swarmauri_vectorstore_redis 0.6.0.dev154__tar.gz → 0.7.0.dev2__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 +1,201 @@
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 +1,76 @@
1
+ Metadata-Version: 2.3
2
+ Name: swarmauri_vectorstore_redis
3
+ Version: 0.7.0.dev2
4
+ Summary: Swarmauri Redis 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 :: 3.10
11
+ Classifier: Programming Language :: Python :: 3.11
12
+ Classifier: Programming Language :: Python :: 3.12
13
+ Requires-Dist: redis (>=4.0)
14
+ Requires-Dist: redisearch
15
+ Requires-Dist: swarmauri_base
16
+ Requires-Dist: swarmauri_core
17
+ Requires-Dist: swarmauri_embedding_doc2vec
18
+ Requires-Dist: swarmauri_standard
19
+ Description-Content-Type: text/markdown
20
+
21
+ ![Swarmauri Logo](https://res.cloudinary.com/dbjmpekvl/image/upload/v1730099724/Swarmauri-logo-lockup-2048x757_hww01w.png)
22
+
23
+ <div align="center">
24
+
25
+ ![PyPI - Downloads](https://img.shields.io/pypi/dm/swarmauri_vectorstore_redis)
26
+ ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/swarmauri_vectorstore_redis)
27
+ ![PyPI - License](https://img.shields.io/pypi/l/swarmauri_vectorstore_redis)
28
+ ![PyPI - Version](https://img.shields.io/pypi/v/swarmauri_vectorstore_redis?label=swarmauri_vectorstore_redis&color=green)
29
+
30
+ </div>
31
+
32
+ ---
33
+
34
+ # Redis Vector Store for Swarmauri
35
+
36
+ A Redis-based vector store implementation for the Swarmauri SDK that enables efficient storage and retrieval of document embeddings.
37
+
38
+ ## Installation
39
+
40
+ ```bash
41
+ pip install swarmauri_vectorstore_redis
42
+ ```
43
+
44
+ ## Usage
45
+
46
+ Basic example of using RedisVectorStore:
47
+
48
+ ```python
49
+ from swarmauri.vector_stores.RedisVectorStore import RedisVectorStore
50
+ from swarmauri.documents.Document import Document
51
+
52
+ # Initialize the vector store
53
+ vector_store = RedisVectorStore(
54
+ redis_host="localhost",
55
+ redis_port=6379,
56
+ redis_password="your_password",
57
+ embedding_dimension=8000
58
+ )
59
+
60
+ # Add documents
61
+ document = Document(
62
+ id="doc1",
63
+ content="Sample document content",
64
+ metadata={"category": "sample"}
65
+ )
66
+ vector_store.add_document(document)
67
+
68
+ # Retrieve similar documents
69
+ similar_docs = vector_store.retrieve("sample content", top_k=5)
70
+ ```
71
+
72
+ ## Want to help?
73
+
74
+ 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.
75
+
76
+
@@ -0,0 +1,55 @@
1
+ ![Swarmauri Logo](https://res.cloudinary.com/dbjmpekvl/image/upload/v1730099724/Swarmauri-logo-lockup-2048x757_hww01w.png)
2
+
3
+ <div align="center">
4
+
5
+ ![PyPI - Downloads](https://img.shields.io/pypi/dm/swarmauri_vectorstore_redis)
6
+ ![PyPI - Python Version](https://img.shields.io/pypi/pyversions/swarmauri_vectorstore_redis)
7
+ ![PyPI - License](https://img.shields.io/pypi/l/swarmauri_vectorstore_redis)
8
+ ![PyPI - Version](https://img.shields.io/pypi/v/swarmauri_vectorstore_redis?label=swarmauri_vectorstore_redis&color=green)
9
+
10
+ </div>
11
+
12
+ ---
13
+
14
+ # Redis Vector Store for Swarmauri
15
+
16
+ A Redis-based vector store implementation for the Swarmauri SDK that enables efficient storage and retrieval of document embeddings.
17
+
18
+ ## Installation
19
+
20
+ ```bash
21
+ pip install swarmauri_vectorstore_redis
22
+ ```
23
+
24
+ ## Usage
25
+
26
+ Basic example of using RedisVectorStore:
27
+
28
+ ```python
29
+ from swarmauri.vector_stores.RedisVectorStore import RedisVectorStore
30
+ from swarmauri.documents.Document import Document
31
+
32
+ # Initialize the vector store
33
+ vector_store = RedisVectorStore(
34
+ redis_host="localhost",
35
+ redis_port=6379,
36
+ redis_password="your_password",
37
+ embedding_dimension=8000
38
+ )
39
+
40
+ # Add documents
41
+ document = Document(
42
+ id="doc1",
43
+ content="Sample document content",
44
+ metadata={"category": "sample"}
45
+ )
46
+ vector_store.add_document(document)
47
+
48
+ # Retrieve similar documents
49
+ similar_docs = vector_store.retrieve("sample content", top_k=5)
50
+ ```
51
+
52
+ ## Want to help?
53
+
54
+ 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.
55
+
@@ -0,0 +1,72 @@
1
+ [project]
2
+ name = "swarmauri_vectorstore_redis"
3
+ version = "0.7.0.dev2"
4
+ description = "Swarmauri Redis Vector Store"
5
+ license = "Apache-2.0"
6
+ readme = "README.md"
7
+ repository = "http://github.com/swarmauri/swarmauri-sdk"
8
+ requires-python = ">=3.10,<3.13"
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
+ authors = [{ name = "Jacob Stewart", email = "jacob@swarmauri.com" }]
16
+ dependencies = [
17
+ "redis>=4.0",
18
+ "redisearch",
19
+ "swarmauri_core",
20
+ "swarmauri_base",
21
+ "swarmauri_standard",
22
+ "swarmauri_embedding_doc2vec"
23
+ ]
24
+
25
+ [tool.uv.sources]
26
+ swarmauri_core = { workspace = true }
27
+ swarmauri_base = { workspace = true }
28
+ swarmauri_standard = { workspace = true }
29
+ swarmauri_embedding_doc2vec = { workspace = true }
30
+
31
+ [tool.pytest.ini_options]
32
+ norecursedirs = ["combined", "scripts"]
33
+ markers = [
34
+ "test: standard test",
35
+ "unit: Unit tests",
36
+ "i9n: Integration tests",
37
+ "r8n: Regression tests",
38
+ "timeout: mark test to timeout after X seconds",
39
+ "xpass: Expected passes",
40
+ "xfail: Expected failures",
41
+ "acceptance: Acceptance tests",
42
+ ]
43
+ timeout = 300
44
+ log_cli = true
45
+ log_cli_level = "INFO"
46
+ log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
47
+ log_cli_date_format = "%Y-%m-%d %H:%M:%S"
48
+ asyncio_default_fixture_loop_scope = "function"
49
+
50
+ [tool.project.entry-points."swarmauri.vector_stores"]
51
+ RedisVectorStore = "swarmauri_vectorstore_redis.RedisVectorStore:RedisVectorStore"
52
+
53
+ [tool.project.entry-points."swarmauri.retrievers"]
54
+ RedisDocumentRetriever = "swarmauri_vectorstore_redis.RedisDocumentRetriever:RedisDocumentRetriever"
55
+
56
+
57
+ [build-system]
58
+ requires = ["poetry-core>=1.0.0"]
59
+ build-backend = "poetry.core.masonry.api"
60
+
61
+ [dependency-groups]
62
+ dev = [
63
+ "pytest>=8.0",
64
+ "pytest-asyncio>=0.24.0",
65
+ "pytest-xdist>=3.6.1",
66
+ "pytest-json-report>=1.5.0",
67
+ "python-dotenv",
68
+ "requests>=2.32.3",
69
+ "flake8>=7.0",
70
+ "pytest-timeout>=2.3.1",
71
+ "ruff>=0.9.9",
72
+ ]
@@ -0,0 +1,57 @@
1
+ from typing import List, Optional
2
+
3
+ from pydantic import Field, PrivateAttr
4
+ from redisearch import Client, Query
5
+ from swarmauri_base.document_stores.DocumentStoreRetrieveBase import (
6
+ DocumentStoreRetrieveBase,
7
+ )
8
+ from swarmauri_base.ComponentBase import ComponentBase
9
+ from swarmauri_standard.documents.Document import Document
10
+
11
+
12
+ @ComponentBase.register_type(DocumentStoreRetrieveBase, "RedisDocumentRetriever")
13
+ class RedisDocumentRetriever(DocumentStoreRetrieveBase):
14
+ """
15
+ A document retriever that fetches documents from a Redis store.
16
+ """
17
+
18
+ type: str = "RedisDocumentRetriever"
19
+ redis_idx_name: str = Field(..., description="Redis index name")
20
+ redis_host: str = Field(default="localhost", description="Redis host")
21
+ redis_port: int = Field(default=6379, description="Redis port")
22
+
23
+ # Private attributes
24
+ _redis_client: Optional[Client] = PrivateAttr(default=None)
25
+
26
+ @property
27
+ def redis_client(self) -> Client:
28
+ """Lazily initialize and return the Redis client using a factory method."""
29
+ if self._redis_client is None:
30
+ self._redis_client = Client(
31
+ self.redis_idx_name, host=self.redis_host, port=self.redis_port
32
+ )
33
+ return self._redis_client
34
+
35
+ def retrieve(self, query: str, top_k: int = 5) -> List[Document]:
36
+ """
37
+ Retrieve the most relevant documents based on the given query.
38
+
39
+ Args:
40
+ query (str): The query string used for document retrieval.
41
+ top_k (int, optional): The number of top relevant documents to retrieve. Defaults to 5.
42
+
43
+ Returns:
44
+ List[Document]: A list of the top_k most relevant documents.
45
+ """
46
+ query_result = self.redis_client.search(Query(query).paging(0, top_k))
47
+
48
+ documents = [
49
+ Document(
50
+ id=doc.id,
51
+ content=doc.content, # Note: Adjust 'text' based on actual Redis document schema
52
+ metadata=doc.__dict__, # Including full document fields and values in metadata
53
+ )
54
+ for doc in query_result.docs
55
+ ]
56
+
57
+ return documents
@@ -1,238 +1,236 @@
1
- import json
2
- from typing import List, Union, Literal, Optional
3
- from pydantic import PrivateAttr
4
-
5
- import numpy as np
6
- import redis
7
- from redis.commands.search.field import VectorField, TextField
8
- from redis.commands.search.indexDefinition import IndexDefinition, IndexType
9
-
10
- from swarmauri_standard.vectors.Vector import Vector
11
- from swarmauri_standard.documents.concrete.Document import Document
12
- from swarmauri_embedding_doc2vec.Doc2VecEmbedding import Doc2VecEmbedding
13
- from swarmauri_base.vector_stores.VectorStoreBase import VectorStoreBase
14
- from swarmauri_base.vector_stores.VectorStoreRetrieveMixin import VectorStoreRetrieveMixin
15
- from swarmauri_base.vector_stores.VectorStoreSaveLoadMixin import VectorStoreSaveLoadMixin
16
- from swarmauri_core.ComponentBase import ComponentBase
17
-
18
- @ComponentBase.register_type(VectorStoreBase, "RedisVectorStore")
19
- class RedisVectorStore(VectorStoreSaveLoadMixin, VectorStoreRetrieveMixin, VectorStoreBase):
20
- type: Literal["RedisVectorStore"] = "RedisVectorStore"
21
- index_name: str = "documents_index"
22
- embedding_dimension: int = 8000 # Default embedding dimension
23
-
24
- # Private attributes
25
- _embedder: Doc2VecEmbedding = PrivateAttr()
26
- _redis_client: Optional[redis.Redis] = PrivateAttr(default=None)
27
-
28
- # Configuration attributes with default values
29
- redis_host: str = "localhost"
30
- redis_port: int = 6379
31
- redis_password: Optional[str] = None
32
-
33
- def __init__(self, **kwargs):
34
- super().__init__(**kwargs)
35
- self._embedder = Doc2VecEmbedding(vector_size=self.embedding_dimension)
36
-
37
- # Initialize Redis client using class attributes
38
- self.connect()
39
-
40
- # Setup Redis Search index
41
- vector_field = VectorField(
42
- "embedding",
43
- "FLAT",
44
- {
45
- "TYPE": "FLOAT32",
46
- "DIM": self.embedding_dimension,
47
- "DISTANCE_METRIC": "COSINE"
48
- }
49
- )
50
- text_field = TextField("content")
51
-
52
- try:
53
- self._redis_client.ft(self.index_name).info()
54
- print(f"Index '{self.index_name}' exists.")
55
- except Exception:
56
- print(f"Index '{self.index_name}' does not exist. Creating index...")
57
- schema = (
58
- text_field,
59
- vector_field
60
- )
61
- definition = IndexDefinition(
62
- prefix=["doc:"],
63
- index_type=IndexType.HASH
64
- )
65
- self._redis_client.ft(self.index_name).create_index(
66
- fields=schema,
67
- definition=definition
68
- )
69
- print(f"Index '{self.index_name}' created successfully.")
70
-
71
-
72
- def connect(self) -> None:
73
- """
74
- Establishes a connection to the Redis server using class attributes.
75
- """
76
- try:
77
- self._redis_client = redis.Redis(
78
- host=self.redis_host,
79
- port=self.redis_port,
80
- password=self.redis_password,
81
- decode_responses=False, # For binary data
82
- )
83
- # Test the connection
84
- self._redis_client.ping()
85
- print("Connected to Redis successfully.")
86
- except Exception as e:
87
- print(f"Failed to connect to Redis: {e}")
88
- raise
89
-
90
- def disconnect(self) -> None:
91
- """
92
- Disconnects from the Redis server.
93
- """
94
- if self._redis_client:
95
- self._redis_client.close()
96
- self._redis_client = None
97
- print("Disconnected from Redis.")
98
-
99
-
100
- def _doc_key(self, document_id: str) -> str:
101
- return f"doc:{document_id}"
102
-
103
- def add_document(self, document: Document) -> None:
104
- doc = document
105
- pipeline = self._redis_client.pipeline()
106
-
107
- # Embed the document content
108
- embedding = self._embedder.fit_transform([doc.content])[0]
109
-
110
- if isinstance(embedding, Vector):
111
- embedding = embedding.value
112
- metadata = doc.metadata
113
-
114
- # print("METADATA ::::::::::::::::::::", metadata)
115
- doc_key = self._doc_key(doc.id)
116
- # print("DOC KEY ::::::::::::::::::::", doc_key)
117
- pipeline.hset(doc_key, mapping={
118
- "content": doc.content,
119
- "metadata": json.dumps(metadata), # Store metadata as JSON
120
- "embedding": np.array(embedding, dtype=np.float32).tobytes() # Convert embedding values to bytes
121
- })
122
- add = pipeline.execute()
123
-
124
- def add_documents(self, documents: List[Document]) -> None:
125
- pipeline = self._redis_client.pipeline()
126
- for doc in documents:
127
- if not doc.content:
128
- continue
129
- # Embed the document content
130
- embedding = self._embedder.fit_transform([doc.content])[0]
131
-
132
- if isinstance(embedding, Vector):
133
- embedding = embedding.value
134
- metadata={doc.metadata}
135
-
136
- doc_key = self._doc_key(doc.id)
137
- pipeline.hset(doc_key, mapping={
138
- "content": doc.content,
139
- "metadata": json.dumps(metadata),
140
- "embedding": np.array(embedding, dtype=np.float32).tobytes()
141
- })
142
- pipeline.execute()
143
-
144
- def get_document(self, id: str) -> Union[Document, None]:
145
-
146
- doc_key = self._doc_key(id)
147
- data = self._redis_client.hgetall(doc_key)
148
- if not data:
149
- return None
150
-
151
- metadata_raw = data.get(b"metadata", b"{}").decode("utf-8")
152
- metadata = json.loads(metadata_raw)
153
-
154
- content = data.get(b"content", b"").decode("utf-8")
155
- # print("METAAAAAAA ::::::::::::", metadata)
156
-
157
- embedding_bytes = data.get(b"embedding")
158
- if embedding_bytes:
159
- embedding = Vector(value=np.frombuffer(embedding_bytes, dtype=np.float32).tolist())
160
- else:
161
- embedding = None
162
- return Document(
163
- id=id,
164
- content=content,
165
- metadata=metadata,
166
- embedding=embedding
167
- )
168
-
169
- def get_all_documents(self) -> List[Document]:
170
- cursor = '0'
171
- documents = []
172
- while cursor != 0:
173
- cursor, keys = self._redis_client.scan(cursor=cursor, match="doc:*", count=1000)
174
- for key in keys:
175
- data = self._redis_client.hgetall(key)
176
- if not data:
177
- continue
178
- doc_id = key.decode("utf-8").split("doc:")[1]
179
- metadata_raw = data.get(b"metadata", b"{}").decode("utf-8")
180
- metadata = json.loads(metadata_raw)
181
- content = data.get(b"content", b"").decode("utf-8")
182
- embedding_bytes = data.get(b"embedding")
183
- if embedding_bytes:
184
- embedding = Vector(value=np.frombuffer(embedding_bytes, dtype=np.float32).tolist())
185
- else:
186
- embedding = None
187
- document = Document(
188
- id=doc_id,
189
- content=content,
190
- metadata=metadata,
191
- embedding=embedding
192
- )
193
- documents.append(document)
194
- return documents
195
-
196
- def delete_document(self, id: str) -> None:
197
- doc_key = self._doc_key(id)
198
- self._redis_client.delete(doc_key)
199
-
200
- def update_document(self, document: Document) -> None:
201
- doc_key = self._doc_key(document.id)
202
- if not self._redis_client.exists(doc_key):
203
- raise ValueError(f"Document with id {document.id} does not exist.")
204
- # Update the document by re-adding it
205
- self.add_documents([document])
206
-
207
-
208
- def cosine_similarity(self, vec1, vec2):
209
- dot_product = np.dot(vec1, vec2)
210
- norm_vec1 = np.linalg.norm(vec1)
211
- norm_vec2 = np.linalg.norm(vec2)
212
- if norm_vec1 == 0 or norm_vec2 == 0:
213
- return 0
214
- return dot_product / (norm_vec1 * norm_vec2)
215
-
216
-
217
- def retrieve(self, query: str, top_k: int = 5) -> List[Document]:
218
- query_vector = self._embedder.infer_vector(query)
219
-
220
- all_documents = self.get_all_documents()
221
- # print("ALL DOCUMENTS ::::::::::::::::::::", all_documents[:10])
222
- similarities = []
223
- for doc in all_documents:
224
- if doc.embedding is not None:
225
- doc_vector = doc.embedding
226
- # print("DOC VECTOR ::::::::::::::::::::", doc_vector.value[:10])
227
- similarity = self.cosine_similarity(query_vector.value, doc_vector.value)
228
- similarities.append((doc, similarity))
229
-
230
- similarities.sort(key=lambda x: x[1], reverse=True)
231
- # print("SIMILARITIES ::::::::::::::::::::", similarities[:10])
232
- top_documents = [doc for doc, _ in similarities[:top_k]]
233
- # print(f"Found {len(top_documents)} similar documents.")
234
- return top_documents
235
-
236
-
237
- class Config:
238
- extra = 'allow'
1
+ import json
2
+ from typing import List, Literal, Optional, Union
3
+
4
+ import numpy as np
5
+ import redis
6
+ from pydantic import PrivateAttr
7
+ from redis.commands.search.field import TextField, VectorField
8
+ from redis.commands.search.indexDefinition import IndexDefinition, IndexType
9
+ from swarmauri_base.vector_stores.VectorStoreBase import VectorStoreBase
10
+ from swarmauri_base.vector_stores.VectorStoreRetrieveMixin import (
11
+ VectorStoreRetrieveMixin,
12
+ )
13
+ from swarmauri_base.vector_stores.VectorStoreSaveLoadMixin import (
14
+ VectorStoreSaveLoadMixin,
15
+ )
16
+ from swarmauri_base.ComponentBase import ComponentBase
17
+ from swarmauri_embedding_doc2vec.Doc2VecEmbedding import Doc2VecEmbedding
18
+ from swarmauri_standard.documents.Document import Document
19
+ from swarmauri_standard.vectors.Vector import Vector
20
+
21
+
22
+ @ComponentBase.register_type(VectorStoreBase, "RedisVectorStore")
23
+ class RedisVectorStore(
24
+ VectorStoreSaveLoadMixin, VectorStoreRetrieveMixin, VectorStoreBase
25
+ ):
26
+ type: Literal["RedisVectorStore"] = "RedisVectorStore"
27
+ index_name: str = "documents_index"
28
+ embedding_dimension: int = 8000 # Default embedding dimension
29
+
30
+ # Private attributes
31
+ _embedder: Doc2VecEmbedding = PrivateAttr()
32
+ _redis_client: Optional[redis.Redis] = PrivateAttr(default=None)
33
+
34
+ # Configuration attributes with default values
35
+ redis_host: str = "localhost"
36
+ redis_port: int = 6379
37
+ redis_password: Optional[str] = None
38
+
39
+ def __init__(self, **kwargs):
40
+ super().__init__(**kwargs)
41
+ self._embedder = Doc2VecEmbedding(vector_size=self.embedding_dimension)
42
+
43
+ # Initialize Redis client using class attributes
44
+ self.connect()
45
+
46
+ # Setup Redis Search index
47
+ vector_field = VectorField(
48
+ "embedding",
49
+ "FLAT",
50
+ {
51
+ "TYPE": "FLOAT32",
52
+ "DIM": self.embedding_dimension,
53
+ "DISTANCE_METRIC": "COSINE",
54
+ },
55
+ )
56
+ text_field = TextField("content")
57
+
58
+ try:
59
+ self._redis_client.ft(self.index_name).info()
60
+ print(f"Index '{self.index_name}' exists.")
61
+ except Exception:
62
+ print(f"Index '{self.index_name}' does not exist. Creating index...")
63
+ schema = (text_field, vector_field)
64
+ definition = IndexDefinition(prefix=["doc:"], index_type=IndexType.HASH)
65
+ self._redis_client.ft(self.index_name).create_index(
66
+ fields=schema, definition=definition
67
+ )
68
+ print(f"Index '{self.index_name}' created successfully.")
69
+
70
+ def connect(self) -> None:
71
+ """
72
+ Establishes a connection to the Redis server using class attributes.
73
+ """
74
+ try:
75
+ self._redis_client = redis.Redis(
76
+ host=self.redis_host,
77
+ port=self.redis_port,
78
+ password=self.redis_password,
79
+ decode_responses=False, # For binary data
80
+ )
81
+ # Test the connection
82
+ self._redis_client.ping()
83
+ print("Connected to Redis successfully.")
84
+ except Exception as e:
85
+ print(f"Failed to connect to Redis: {e}")
86
+ raise
87
+
88
+ def disconnect(self) -> None:
89
+ """
90
+ Disconnects from the Redis server.
91
+ """
92
+ if self._redis_client:
93
+ self._redis_client.close()
94
+ self._redis_client = None
95
+ print("Disconnected from Redis.")
96
+
97
+ def _doc_key(self, document_id: str) -> str:
98
+ return f"doc:{document_id}"
99
+
100
+ def add_document(self, document: Document) -> None:
101
+ doc = document
102
+ pipeline = self._redis_client.pipeline()
103
+
104
+ # Embed the document content
105
+ embedding = self._embedder.fit_transform([doc.content])[0]
106
+
107
+ if isinstance(embedding, Vector):
108
+ embedding = embedding.value
109
+ metadata = doc.metadata
110
+
111
+ # print("METADATA ::::::::::::::::::::", metadata)
112
+ doc_key = self._doc_key(doc.id)
113
+ # print("DOC KEY ::::::::::::::::::::", doc_key)
114
+ pipeline.hset(
115
+ doc_key,
116
+ mapping={
117
+ "content": doc.content,
118
+ "metadata": json.dumps(metadata), # Store metadata as JSON
119
+ "embedding": np.array(
120
+ embedding, dtype=np.float32
121
+ ).tobytes(), # Convert embedding values to bytes
122
+ },
123
+ )
124
+ pipeline.execute()
125
+
126
+ def add_documents(self, documents: List[Document]) -> None:
127
+ pipeline = self._redis_client.pipeline()
128
+ for doc in documents:
129
+ if not doc.content:
130
+ continue
131
+ # Embed the document content
132
+ embedding = self._embedder.fit_transform([doc.content])[0]
133
+
134
+ if isinstance(embedding, Vector):
135
+ embedding = embedding.value
136
+ metadata = {doc.metadata}
137
+
138
+ doc_key = self._doc_key(doc.id)
139
+ pipeline.hset(
140
+ doc_key,
141
+ mapping={
142
+ "content": doc.content,
143
+ "metadata": json.dumps(metadata),
144
+ "embedding": np.array(embedding, dtype=np.float32).tobytes(),
145
+ },
146
+ )
147
+ pipeline.execute()
148
+
149
+ def get_document(self, id: str) -> Union[Document, None]:
150
+ doc_key = self._doc_key(id)
151
+ data = self._redis_client.hgetall(doc_key)
152
+ if not data:
153
+ return None
154
+
155
+ metadata_raw = data.get(b"metadata", b"{}").decode("utf-8")
156
+ metadata = json.loads(metadata_raw)
157
+
158
+ content = data.get(b"content", b"").decode("utf-8")
159
+ # print("METAAAAAAA ::::::::::::", metadata)
160
+
161
+ embedding_bytes = data.get(b"embedding")
162
+ if embedding_bytes:
163
+ embedding = Vector(
164
+ value=np.frombuffer(embedding_bytes, dtype=np.float32).tolist()
165
+ )
166
+ else:
167
+ embedding = None
168
+ return Document(id=id, content=content, metadata=metadata, embedding=embedding)
169
+
170
+ def get_all_documents(self) -> List[Document]:
171
+ cursor = "0"
172
+ documents = []
173
+ while cursor != 0:
174
+ cursor, keys = self._redis_client.scan(
175
+ cursor=cursor, match="doc:*", count=1000
176
+ )
177
+ for key in keys:
178
+ data = self._redis_client.hgetall(key)
179
+ if not data:
180
+ continue
181
+ doc_id = key.decode("utf-8").split("doc:")[1]
182
+ metadata_raw = data.get(b"metadata", b"{}").decode("utf-8")
183
+ metadata = json.loads(metadata_raw)
184
+ content = data.get(b"content", b"").decode("utf-8")
185
+ embedding_bytes = data.get(b"embedding")
186
+ if embedding_bytes:
187
+ embedding = Vector(
188
+ value=np.frombuffer(embedding_bytes, dtype=np.float32).tolist()
189
+ )
190
+ else:
191
+ embedding = None
192
+ document = Document(
193
+ id=doc_id, content=content, metadata=metadata, embedding=embedding
194
+ )
195
+ documents.append(document)
196
+ return documents
197
+
198
+ def delete_document(self, id: str) -> None:
199
+ doc_key = self._doc_key(id)
200
+ self._redis_client.delete(doc_key)
201
+
202
+ def update_document(self, document: Document) -> None:
203
+ doc_key = self._doc_key(document.id)
204
+ if not self._redis_client.exists(doc_key):
205
+ raise ValueError(f"Document with id {document.id} does not exist.")
206
+ # Update the document by re-adding it
207
+ self.add_documents([document])
208
+
209
+ def cosine_similarity(self, vec1, vec2):
210
+ dot_product = np.dot(vec1, vec2)
211
+ norm_vec1 = np.linalg.norm(vec1)
212
+ norm_vec2 = np.linalg.norm(vec2)
213
+ if norm_vec1 == 0 or norm_vec2 == 0:
214
+ return 0
215
+ return dot_product / (norm_vec1 * norm_vec2)
216
+
217
+ def retrieve(self, query: str, top_k: int = 5) -> List[Document]:
218
+ query_vector = self._embedder.infer_vector(query)
219
+
220
+ all_documents = self.get_all_documents()
221
+ # print("ALL DOCUMENTS ::::::::::::::::::::", all_documents[:10])
222
+ similarities = []
223
+ for doc in all_documents:
224
+ if doc.embedding is not None:
225
+ doc_vector = doc.embedding
226
+ # print("DOC VECTOR ::::::::::::::::::::", doc_vector.value[:10])
227
+ similarity = self.cosine_similarity(
228
+ query_vector.value, doc_vector.value
229
+ )
230
+ similarities.append((doc, similarity))
231
+
232
+ similarities.sort(key=lambda x: x[1], reverse=True)
233
+ # print("SIMILARITIES ::::::::::::::::::::", similarities[:10])
234
+ top_documents = [doc for doc, _ in similarities[:top_k]]
235
+ # print(f"Found {len(top_documents)} similar documents.")
236
+ return top_documents
@@ -0,0 +1,17 @@
1
+ from .RedisVectorStore import RedisVectorStore
2
+ from .RedisDocumentRetriever import RedisDocumentRetriever
3
+
4
+ __all__ = ["RedisVectorStore", "RedisDocumentRetriever"]
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_redis")
15
+ except PackageNotFoundError:
16
+ # If the package is not installed (for example, during development)
17
+ __version__ = "0.0.0"
@@ -1,20 +0,0 @@
1
- Metadata-Version: 2.3
2
- Name: swarmauri_vectorstore_redis
3
- Version: 0.6.0.dev154
4
- Summary: Swarmauri Redis 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: redis (>=4.0,<5.0)
15
- Requires-Dist: swarmauri_base (>=0.6.0.dev154,<0.7.0)
16
- Requires-Dist: swarmauri_core (>=0.6.0.dev154,<0.7.0)
17
- Project-URL: Repository, http://github.com/swarmauri/swarmauri-sdk
18
- Description-Content-Type: text/markdown
19
-
20
- # Swarmauri Example Community Package
@@ -1 +0,0 @@
1
- # Swarmauri Example Community Package
@@ -1,62 +0,0 @@
1
- [tool.poetry]
2
- name = "swarmauri_vectorstore_redis"
3
- version = "0.6.0.dev154"
4
- description = "Swarmauri Redis 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.dev154"}
21
- swarmauri_base = {version = "^0.6.0.dev154"}
22
-
23
- # Dependencies
24
- redis = "^4.0"
25
-
26
-
27
- [tool.poetry.group.dev.dependencies]
28
- flake8 = "^7.0"
29
- pytest = "^8.0"
30
- pytest-asyncio = ">=0.24.0"
31
- pytest-xdist = "^3.6.1"
32
- pytest-json-report = "^1.5.0"
33
- python-dotenv = "*"
34
- requests = "^2.32.3"
35
-
36
- [build-system]
37
- requires = ["poetry-core>=1.0.0"]
38
- build-backend = "poetry.core.masonry.api"
39
-
40
- [tool.pytest.ini_options]
41
- norecursedirs = ["combined", "scripts"]
42
-
43
- markers = [
44
- "test: standard test",
45
- "unit: Unit tests",
46
- "integration: Integration tests",
47
- "acceptance: Acceptance tests",
48
- "experimental: Experimental tests"
49
- ]
50
- log_cli = true
51
- log_cli_level = "INFO"
52
- log_cli_format = "%(asctime)s [%(levelname)s] %(message)s"
53
- log_cli_date_format = "%Y-%m-%d %H:%M:%S"
54
- asyncio_default_fixture_loop_scope = "function"
55
-
56
- [tool.poetry.plugins."swarmauri.vector_stores"]
57
- RedisVectorStore = "swarmauri_vectorstore_redis.RedisVectorStore:RedisVectorStore"
58
-
59
- [tool.poetry.plugins."swarmauri.retrievers"]
60
- RedisDocumentRetriever = "swarmauri_vectorstore_redis.RedisDocumentRetriever:RedisDocumentRetriever"
61
-
62
-
@@ -1,59 +0,0 @@
1
- from typing import List
2
- from redisearch import Client, Query
3
- from swarmauri_core.documents.IDocument import IDocument
4
- from swarmauri_standard.document_stores.ConcreteDocument import (
5
- ConcreteDocument,
6
- )
7
- from swarmauri_base.retrievers.DocumentRetrieverBase import DocumentRetrieverBase
8
- from swarmauri_core.ComponentBase import ComponentBase
9
-
10
- @ComponentBase.register_type(DocumentRetrieverBase, "RedisDocumentRetriever")
11
- class RedisDocumentRetriever(DocumentRetrieverBase):
12
- """
13
- A document retriever that fetches documents from a Redis store.
14
- """
15
-
16
- def __init__(self, redis_idx_name, redis_host, redis_port):
17
- """
18
- Initializes a new instance of RedisDocumentRetriever.
19
-
20
- Args:
21
- redis_client (Redis): An instance of the Redis client.
22
- """
23
- self._redis_client = None
24
- self._redis_idx_name = redis_idx_name
25
- self._redis_host = redis_host
26
- self._redis_port = redis_port
27
-
28
- @property
29
- def redis_client(self):
30
- """Lazily initialize and return the Redis client using a factory method."""
31
- if self._redis_client is None:
32
- self._redis_client = Client(
33
- self.redis_idx_name, host=self.redis_host, port=self.redis_port
34
- )
35
- return self._redis_client
36
-
37
- def retrieve(self, query: str, top_k: int = 5) -> List[IDocument]:
38
- """
39
- Retrieve the most relevant documents based on the given query.
40
-
41
- Args:
42
- query (str): The query string used for document retrieval.
43
- top_k (int, optional): The number of top relevant documents to retrieve. Defaults to 5.
44
-
45
- Returns:
46
- List[IDocument]: A list of the top_k most relevant documents.
47
- """
48
- query_result = self.redis_client.search(Query(query).paging(0, top_k))
49
-
50
- documents = [
51
- ConcreteDocument(
52
- doc_id=doc.id,
53
- content=doc.text, # Note: Adjust 'text' based on actual Redis document schema
54
- metadata=doc.__dict__, # Including full document fields and values in metadata
55
- )
56
- for doc in query_result.docs
57
- ]
58
-
59
- return documents
@@ -1,12 +0,0 @@
1
- from .RedisVectorStore import RedisVectorStore
2
-
3
- __version__ = "0.6.0.dev26"
4
- __long_desc__ = """
5
-
6
- # Swarmauri Redis VectorStore Plugin
7
-
8
- Visit us at: https://swarmauri.com
9
- Follow us at: https://github.com/swarmauri
10
- Star us at: https://github.com/swarmauri/swarmauri-sdk
11
-
12
- """