(text="What is machine learning?")
24
+ query_embedding = result["embedding"]
25
+
26
+ # Embed documents
27
+ doc_embedder = SIEDocumentEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
28
+ docs = [Document(content="Python is a programming language.")]
29
+ result = doc_embedder.run(documents=docs)
30
+ embedded_docs = result["documents"]
31
+
32
+ # Rerank documents
33
+ ranker = SIERanker(base_url="http://localhost:8080", model="jinaai/jina-reranker-v2-base-multilingual")
34
+ result = ranker.run(query="What is Python?", documents=embedded_docs, top_k=3)
35
+ ranked_docs = result["documents"]
36
+
37
+ Hybrid search example:
38
+ from sie_haystack import SIESparseTextEmbedder, SIESparseDocumentEmbedder
39
+
40
+ # Sparse embeddings for hybrid search with Qdrant
41
+ sparse_text_embedder = SIESparseTextEmbedder(model="BAAI/bge-m3")
42
+ result = sparse_text_embedder.run(text="What is machine learning?")
43
+ sparse_embedding = result["sparse_embedding"] # {"indices": [...], "values": [...]}
44
+ """
45
+
46
+ from sie_haystack.embedders import (
47
+ SIEDocumentEmbedder,
48
+ SIESparseDocumentEmbedder,
49
+ SIESparseTextEmbedder,
50
+ SIETextEmbedder,
51
+ )
52
+ from sie_haystack.extractors import SIEExtractor
53
+ from sie_haystack.rankers import SIERanker
54
+
55
+ __all__ = [
56
+ "SIEDocumentEmbedder",
57
+ "SIEExtractor",
58
+ "SIERanker",
59
+ "SIESparseDocumentEmbedder",
60
+ "SIESparseTextEmbedder",
61
+ "SIETextEmbedder",
62
+ ]