swarmauri_vectorstore_pinecone 0.6.0__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.
- swarmauri_vectorstore_pinecone-0.6.0/LICENSE +201 -0
- swarmauri_vectorstore_pinecone-0.6.0/PKG-INFO +73 -0
- swarmauri_vectorstore_pinecone-0.6.0/README.md +51 -0
- swarmauri_vectorstore_pinecone-0.6.0/pyproject.toml +58 -0
- swarmauri_vectorstore_pinecone-0.6.0/swarmauri_vectorstore_pinecone/PineconeVectorStore.py +377 -0
- swarmauri_vectorstore_pinecone-0.6.0/swarmauri_vectorstore_pinecone/__init__.py +17 -0
|
@@ -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] [Jacob Stewart @ Swarmauri]
|
|
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 +1,73 @@
|
|
|
1
|
+
Metadata-Version: 2.3
|
|
2
|
+
Name: swarmauri_vectorstore_pinecone
|
|
3
|
+
Version: 0.6.0
|
|
4
|
+
Summary: Swarmauri Pinecone Vector Store
|
|
5
|
+
License: Apache-2.0
|
|
6
|
+
Author: Jacob Stewart
|
|
7
|
+
Author-email: jacob@swarmauri.com
|
|
8
|
+
Requires-Python: >=3.10,<3.13
|
|
9
|
+
Classifier: License :: OSI Approved :: Apache Software License
|
|
10
|
+
Classifier: Programming Language :: Python :: 3
|
|
11
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
+
Requires-Dist: pinecone-client[grpc] (>=5.0.1,<6.0.0)
|
|
15
|
+
Requires-Dist: swarmauri_base (>=0.6.0,<0.7.0)
|
|
16
|
+
Requires-Dist: swarmauri_core (>=0.6.0,<0.7.0)
|
|
17
|
+
Requires-Dist: swarmauri_embedding_doc2vec (>=0.6.0,<0.7.0)
|
|
18
|
+
Requires-Dist: swarmauri_standard (>=0.6.0,<0.7.0)
|
|
19
|
+
Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
|
|
20
|
+
Description-Content-Type: text/markdown
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
<div align="center">
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
</div>
|
|
32
|
+
|
|
33
|
+
---
|
|
34
|
+
|
|
35
|
+
# Swarmauri Pinecone Vector Store
|
|
36
|
+
|
|
37
|
+
A vector store implementation using Pinecone as the backend for efficient similarity search and document storage.
|
|
38
|
+
|
|
39
|
+
## Installation
|
|
40
|
+
|
|
41
|
+
```bash
|
|
42
|
+
pip install swarmauri_vectorstore_pinecone
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
## Usage
|
|
46
|
+
|
|
47
|
+
```python
|
|
48
|
+
from swarmauri.vector_stores.PineconeVectorStore import PineconeVectorStore
|
|
49
|
+
from swarmauri.documents.Document import Document
|
|
50
|
+
|
|
51
|
+
# Initialize vector store
|
|
52
|
+
vector_store = PineconeVectorStore(
|
|
53
|
+
api_key="your-pinecone-api-key",
|
|
54
|
+
collection_name="example",
|
|
55
|
+
vector_size=100
|
|
56
|
+
)
|
|
57
|
+
vector_store.connect()
|
|
58
|
+
|
|
59
|
+
# Add documents
|
|
60
|
+
documents = [
|
|
61
|
+
Document(content="First document"),
|
|
62
|
+
Document(content="Second document"),
|
|
63
|
+
]
|
|
64
|
+
vector_store.add_documents(documents)
|
|
65
|
+
|
|
66
|
+
# Retrieve similar documents
|
|
67
|
+
results = vector_store.retrieve(query="document", top_k=2)
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
## Want to help?
|
|
71
|
+
|
|
72
|
+
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
|
73
|
+
|
|
@@ -0,0 +1,51 @@
|
|
|
1
|
+
|
|
2
|
+
|
|
3
|
+
<div align="center">
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
</div>
|
|
11
|
+
|
|
12
|
+
---
|
|
13
|
+
|
|
14
|
+
# Swarmauri Pinecone Vector Store
|
|
15
|
+
|
|
16
|
+
A vector store implementation using Pinecone as the backend for efficient similarity search and document storage.
|
|
17
|
+
|
|
18
|
+
## Installation
|
|
19
|
+
|
|
20
|
+
```bash
|
|
21
|
+
pip install swarmauri_vectorstore_pinecone
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## Usage
|
|
25
|
+
|
|
26
|
+
```python
|
|
27
|
+
from swarmauri.vector_stores.PineconeVectorStore import PineconeVectorStore
|
|
28
|
+
from swarmauri.documents.Document import Document
|
|
29
|
+
|
|
30
|
+
# Initialize vector store
|
|
31
|
+
vector_store = PineconeVectorStore(
|
|
32
|
+
api_key="your-pinecone-api-key",
|
|
33
|
+
collection_name="example",
|
|
34
|
+
vector_size=100
|
|
35
|
+
)
|
|
36
|
+
vector_store.connect()
|
|
37
|
+
|
|
38
|
+
# Add documents
|
|
39
|
+
documents = [
|
|
40
|
+
Document(content="First document"),
|
|
41
|
+
Document(content="Second document"),
|
|
42
|
+
]
|
|
43
|
+
vector_store.add_documents(documents)
|
|
44
|
+
|
|
45
|
+
# Retrieve similar documents
|
|
46
|
+
results = vector_store.retrieve(query="document", top_k=2)
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
## Want to help?
|
|
50
|
+
|
|
51
|
+
If you want to contribute to swarmauri-sdk, read up on our [guidelines for contributing](https://github.com/swarmauri/swarmauri-sdk/blob/master/contributing.md) that will help you get started.
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
[tool.poetry]
|
|
2
|
+
name = "swarmauri_vectorstore_pinecone"
|
|
3
|
+
version = "0.6.0"
|
|
4
|
+
description = "Swarmauri Pinecone Vector Store"
|
|
5
|
+
authors = ["Jacob Stewart <jacob@swarmauri.com>"]
|
|
6
|
+
license = "Apache-2.0"
|
|
7
|
+
readme = "README.md"
|
|
8
|
+
repository = "http://github.com/swarmauri/swarmauri-sdk"
|
|
9
|
+
classifiers = [
|
|
10
|
+
"License :: OSI Approved :: Apache Software License",
|
|
11
|
+
"Programming Language :: Python :: 3.10",
|
|
12
|
+
"Programming Language :: Python :: 3.11",
|
|
13
|
+
"Programming Language :: Python :: 3.12"
|
|
14
|
+
]
|
|
15
|
+
|
|
16
|
+
[tool.poetry.dependencies]
|
|
17
|
+
python = ">=3.10,<3.13"
|
|
18
|
+
|
|
19
|
+
# Swarmauri
|
|
20
|
+
swarmauri_core = {version = "^0.6.0"}
|
|
21
|
+
swarmauri_base = {version = "^0.6.0"}
|
|
22
|
+
swarmauri_standard = {version = "^0.6.0"}
|
|
23
|
+
swarmauri_embedding_doc2vec = {version = "^0.6.0"}
|
|
24
|
+
|
|
25
|
+
# Dependencies
|
|
26
|
+
pinecone-client = { version = "^5.0.1", extras = ["grpc"] }
|
|
27
|
+
|
|
28
|
+
[tool.poetry.group.dev.dependencies]
|
|
29
|
+
flake8 = "^7.0"
|
|
30
|
+
pytest = "^8.0"
|
|
31
|
+
pytest-asyncio = ">=0.24.0"
|
|
32
|
+
pytest-xdist = "^3.6.1"
|
|
33
|
+
pytest-json-report = "^1.5.0"
|
|
34
|
+
python-dotenv = "*"
|
|
35
|
+
requests = "^2.32.3"
|
|
36
|
+
|
|
37
|
+
[build-system]
|
|
38
|
+
requires = ["poetry-core>=1.0.0"]
|
|
39
|
+
build-backend = "poetry.core.masonry.api"
|
|
40
|
+
|
|
41
|
+
[tool.pytest.ini_options]
|
|
42
|
+
norecursedirs = ["combined", "scripts"]
|
|
43
|
+
|
|
44
|
+
markers = [
|
|
45
|
+
"test: standard test",
|
|
46
|
+
"unit: Unit tests",
|
|
47
|
+
"integration: Integration tests",
|
|
48
|
+
"acceptance: Acceptance tests",
|
|
49
|
+
"experimental: Experimental tests"
|
|
50
|
+
]
|
|
51
|
+
log_cli = true
|
|
52
|
+
log_cli_level = "INFO"
|
|
53
|
+
log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
|
|
54
|
+
log_cli_date_format = "%Y-%m-%d %H:%M:%S"
|
|
55
|
+
asyncio_default_fixture_loop_scope = "function"
|
|
56
|
+
|
|
57
|
+
[tool.poetry.plugins."swarmauri.vector_stores"]
|
|
58
|
+
PineconeVectorStore = "swarmauri_vectorstore_pinecone.PineconeVectorStore:PineconeVectorStore"
|
|
@@ -0,0 +1,377 @@
|
|
|
1
|
+
import numpy as np
|
|
2
|
+
from typing import List, Union, Literal, Dict, Any, Optional
|
|
3
|
+
|
|
4
|
+
from pinecone.grpc import PineconeGRPC as Pinecone
|
|
5
|
+
from pinecone import ServerlessSpec
|
|
6
|
+
|
|
7
|
+
from swarmauri_standard.documents.Document import Document
|
|
8
|
+
from swarmauri_embedding_doc2vec.Doc2VecEmbedding import Doc2VecEmbedding
|
|
9
|
+
from swarmauri_standard.distances.CosineDistance import CosineDistance
|
|
10
|
+
|
|
11
|
+
from swarmauri_base.vector_stores.VectorStoreBase import VectorStoreBase
|
|
12
|
+
from swarmauri_base.vector_stores.VectorStoreRetrieveMixin import (
|
|
13
|
+
VectorStoreRetrieveMixin,
|
|
14
|
+
)
|
|
15
|
+
from swarmauri_base.vector_stores.VectorStoreCloudMixin import (
|
|
16
|
+
VectorStoreCloudMixin,
|
|
17
|
+
)
|
|
18
|
+
from swarmauri_base.vector_stores.VectorStoreSaveLoadMixin import (
|
|
19
|
+
VectorStoreSaveLoadMixin,
|
|
20
|
+
)
|
|
21
|
+
from swarmauri_core.ComponentBase import ComponentBase
|
|
22
|
+
|
|
23
|
+
|
|
24
|
+
@ComponentBase.register_type(VectorStoreBase, "PineconeVectorStore")
|
|
25
|
+
class PineconeVectorStore(
|
|
26
|
+
VectorStoreRetrieveMixin,
|
|
27
|
+
VectorStoreCloudMixin,
|
|
28
|
+
VectorStoreSaveLoadMixin,
|
|
29
|
+
VectorStoreBase,
|
|
30
|
+
):
|
|
31
|
+
"""
|
|
32
|
+
A vector store implementation using Pinecone as the backend.
|
|
33
|
+
|
|
34
|
+
This class provides methods to interact with a Pinecone index, including
|
|
35
|
+
adding, retrieving, updating, and deleting documents, as well as performing
|
|
36
|
+
similarity searches.
|
|
37
|
+
"""
|
|
38
|
+
|
|
39
|
+
type: Literal["PineconeVectorStore"] = "PineconeVectorStore"
|
|
40
|
+
|
|
41
|
+
def __init__(self, **kwargs):
|
|
42
|
+
"""
|
|
43
|
+
Initialize the PineconeVectorStore.
|
|
44
|
+
Args:
|
|
45
|
+
**kwargs: Additional keyword arguments.
|
|
46
|
+
"""
|
|
47
|
+
super().__init__(**kwargs)
|
|
48
|
+
self._embedder = Doc2VecEmbedding(vector_size=self.vector_size)
|
|
49
|
+
self._distance = CosineDistance()
|
|
50
|
+
|
|
51
|
+
def delete(self):
|
|
52
|
+
"""
|
|
53
|
+
Delete the Pinecone index if it exists.
|
|
54
|
+
|
|
55
|
+
"""
|
|
56
|
+
try:
|
|
57
|
+
pc = Pinecone(api_key=self.api_key.get_secret_value())
|
|
58
|
+
pc.delete_index(self.collection_name)
|
|
59
|
+
self.client = None
|
|
60
|
+
except Exception as e:
|
|
61
|
+
raise RuntimeError(
|
|
62
|
+
f"Failed to delete index {self.collection_name}: {str(e)}"
|
|
63
|
+
)
|
|
64
|
+
|
|
65
|
+
def connect(
|
|
66
|
+
self,
|
|
67
|
+
metric: Optional[str] = "cosine",
|
|
68
|
+
cloud: Optional[str] = "aws",
|
|
69
|
+
region: Optional[str] = "us-east-1",
|
|
70
|
+
):
|
|
71
|
+
"""
|
|
72
|
+
Connect to the Pinecone index, creating it if it doesn't exist.
|
|
73
|
+
|
|
74
|
+
Args:
|
|
75
|
+
metric (Optional[str]): The distance metric to use. Defaults to "cosine".
|
|
76
|
+
cloud (Optional[str]): The cloud provider to use. Defaults to "aws".
|
|
77
|
+
region (Optional[str]): The region to use. Defaults to "us-east-1".
|
|
78
|
+
|
|
79
|
+
"""
|
|
80
|
+
try:
|
|
81
|
+
pc = Pinecone(api_key=self.api_key.get_secret_value())
|
|
82
|
+
if not pc.has_index(self.collection_name):
|
|
83
|
+
pc.create_index(
|
|
84
|
+
name=self.collection_name,
|
|
85
|
+
dimension=self.vector_size,
|
|
86
|
+
metric=metric,
|
|
87
|
+
spec=ServerlessSpec(
|
|
88
|
+
cloud=cloud,
|
|
89
|
+
region=region,
|
|
90
|
+
),
|
|
91
|
+
)
|
|
92
|
+
self.client = pc.Index(self.collection_name)
|
|
93
|
+
except Exception as e:
|
|
94
|
+
raise RuntimeError(
|
|
95
|
+
f"Failed to connect to Pinecone index {self.collection_name}: {str(e)}"
|
|
96
|
+
)
|
|
97
|
+
|
|
98
|
+
def disconnect(self):
|
|
99
|
+
"""
|
|
100
|
+
Disconnect from the Pinecone index.
|
|
101
|
+
|
|
102
|
+
"""
|
|
103
|
+
try:
|
|
104
|
+
self.client = None
|
|
105
|
+
except Exception as e:
|
|
106
|
+
raise RuntimeError(f"Error during disconnecting: {str(e)}")
|
|
107
|
+
|
|
108
|
+
def _prepare_vector(self, document: Document) -> Dict[str, Any]:
|
|
109
|
+
"""
|
|
110
|
+
Prepare a vector for insertion into the Pinecone index.
|
|
111
|
+
|
|
112
|
+
Args:
|
|
113
|
+
document (Document): The document to prepare.
|
|
114
|
+
|
|
115
|
+
Returns:
|
|
116
|
+
Dict[str, Any]: A dictionary containing the prepared vector data.
|
|
117
|
+
"""
|
|
118
|
+
embedding = None
|
|
119
|
+
if not document.embedding:
|
|
120
|
+
self._embedder.fit([document.content])
|
|
121
|
+
embedding = (
|
|
122
|
+
self._embedder.transform([document.content])[0].to_numpy().tolist()
|
|
123
|
+
)
|
|
124
|
+
else:
|
|
125
|
+
embedding = document.embedding
|
|
126
|
+
|
|
127
|
+
document.metadata["content"] = document.content
|
|
128
|
+
return {"id": document.id, "values": embedding, "metadata": document.metadata}
|
|
129
|
+
|
|
130
|
+
def add_document(self, document: Document, namespace: Optional[str] = "") -> None:
|
|
131
|
+
"""
|
|
132
|
+
Add a single document to the Pinecone index.
|
|
133
|
+
|
|
134
|
+
Args:
|
|
135
|
+
document (Document): The document to add.
|
|
136
|
+
namespace (Optional[str]): The namespace to add the document to. Defaults to "".
|
|
137
|
+
"""
|
|
138
|
+
try:
|
|
139
|
+
vector = self._prepare_vector(document)
|
|
140
|
+
self.client.upsert(vectors=[vector], namespace=namespace)
|
|
141
|
+
except Exception as e:
|
|
142
|
+
raise RuntimeError(f"Failed to add document {document.id}: {str(e)}")
|
|
143
|
+
|
|
144
|
+
def add_documents(
|
|
145
|
+
self,
|
|
146
|
+
documents: List[Document],
|
|
147
|
+
namespace: Optional[str] = "",
|
|
148
|
+
batch_size: int = 200,
|
|
149
|
+
) -> None:
|
|
150
|
+
"""
|
|
151
|
+
Add multiple documents to the Pinecone index in batches.
|
|
152
|
+
|
|
153
|
+
Args:
|
|
154
|
+
documents (List[Document]): The list of documents to add.
|
|
155
|
+
namespace (Optional[str]): The namespace to add the documents to. Defaults to "".
|
|
156
|
+
batch_size (int): The number of documents to add in each batch. Defaults to 200.
|
|
157
|
+
|
|
158
|
+
"""
|
|
159
|
+
if batch_size <= 0 or batch_size > 1000:
|
|
160
|
+
raise ValueError("Batch size must be between 1 and 1000.")
|
|
161
|
+
|
|
162
|
+
vectors = [self._prepare_vector(doc) for doc in documents]
|
|
163
|
+
for i in range(0, len(vectors), batch_size):
|
|
164
|
+
batch_vectors = vectors[i : i + batch_size]
|
|
165
|
+
try:
|
|
166
|
+
self.client.upsert(vectors=batch_vectors, namespace=namespace)
|
|
167
|
+
except Exception as e:
|
|
168
|
+
raise RuntimeError(
|
|
169
|
+
f"Error during batch upsert. Consider lowering batch size: {str(e)}"
|
|
170
|
+
)
|
|
171
|
+
|
|
172
|
+
def get_document(
|
|
173
|
+
self, id: str, namespace: Optional[str] = ""
|
|
174
|
+
) -> Union[Document, None]:
|
|
175
|
+
"""
|
|
176
|
+
Retrieve a single document from the Pinecone index by its ID.
|
|
177
|
+
|
|
178
|
+
Args:
|
|
179
|
+
id (str): The ID of the document to retrieve.
|
|
180
|
+
namespace (Optional[str]): The namespace to search in. Defaults to "".
|
|
181
|
+
|
|
182
|
+
Returns:
|
|
183
|
+
Union[Document, None]: The retrieved document, or None if not found.
|
|
184
|
+
|
|
185
|
+
"""
|
|
186
|
+
try:
|
|
187
|
+
result = self.client.fetch(ids=[id], namespace=namespace)
|
|
188
|
+
if id in result["vectors"]:
|
|
189
|
+
vector = result["vectors"][id]
|
|
190
|
+
return Document(
|
|
191
|
+
id=id,
|
|
192
|
+
content=vector["metadata"].get("content", ""),
|
|
193
|
+
metadata=vector["metadata"] or {},
|
|
194
|
+
)
|
|
195
|
+
return None
|
|
196
|
+
except Exception as e:
|
|
197
|
+
raise RuntimeError(f"Failed to get document {id}: {str(e)}")
|
|
198
|
+
|
|
199
|
+
def _get_ids_from_query(self, input_vector):
|
|
200
|
+
"""
|
|
201
|
+
Get document IDs from a query vector.
|
|
202
|
+
|
|
203
|
+
Args:
|
|
204
|
+
input_vector: The input vector to query.
|
|
205
|
+
|
|
206
|
+
"""
|
|
207
|
+
results = self.client.query(
|
|
208
|
+
vector=input_vector, top_k=10000, include_values=False
|
|
209
|
+
)
|
|
210
|
+
return {result["id"] for result in results["matches"]}
|
|
211
|
+
|
|
212
|
+
def _get_all_ids_from_client(self, namespace: Optional[str] = ""):
|
|
213
|
+
"""
|
|
214
|
+
Get all document IDs from the Pinecone index.
|
|
215
|
+
|
|
216
|
+
Args:
|
|
217
|
+
namespace (Optional[str]): The namespace to search in. Defaults to "".
|
|
218
|
+
|
|
219
|
+
Returns:
|
|
220
|
+
set: A set of all document IDs in the index.
|
|
221
|
+
"""
|
|
222
|
+
num_vectors = self.client.describe_index_stats()["namespaces"][namespace][
|
|
223
|
+
"vector_count"
|
|
224
|
+
]
|
|
225
|
+
all_ids = set()
|
|
226
|
+
while len(all_ids) < num_vectors:
|
|
227
|
+
input_vector = np.random.rand(self.vector_size).tolist()
|
|
228
|
+
ids = self._get_ids_from_query(input_vector)
|
|
229
|
+
all_ids.update(ids)
|
|
230
|
+
return all_ids
|
|
231
|
+
|
|
232
|
+
def get_all_documents(self, namespace: Optional[str] = "") -> List[Document]:
|
|
233
|
+
"""
|
|
234
|
+
Retrieve all documents from the Pinecone index.
|
|
235
|
+
|
|
236
|
+
Args:
|
|
237
|
+
namespace (Optional[str]): The namespace to search in. Defaults to "".
|
|
238
|
+
|
|
239
|
+
Returns:
|
|
240
|
+
List[Document]: A list of all documents in the index.
|
|
241
|
+
|
|
242
|
+
"""
|
|
243
|
+
try:
|
|
244
|
+
documents = []
|
|
245
|
+
id_list = list(self._get_all_ids_from_client(namespace))
|
|
246
|
+
batch_size = min(len(id_list), 1000)
|
|
247
|
+
for i in range(0, len(id_list), batch_size):
|
|
248
|
+
batch_ids = id_list[i : i + batch_size]
|
|
249
|
+
result = self.client.fetch(ids=batch_ids, namespace=namespace)
|
|
250
|
+
for id, vector in result["vectors"].items():
|
|
251
|
+
documents.append(
|
|
252
|
+
Document(
|
|
253
|
+
id=id,
|
|
254
|
+
content=vector["metadata"].get("content", ""),
|
|
255
|
+
metadata=vector["metadata"] or {},
|
|
256
|
+
)
|
|
257
|
+
)
|
|
258
|
+
return documents
|
|
259
|
+
except Exception as e:
|
|
260
|
+
raise RuntimeError(f"Failed to get all documents: {str(e)}")
|
|
261
|
+
|
|
262
|
+
def delete_document(self, id: str, namespace: Optional[str] = "") -> None:
|
|
263
|
+
"""
|
|
264
|
+
Delete a single document from the Pinecone index.
|
|
265
|
+
|
|
266
|
+
Args:
|
|
267
|
+
id (str): The ID of the document to delete.
|
|
268
|
+
namespace (Optional[str]): The namespace to delete from. Defaults to "".
|
|
269
|
+
|
|
270
|
+
"""
|
|
271
|
+
try:
|
|
272
|
+
self.client.delete(ids=[id], namespace=namespace)
|
|
273
|
+
except Exception as e:
|
|
274
|
+
raise RuntimeError(f"Failed to delete document {id}: {str(e)}")
|
|
275
|
+
|
|
276
|
+
def clear_documents(self, namespace: Optional[str] = "") -> None:
|
|
277
|
+
"""
|
|
278
|
+
Delete all documents from the Pinecone index in a given namespace.
|
|
279
|
+
|
|
280
|
+
Args:
|
|
281
|
+
namespace (Optional[str]): The namespace to clear. Defaults to "".
|
|
282
|
+
|
|
283
|
+
"""
|
|
284
|
+
try:
|
|
285
|
+
self.client.delete(delete_all=True, namespace=namespace)
|
|
286
|
+
except Exception as e:
|
|
287
|
+
raise RuntimeError(
|
|
288
|
+
f"Failed to clear documents in namespace {namespace}: {str(e)}"
|
|
289
|
+
)
|
|
290
|
+
|
|
291
|
+
def update_document(
|
|
292
|
+
self, id: str, document: Document, namespace: Optional[str] = ""
|
|
293
|
+
) -> None:
|
|
294
|
+
"""
|
|
295
|
+
Update a document in the Pinecone index.
|
|
296
|
+
|
|
297
|
+
Args:
|
|
298
|
+
id (str): The ID of the document to update.
|
|
299
|
+
document (Document): The updated document.
|
|
300
|
+
namespace (Optional[str]): The namespace of the document. Defaults to "".
|
|
301
|
+
|
|
302
|
+
"""
|
|
303
|
+
try:
|
|
304
|
+
embedding = (
|
|
305
|
+
self._embedder.transform([document.content])[0].to_numpy().tolist()
|
|
306
|
+
)
|
|
307
|
+
document.metadata["content"] = document.content
|
|
308
|
+
self.client.update(
|
|
309
|
+
id=id,
|
|
310
|
+
values=embedding,
|
|
311
|
+
set_metadata=document.metadata,
|
|
312
|
+
namespace=namespace,
|
|
313
|
+
)
|
|
314
|
+
except Exception as e:
|
|
315
|
+
raise RuntimeError(f"Failed to update document {id}: {str(e)}")
|
|
316
|
+
|
|
317
|
+
def document_count(self, namespace: Optional[str] = "") -> int:
|
|
318
|
+
"""
|
|
319
|
+
Get the number of documents in the Pinecone index.
|
|
320
|
+
|
|
321
|
+
Args:
|
|
322
|
+
namespace (Optional[str]): The namespace to count documents in. Defaults to "".
|
|
323
|
+
|
|
324
|
+
Returns:
|
|
325
|
+
int: The number of documents in the index.
|
|
326
|
+
|
|
327
|
+
"""
|
|
328
|
+
try:
|
|
329
|
+
return self.client.describe_index_stats()["namespaces"][namespace][
|
|
330
|
+
"vector_count"
|
|
331
|
+
]
|
|
332
|
+
except Exception as e:
|
|
333
|
+
raise RuntimeError(
|
|
334
|
+
f"Failed to get document count for namespace {namespace}: {str(e)}"
|
|
335
|
+
)
|
|
336
|
+
|
|
337
|
+
def retrieve(
|
|
338
|
+
self, query: str, top_k: int = 5, namespace: Optional[str] = ""
|
|
339
|
+
) -> List[Document]:
|
|
340
|
+
"""
|
|
341
|
+
Retrieve documents from the Pinecone index based on a query string.
|
|
342
|
+
|
|
343
|
+
Args:
|
|
344
|
+
query (str): The query string to search for.
|
|
345
|
+
top_k (int): The number of results to return. Defaults to 5.
|
|
346
|
+
namespace (Optional[str]): The namespace to search in. Defaults to "".
|
|
347
|
+
|
|
348
|
+
Returns:
|
|
349
|
+
List[Document]: A list of retrieved documents.
|
|
350
|
+
|
|
351
|
+
"""
|
|
352
|
+
try:
|
|
353
|
+
query_embedding = self._embedder.infer_vector(query).value
|
|
354
|
+
results = self.client.query(
|
|
355
|
+
vector=query_embedding,
|
|
356
|
+
top_k=top_k,
|
|
357
|
+
namespace=namespace,
|
|
358
|
+
include_metadata=True,
|
|
359
|
+
)
|
|
360
|
+
return [
|
|
361
|
+
Document(
|
|
362
|
+
id=match["id"],
|
|
363
|
+
content=match["metadata"].get("content", ""),
|
|
364
|
+
metadata=match["metadata"] or {},
|
|
365
|
+
)
|
|
366
|
+
for match in results["matches"]
|
|
367
|
+
]
|
|
368
|
+
except Exception as e:
|
|
369
|
+
raise RuntimeError(f"Failed to retrieve documents: {str(e)}")
|
|
370
|
+
|
|
371
|
+
# Override the model_dump_json method
|
|
372
|
+
def model_dump_json(self, *args, **kwargs) -> str:
|
|
373
|
+
# Call the disconnect method before serialization
|
|
374
|
+
self.disconnect()
|
|
375
|
+
|
|
376
|
+
# Now proceed with the usual JSON serialization
|
|
377
|
+
return super().model_dump_json(*args, **kwargs)
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
from .PineconeVectorStore import PineconeVectorStore
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
__all__ = ["PineconeVectorStore"]
|
|
5
|
+
|
|
6
|
+
try:
|
|
7
|
+
# For Python 3.8 and newer
|
|
8
|
+
from importlib.metadata import version, PackageNotFoundError
|
|
9
|
+
except ImportError:
|
|
10
|
+
# For older Python versions, use the backport
|
|
11
|
+
from importlib_metadata import version, PackageNotFoundError
|
|
12
|
+
|
|
13
|
+
try:
|
|
14
|
+
__version__ = version("swarmauri_vectorstore_pinecone")
|
|
15
|
+
except PackageNotFoundError:
|
|
16
|
+
# If the package is not installed (for example, during development)
|
|
17
|
+
__version__ = "0.0.0"
|