langchain-ydb 0.0.1__tar.gz

langchain_ydb-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

langchain_ydb-0.0.1/PKG-INFO

@@ -0,0 +1,216 @@
+Metadata-Version: 2.3
+Name: langchain-ydb
+Version: 0.0.1
+Summary: An integration package connecting YDB and LangChain
+Requires-Python: >=3.9,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: langchain-core (>=0.2.13,<0.4.0)
+Requires-Dist: ydb-dbapi (>=0.1.11,<0.2.0)
+Description-Content-Type: text/markdown
+
+# langchain-ydb
+---
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/ydb-platform/langchain-ydb/blob/main/LICENSE)
+[![Functional tests](https://github.com/ydb-platform/langchain-ydb/actions/workflows/tests.yml/badge.svg)](https://github.com/ydb-platform/langchain-ydb/actions/workflows/tests.yml)
+[![Lint checks](https://github.com/ydb-platform/langchain-ydb/actions/workflows/lint.yml/badge.svg)](https://github.com/ydb-platform/langchain-ydb/actions/workflows/lint.yml)
+
+LangChain's YDB integration (langchain-ydb) provides vector capabilities for working with [YDB](https://ydb.tech/).
+
+## Getting Started
+
+### Setting Up YDB
+
+Launch a YDB Docker container with:
+
+```shell
+docker run -d -p 2136:2136 --name ydb-langchain -e YDB_USE_IN_MEMORY_PDISKS=true -h localhost ydbplatform/local-ydb:trunk
+```
+
+### Installing the Package
+
+Install `langchain-ydb` package with:
+
+```bash
+pip install -U langchain-ydb
+```
+
+VectorStore works along with an embedding model, here using `langchain-openai` as example.
+
+```shell
+pip install langchain-openai
+export OPENAI_API_KEY=...
+```
+
+## Work with YDB Vector Store
+
+### Creating a Vector Store
+
+```python
+from langchain_openai import OpenAIEmbeddings
+from langchain_ydb.vectorstores import YDB, YDBSearchStrategy, YDBSettings
+
+
+settings = YDBSettings(
+    table="ydb_example",
+    strategy=YDBSearchStrategy.COSINE_SIMILARITY,
+)
+vector_store = YDB(
+    OpenAIEmbeddings(),
+    config=settings,
+)
+```
+
+### Add items to vector store
+
+Once you have created your vector store, you can interact with it by adding and deleting different items.
+
+Prepare documents to work with:
+
+```python
+from uuid import uuid4
+
+from langchain_core.documents import Document
+
+document_1 = Document(
+    page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
+    metadata={"source": "tweet"},
+)
+
+document_2 = Document(
+    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
+    metadata={"source": "news"},
+)
+
+document_3 = Document(
+    page_content="Building an exciting new project with LangChain - come check it out!",
+    metadata={"source": "tweet"},
+)
+
+document_4 = Document(
+    page_content="Robbers broke into the city bank and stole $1 million in cash.",
+    metadata={"source": "news"},
+)
+
+document_5 = Document(
+    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
+    metadata={"source": "tweet"},
+)
+
+document_6 = Document(
+    page_content="Is the new iPhone worth the price? Read this review to find out.",
+    metadata={"source": "website"},
+)
+
+document_7 = Document(
+    page_content="The top 10 soccer players in the world right now.",
+    metadata={"source": "website"},
+)
+
+document_8 = Document(
+    page_content="LangGraph is the best framework for building stateful, agentic applications!",
+    metadata={"source": "tweet"},
+)
+
+document_9 = Document(
+    page_content="The stock market is down 500 points today due to fears of a recession.",
+    metadata={"source": "news"},
+)
+
+document_10 = Document(
+    page_content="I have a bad feeling I am going to get deleted :(",
+    metadata={"source": "tweet"},
+)
+
+documents = [
+    document_1,
+    document_2,
+    document_3,
+    document_4,
+    document_5,
+    document_6,
+    document_7,
+    document_8,
+    document_9,
+    document_10,
+]
+uuids = [str(uuid4()) for _ in range(len(documents))]
+```
+
+You can add items to your vector store by using the `add_documents` function.
+
+```python
+vector_store.add_documents(documents=documents, ids=uuids)
+```
+
+### Delete items from vector store
+
+You can delete items from your vector store by ID using the `delete` function.
+
+```python
+vector_store.delete(ids=[uuids[-1]])
+```
+
+### Query vector store
+
+Once your vector store has been created and relevant documents have been added, you will likely want to query it during the execution of your chain or agent.
+
+#### Query directly
+
+**Similarity search**:
+
+A simple similarity search can be performed as follows:
+
+```python
+results = vector_store.similarity_search(
+    "LangChain provides abstractions to make working with LLMs easy", k=2
+)
+for res in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```
+
+**Similarity search with score**
+
+You can also perform a search with a score:
+
+```python
+results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=3)
+for res, score in results:
+    print(f"* [SIM={score:.3f}] {res.page_content} [{res.metadata}]")
+```
+
+#### Filtering
+
+You can search with filters as described below:
+
+```python
+results = vector_store.similarity_search_with_score(
+    "What did I eat for breakfast?",
+    k=4,
+    filter={"source": "tweet"},
+)
+for res, _ in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```
+
+#### Query by turning into retriever
+
+You can also transform the vector store into a retriever for easier usage in your chains.
+
+Here's how to transform your vector store into a retriever and then invoke the retriever with a simple query and filter.
+
+```python
+retriever = vector_store.as_retriever(
+    search_kwargs={"k": 2},
+)
+results = retriever.invoke(
+    "Stealing from the bank is a crime", filter={"source": "news"}
+)
+for res in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```
+

langchain_ydb-0.0.1/README.md

@@ -0,0 +1,200 @@
+# langchain-ydb
+---
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/ydb-platform/langchain-ydb/blob/main/LICENSE)
+[![Functional tests](https://github.com/ydb-platform/langchain-ydb/actions/workflows/tests.yml/badge.svg)](https://github.com/ydb-platform/langchain-ydb/actions/workflows/tests.yml)
+[![Lint checks](https://github.com/ydb-platform/langchain-ydb/actions/workflows/lint.yml/badge.svg)](https://github.com/ydb-platform/langchain-ydb/actions/workflows/lint.yml)
+
+LangChain's YDB integration (langchain-ydb) provides vector capabilities for working with [YDB](https://ydb.tech/).
+
+## Getting Started
+
+### Setting Up YDB
+
+Launch a YDB Docker container with:
+
+```shell
+docker run -d -p 2136:2136 --name ydb-langchain -e YDB_USE_IN_MEMORY_PDISKS=true -h localhost ydbplatform/local-ydb:trunk
+```
+
+### Installing the Package
+
+Install `langchain-ydb` package with:
+
+```bash
+pip install -U langchain-ydb
+```
+
+VectorStore works along with an embedding model, here using `langchain-openai` as example.
+
+```shell
+pip install langchain-openai
+export OPENAI_API_KEY=...
+```
+
+## Work with YDB Vector Store
+
+### Creating a Vector Store
+
+```python
+from langchain_openai import OpenAIEmbeddings
+from langchain_ydb.vectorstores import YDB, YDBSearchStrategy, YDBSettings
+
+
+settings = YDBSettings(
+    table="ydb_example",
+    strategy=YDBSearchStrategy.COSINE_SIMILARITY,
+)
+vector_store = YDB(
+    OpenAIEmbeddings(),
+    config=settings,
+)
+```
+
+### Add items to vector store
+
+Once you have created your vector store, you can interact with it by adding and deleting different items.
+
+Prepare documents to work with:
+
+```python
+from uuid import uuid4
+
+from langchain_core.documents import Document
+
+document_1 = Document(
+    page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
+    metadata={"source": "tweet"},
+)
+
+document_2 = Document(
+    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
+    metadata={"source": "news"},
+)
+
+document_3 = Document(
+    page_content="Building an exciting new project with LangChain - come check it out!",
+    metadata={"source": "tweet"},
+)
+
+document_4 = Document(
+    page_content="Robbers broke into the city bank and stole $1 million in cash.",
+    metadata={"source": "news"},
+)
+
+document_5 = Document(
+    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
+    metadata={"source": "tweet"},
+)
+
+document_6 = Document(
+    page_content="Is the new iPhone worth the price? Read this review to find out.",
+    metadata={"source": "website"},
+)
+
+document_7 = Document(
+    page_content="The top 10 soccer players in the world right now.",
+    metadata={"source": "website"},
+)
+
+document_8 = Document(
+    page_content="LangGraph is the best framework for building stateful, agentic applications!",
+    metadata={"source": "tweet"},
+)
+
+document_9 = Document(
+    page_content="The stock market is down 500 points today due to fears of a recession.",
+    metadata={"source": "news"},
+)
+
+document_10 = Document(
+    page_content="I have a bad feeling I am going to get deleted :(",
+    metadata={"source": "tweet"},
+)
+
+documents = [
+    document_1,
+    document_2,
+    document_3,
+    document_4,
+    document_5,
+    document_6,
+    document_7,
+    document_8,
+    document_9,
+    document_10,
+]
+uuids = [str(uuid4()) for _ in range(len(documents))]
+```
+
+You can add items to your vector store by using the `add_documents` function.
+
+```python
+vector_store.add_documents(documents=documents, ids=uuids)
+```
+
+### Delete items from vector store
+
+You can delete items from your vector store by ID using the `delete` function.
+
+```python
+vector_store.delete(ids=[uuids[-1]])
+```
+
+### Query vector store
+
+Once your vector store has been created and relevant documents have been added, you will likely want to query it during the execution of your chain or agent.
+
+#### Query directly
+
+**Similarity search**:
+
+A simple similarity search can be performed as follows:
+
+```python
+results = vector_store.similarity_search(
+    "LangChain provides abstractions to make working with LLMs easy", k=2
+)
+for res in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```
+
+**Similarity search with score**
+
+You can also perform a search with a score:
+
+```python
+results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=3)
+for res, score in results:
+    print(f"* [SIM={score:.3f}] {res.page_content} [{res.metadata}]")
+```
+
+#### Filtering
+
+You can search with filters as described below:
+
+```python
+results = vector_store.similarity_search_with_score(
+    "What did I eat for breakfast?",
+    k=4,
+    filter={"source": "tweet"},
+)
+for res, _ in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```
+
+#### Query by turning into retriever
+
+You can also transform the vector store into a retriever for easier usage in your chains.
+
+Here's how to transform your vector store into a retriever and then invoke the retriever with a simple query and filter.
+
+```python
+retriever = vector_store.as_retriever(
+    search_kwargs={"k": 2},
+)
+results = retriever.invoke(
+    "Stealing from the bank is a crime", filter={"source": "news"}
+)
+for res in results:
+    print(f"* {res.page_content} [{res.metadata}]")
+```

langchain_ydb-0.0.1/langchain_ydb/__init__.py

@@ -0,0 +1,7 @@
+from importlib import metadata
+
+try:
+    __version__ = metadata.version(__package__)
+except metadata.PackageNotFoundError:
+    # Case where package metadata is not available.
+    __version__ = ""

langchain_ydb-0.0.1/langchain_ydb/vectorstores.py

@@ -0,0 +1,464 @@
+from __future__ import annotations
+
+import enum
+import json
+import logging
+from dataclasses import dataclass, field
+from hashlib import sha1
+from typing import Any, Dict, Iterable, List, Optional
+
+from langchain_core.documents import Document
+from langchain_core.embeddings import Embeddings
+from langchain_core.vectorstores import VectorStore
+
+logger = logging.getLogger()
+
+
+class YDBSearchStrategy(str, enum.Enum):
+    """Enumerator of the search strategies."""
+
+    INNER_PRODUCT_SIMILARITY = "InnerProductSimilarity"
+    COSINE_SIMILARITY = "CosineSimilarity"
+    COSINE_DISTANCE = "CosineDistance"
+    MANHATTAN_DISTANCE = "ManhattanDistance"
+    EUCLIDEAN_DISTANCE = "EuclideanDistance"
+
+    def __str__(self) -> str:
+        return self.value
+
+
+DEFAULT_SEARCH_STRATEGY = YDBSearchStrategy.COSINE_SIMILARITY
+
+
+def _get_default_column_map_dict() -> Dict[str, str]:
+    return {
+        "id": "id",
+        "document": "document",
+        "embedding": "embedding",
+        "metadata": "metadata",
+    }
+
+
+@dataclass
+class YDBSettings:
+    """`YDB` client configuration.
+
+    Attribute:
+        host (str) : An URL to connect to YDB. Defaults to 'localhost'.
+        port (int) : URL port to connect with GRPC. Defaults to 2136.
+        username (str) : Username to login. Defaults to None.
+        password (str) : Password to login. Defaults to None.
+        secure (bool) : Connect to server over secure connection. Defaults to False.
+        database (str) : Database name to find the table. Defaults to '/local'.
+        table (str) : Table name to operate on. Defaults to 'langchain_store'.
+        column_map (Dict) : Column type map to project column name onto langchain
+                            semantics. Must have keys: `text`, `id`, `vector`,
+                            must be same size to number of columns. For example:
+                            .. code-block:: python
+
+                                {
+                                    'id': 'text_id',
+                                    'embedding': 'text_embedding',
+                                    'document': 'text_plain',
+                                    'metadata': 'metadata_dictionary_in_json',
+                                }
+
+                            Defaults to identity map.
+        strategy (str) : Strategy to perform search,
+                         supported are ('InnerProductSimilarity', 'CosineSimilarity',
+                         'CosineDistance', 'ManhattanDistance',
+                         'EuclideanDistance'). Defaults to 'CosineSimilarity'.
+                         Enum `YDBSearchStrategy` contains all of them.
+        drop_existing_table (bool) : Flag to drop existing table while init.
+                                     Defaults to False.
+    """
+
+    host: str = "localhost"
+    port: int = 2136
+
+    username: Optional[str] = None
+    password: Optional[str] = None
+
+    secure: bool = False
+
+    database: str = "/local"
+    table: str = "langchain_store"
+
+    column_map: Dict[str, str] = field(default_factory=_get_default_column_map_dict)
+
+    strategy: str = DEFAULT_SEARCH_STRATEGY
+
+    drop_existing_table: bool = False
+
+
+class YDB(VectorStore):
+    """`YDB` vector store.
+
+    To use, you should have the ``ydb-dbapi`` python package installed.
+    """
+
+    def __init__(
+        self,
+        embedding: Embeddings,
+        config: Optional[YDBSettings] = None,
+        **kwargs: Any,
+    ) -> None:
+        """YDB Wrapper to LangChain
+
+        Args:
+            embedding (Embeddings): embedding function to use
+            config (YDBSettings): Configuration to YDB DBAPI
+            kwargs (any): Other keyword arguments will pass into ydb-dbapi
+        """
+        try:
+            import ydb
+            import ydb_dbapi
+
+            self._ydb_lib = ydb
+        except ImportError:
+            raise ImportError(
+                "Could not import ydb-dbapi python package. "
+                "Please install it with `pip install ydb-dbapi`."
+            )
+
+        try:
+            from tqdm import tqdm
+
+            self.pgbar = tqdm
+        except ImportError:
+            # Just in case if tqdm is not installed
+            self.pgbar = lambda x, **kwargs: x
+
+        super().__init__()
+        if config is not None:
+            self.config = config
+        else:
+            self.config = YDBSettings()
+
+        assert self.config
+        assert self.config.host and self.config.port
+        assert self.config.database and self.config.table
+        assert self.config.column_map and self.config.strategy
+
+        self.sort_order = (
+            "DESC" if self.config.strategy.endswith("Similarity") else "ASC"
+        )
+
+        self.embedding_function = embedding
+
+        # Create a connection to ydb
+        self.connection = ydb_dbapi.connect(
+            host=self.config.host,
+            port=self.config.port,
+            database=self.config.database,
+            username=self.config.username,
+            password=self.config.password,
+            protocol="grpcs" if self.config.secure else "grpc",
+            **kwargs,
+        )
+
+        if self.config.drop_existing_table:
+            self.drop()
+
+        self._execute_query(self._prepare_scheme_query(), ddl=True)
+
+        self._insert_query = self._prepare_insert_query()
+
+    @property
+    def embeddings(self) -> Optional[Embeddings]:
+        """Access the query embedding object if available."""
+        return self.embedding_function
+
+    def _execute_query(
+        self,
+        query: str,
+        params: Optional[dict] = None,
+        ddl: bool = False,
+    ) -> List:
+        with self.connection.cursor() as cursor:
+            if ddl:
+                cursor.execute_scheme(query, params)
+            else:
+                cursor.execute(query, params)
+
+            if cursor.description is None:
+                return []
+
+            columns = [col[0] for col in cursor.description]
+
+            return [dict(zip(columns, row)) for row in cursor.fetchall()]
+
+    def _prepare_scheme_query(self) -> str:
+        """Create table schema
+        :param dim: dimension of embeddings
+        :param index_params: parameters used for index
+
+        This function returns a `CREATE TABLE` statement based on the value of
+        `self.config.index_type`.
+        If an index type is specified that index will be created, otherwise
+        no index will be created.
+        In the case of there being no index, a linear scan will be performed
+        when the embedding field is queried.
+        """
+        return f"""
+        CREATE TABLE IF NOT EXISTS `{self.config.table}` (
+            {self.config.column_map["id"]} Utf8,
+            {self.config.column_map["document"]} Utf8,
+            {self.config.column_map["embedding"]} String,
+            {self.config.column_map["metadata"]} Json,
+            PRIMARY KEY ({self.config.column_map["id"]})
+        );"""
+
+    def _escape_str(self, text: str) -> str:
+        escape = "\\"
+        chars_to_escape = ["\\", '"', "'"]
+        return "".join(
+            [ch if ch not in chars_to_escape else escape + ch for ch in text]
+        )
+
+    def _prepare_insert_query(self) -> str:
+        return f"""
+        DECLARE $id AS Utf8;
+        DECLARE $document as Utf8;
+        DECLARE $embedding as List<Float>;
+        DECLARE $metadata as Json;
+
+        UPSERT INTO `{self.config.table}`
+        (
+        {self.config.column_map["id"]},
+        {self.config.column_map["document"]},
+        {self.config.column_map["embedding"]},
+        {self.config.column_map["metadata"]}
+        )
+        VALUES
+        (
+        $id,
+        $document,
+        Untag(Knn::ToBinaryStringFloat($embedding), "FloatVector"),
+        $metadata
+        );
+        """
+
+    def _prepare_search_query(
+        self,
+        k: int,
+        filter: Optional[dict],
+    ) -> str:
+        where_statement = ""
+        if filter:
+            where_statement = "WHERE "
+            metadata_col = self.config.column_map["metadata"]
+            stmts = []
+            for key, value in filter.items():
+                stmts.append(f'JSON_VALUE({metadata_col}, "$.{key}") = "{value}"')
+
+            where_statement = f"WHERE {' AND '.join(stmts)}"
+
+        strategy = self.config.strategy
+        embedding_col = self.config.column_map["embedding"]
+
+        return f"""
+        DECLARE $embedding as List<Float>;
+
+        $TargetEmbedding = Knn::ToBinaryStringFloat($embedding);
+
+        SELECT
+            {self.config.column_map["id"]} as id,
+            {self.config.column_map["document"]} as document,
+            {self.config.column_map["metadata"]} as metadata,
+        Knn::{strategy}({embedding_col}, $TargetEmbedding) as score
+        FROM {self.config.table} {where_statement}
+        ORDER BY score
+        {self.sort_order}
+        LIMIT {k};
+        """
+
+    def _prepare_delete_query(self, ids: Optional[list[str]]) -> str:
+        query = f"DELETE FROM {self.config.table}"
+        if ids:
+            query += f" WHERE {self.config.column_map['id']} IN {str(ids)}"
+        return query
+
+    def add_texts(
+        self,
+        texts: Iterable[str],
+        metadatas: Optional[list[dict]] = None,
+        *,
+        ids: Optional[list[str]] = None,
+        **kwargs: Any,
+    ) -> list[str]:
+        """Run more texts through the embeddings and add to the vectorstore.
+
+        Args:
+            texts: Iterable of strings to add to the vectorstore.
+            metadatas: Optional list of metadatas associated with the texts.
+            ids: Optional list of IDs associated with the texts.
+            **kwargs: vectorstore specific parameters.
+                One of the kwargs should be `ids` which is a list of ids
+                associated with the texts.
+
+        Returns:
+            List of ids from adding the texts into the vectorstore.
+        """
+        texts_ = texts if isinstance(texts, (list, tuple)) else list(texts)
+
+        if ids is None:
+            ids = [sha1(t.encode("utf-8")).hexdigest() for t in texts_]
+
+        if metadatas and len(metadatas) != len(texts_):
+            msg = (
+                "The number of metadatas must match the number of texts."
+                f"Got {len(metadatas)} metadatas and {len(texts_)} texts."
+            )
+            raise ValueError(msg)
+
+        metadatas = metadatas if metadatas else [{} for _ in range(len(texts_))]
+
+        ydb = self._ydb_lib
+
+        for id, text, metadata in self.pgbar(
+            zip(ids, texts, metadatas),
+            desc="Inserting data...",
+            total=len(ids),
+        ):
+            embedding = self.embedding_function.embed_query(text)
+            self._execute_query(
+                self._insert_query,
+                {
+                    "$id": id,
+                    "$document": text,
+                    "$embedding": (embedding, ydb.ListType(ydb.PrimitiveType.Float)),
+                    "$metadata": (json.dumps(metadata), ydb.PrimitiveType.Json),
+                },
+            )
+
+        return ids
+
+    @classmethod
+    def from_texts(
+        cls,
+        texts: list[str],
+        embedding: Embeddings,
+        metadatas: Optional[list[dict]] = None,
+        *,
+        config: Optional[YDBSettings] = None,
+        ids: Optional[list[str]] = None,
+        **kwargs: Any,
+    ) -> YDB:
+        """Return YDB VectorStore initialized from texts and embeddings.
+
+        Args:
+            texts: Texts to add to the vectorstore.
+            embedding: Embedding function to use.
+            metadatas: Optional list of metadatas associated with the texts.
+                Default is None.
+            ids: Optional list of IDs associated with the texts.
+            kwargs: Additional keyword arguments.
+
+        Returns:
+            VectorStore: VectorStore initialized from texts and embeddings.
+        """
+        vs = cls(embedding, config, **kwargs)
+        vs.add_texts(texts=texts, metadatas=metadatas, ids=ids)
+        return vs
+
+    def delete(self, ids: Optional[list[str]] = None, **kwargs: Any) -> Optional[bool]:
+        """Delete by vector ID or other criteria.
+
+        Args:
+            ids: List of ids to delete. If None, delete all. Default is None.
+            **kwargs: Other keyword arguments that subclasses might use.
+
+        Returns:
+            Optional[bool]: True if deletion is successful,
+            False otherwise, None if not implemented.
+        """
+        query = self._prepare_delete_query(ids)
+        self._execute_query(query)
+        return True
+
+    def similarity_search(
+        self, query: str, k: int = 4, filter: Optional[dict] = None, **kwargs: Any
+    ) -> list[Document]:
+        """Return docs most similar to query.
+
+        Args:
+            query: Input text.
+            k: Number of Documents to return. Defaults to 4.
+            **kwargs: Arguments to pass to the search method.
+
+        Returns:
+            List of Documents most similar to the query.
+        """
+        embedding = self.embedding_function.embed_query(query)
+        return self.similarity_search_by_vector(embedding, k, filter=filter, **kwargs)
+
+    def similarity_search_by_vector(
+        self,
+        embedding: list[float],
+        k: int = 4,
+        filter: Optional[dict] = None,
+        **kwargs: Any,
+    ) -> list[Document]:
+        """Return docs most similar to embedding vector.
+
+        Args:
+            embedding: Embedding to look up documents similar to.
+            k: Number of Documents to return. Defaults to 4.
+            **kwargs: Arguments to pass to the search method.
+
+        Returns:
+            List of Documents most similar to the query vector.
+        """
+        ydb = self._ydb_lib
+        query = self._prepare_search_query(k, filter=filter)
+        res = self._execute_query(
+            query,
+            params={"$embedding": (embedding, ydb.ListType(ydb.PrimitiveType.Float))},
+        )
+        return [
+            Document(
+                page_content=row["document"],
+                metadata=json.loads(row["metadata"]),
+            )
+            for row in res
+        ]
+
+    def similarity_search_with_score(
+        self, query: str, k: int = 4, filter: Optional[dict] = None, **kwargs: Any
+    ) -> list[tuple[Document, float]]:
+        """Run similarity search with distance.
+
+        Args:
+            *args: Arguments to pass to the search method.
+            **kwargs: Arguments to pass to the search method.
+
+        Returns:
+            List of Tuples of (doc, similarity_score).
+        """
+        ydb = self._ydb_lib
+        embedding = self.embedding_function.embed_query(query)
+        query = self._prepare_search_query(k, filter=filter)
+        res = self._execute_query(
+            query,
+            params={"$embedding": (embedding, ydb.ListType(ydb.PrimitiveType.Float))},
+        )
+        return [
+            (
+                Document(
+                    page_content=row[self.config.column_map["document"]],
+                    metadata=json.loads(row["metadata"]),
+                ),
+                row["score"],
+            )
+            for row in res
+        ]
+
+    def drop(self) -> None:
+        """
+        Helper function: Drop data
+        """
+        self._execute_query(
+            f"DROP TABLE IF EXISTS `{self.config.table}`",
+            ddl=True,
+        )

langchain_ydb-0.0.1/pyproject.toml

@@ -0,0 +1,35 @@
+[project]
+name = "langchain-ydb"
+version = "0.0.1"  # AUTOVERSION
+description = "An integration package connecting YDB and LangChain"
+authors = []
+readme = "README.md"
+requires-python = ">=3.9,<4.0"
+dependencies = [
+    "langchain-core (>=0.2.13,<0.4.0)",
+    "ydb-dbapi (>=0.1.11,<0.2.0)"
+]
+
+
+[build-system]
+requires = ["poetry-core>=2.0.0,<3.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.3.5"
+ruff = "^0.11.2"
+mypy = "^1.15.0"
+pytest-asyncio = "^0.26.0"
+
+
+[tool.ruff.lint]
+select = [
+  "E",    # pycodestyle
+  "F",    # pyflakes
+  "I",    # isort
+]
+
+
+[tool.mypy]
+disable_error_code = ["import-untyped"]