partners: MongoDB Partner Package -- Porting MongoDBAtlasVectorSearch

docs/docs/integrations/providers/mongodb_atlas.mdx

@@ -8,17 +8,17 @@
 
 See [detail configuration instructions](/docs/integrations/vectorstores/mongodb_atlas).
 
-We need to install `pymongo` python package.
+We need to install `langchain-mongodb` python package.
 
 ```bash
-pip install pymongo
+pip install langchain-mongodb
 ```
 
 ## Vector Store
 
 See a [usage example](/docs/integrations/vectorstores/mongodb_atlas).
 
 ```python
-from langchain_community.vectorstores import MongoDBAtlasVectorSearch
+from langchain_mongodb import MongoDBAtlasVectorSearch
 ```
 

libs/community/langchain_community/vectorstores/mongodb_atlas.py

@@ -16,6 +16,7 @@
 )
 
 import numpy as np
+from langchain_core._api.deprecation import deprecated
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
 from langchain_core.vectorstores import VectorStore
@@ -32,6 +33,11 @@
 DEFAULT_INSERT_BATCH_SIZE = 100
 
 
+@deprecated(
+    since="0.0.25",
+    removal="0.2.0",
+    alternative_import="langchain_mongodb.MongoDBAtlasVectorSearch",
+)
 class MongoDBAtlasVectorSearch(VectorStore):
     """`MongoDB Atlas Vector Search` vector store.
 

libs/partners/mongodb/.gitignore

@@ -0,0 +1 @@
+__pycache__

libs/partners/mongodb/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

libs/partners/mongodb/Makefile

@@ -0,0 +1,57 @@
+.PHONY: all format lint test tests integration_tests docker_tests help extended_tests
+
+# Default target executed when no arguments are given to make.
+all: help
+
+# Define a variable for the test file path.
+TEST_FILE ?= tests/unit_tests/
+integration_test integration_tests: TEST_FILE=tests/integration_tests/
+
+test tests integration_test integration_tests:
+	poetry run pytest $(TEST_FILE)
+
+
+######################
+# LINTING AND FORMATTING
+######################
+
+# Define a variable for Python and notebook files.
+PYTHON_FILES=.
+MYPY_CACHE=.mypy_cache
+lint format: PYTHON_FILES=.
+lint_diff format_diff: PYTHON_FILES=$(shell git diff --relative=libs/partners/mongodb --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
+lint_package: PYTHON_FILES=langchain_mongodb
+lint_tests: PYTHON_FILES=tests
+lint_tests: MYPY_CACHE=.mypy_cache_test
+
+lint lint_diff lint_package lint_tests:
+	poetry run ruff .
+	poetry run ruff format $(PYTHON_FILES) --diff
+	poetry run ruff --select I $(PYTHON_FILES)
+	mkdir $(MYPY_CACHE); poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
+
+format format_diff:
+	poetry run ruff format $(PYTHON_FILES)
+	poetry run ruff --select I --fix $(PYTHON_FILES)
+
+spell_check:
+	poetry run codespell --toml pyproject.toml
+
+spell_fix:
+	poetry run codespell --toml pyproject.toml -w
+
+check_imports: $(shell find langchain_mongodb -name '*.py')
+	poetry run python ./scripts/check_imports.py $^
+
+######################
+# HELP
+######################
+
+help:
+	@echo '----'
+	@echo 'check_imports				- check imports'
+	@echo 'format                       - run code formatters'
+	@echo 'lint                         - run linters'
+	@echo 'test                         - run unit tests'
+	@echo 'tests                        - run unit tests'
+	@echo 'test TEST_FILE=<test_file>   - run all tests in file'

libs/partners/mongodb/README.md

@@ -0,0 +1,40 @@
+# langchain-mongodb
+
+# Installation
+```
+pip install -U langchain-mongodb
+```
+
+# Usage
+- See [integrations doc](../../../docs/docs/integrations/vectorstores/mongodb.ipynb) for more in-depth usage instructions.
+- See [Getting Started with the LangChain Integration](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-integrations/langchain/#get-started-with-the-langchain-integration) for a walkthrough on using your first LangChain implementation with MongoDB Atlas.
+
+## Using MongoDBAtlasVectorSearch
+```python
+from langchain_mongodb import MongoDBAtlasVectorSearch
+
+# Pull MongoDB Atlas URI from environment variables
+MONGODB_ATLAS_CLUSTER_URI = os.environ.get("MONGODB_ATLAS_CLUSTER_URI")
+
+DB_NAME = "langchain_db"
+COLLECTION_NAME = "test"
+ATLAS_VECTOR_SEARCH_INDEX_NAME = "index_name"
+MONGODB_COLLECTION = client[DB_NAME][COLLECITON_NAME]
+
+# Create the vector search via `from_connection_string`
+vector_search = MongoDBAtlasVectorSearch.from_connection_string(
+    MONGODB_ATLAS_CLUSTER_URI,
+    DB_NAME + "." + COLLECTION_NAME,
+    OpenAIEmbeddings(disallowed_special=()),
+    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
+)
+
+# Initialize MongoDB python client
+client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)
+# Create the vector search via instantiation
+vector_search_2 = MongoDBAtlasVectorSearch(
+    collection=MONGODB_COLLECTION,
+    embeddings=OpenAIEmbeddings(disallowed_special=()),
+    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
+)
+```

libs/partners/mongodb/langchain_mongodb/__init__.py

@@ -0,0 +1,7 @@
+from langchain_mongodb.vectorstores import (
+    MongoDBAtlasVectorSearch,
+)
+
+__all__ = [
+    "MongoDBAtlasVectorSearch",
+]

libs/partners/mongodb/langchain_mongodb/utils.py

@@ -0,0 +1,87 @@
+"""
+Tools for the Maximal Marginal Relevance (MMR) reranking.
+Duplicated from langchain_community to avoid cross-dependencies.
+
+Functions "maximal_marginal_relevance" and "cosine_similarity"
+are duplicated in this utility respectively from modules:
+    - "libs/community/langchain_community/vectorstores/utils.py"
+    - "libs/community/langchain_community/utils/math.py"
+"""
+
+import logging
+from typing import List, Union
+
+import numpy as np
+
+logger = logging.getLogger(__name__)
+
+Matrix = Union[List[List[float]], List[np.ndarray], np.ndarray]
+
+
+def cosine_similarity(X: Matrix, Y: Matrix) -> np.ndarray:
+    """Row-wise cosine similarity between two equal-width matrices."""
+    if len(X) == 0 or len(Y) == 0:
+        return np.array([])
+
+    X = np.array(X)
+    Y = np.array(Y)
+    if X.shape[1] != Y.shape[1]:
+        raise ValueError(
+            f"Number of columns in X and Y must be the same. X has shape {X.shape} "
+            f"and Y has shape {Y.shape}."
+        )
+    try:
+        import simsimd as simd  # type: ignore
+
+        X = np.array(X, dtype=np.float32)
+        Y = np.array(Y, dtype=np.float32)
+        Z = 1 - simd.cdist(X, Y, metric="cosine")
+        if isinstance(Z, float):
+            return np.array([Z])
+        return Z
+    except ImportError:
+        logger.info(
+            "Unable to import simsimd, defaulting to NumPy implementation. If you want "
+            "to use simsimd please install with `pip install simsimd`."
+        )
+        X_norm = np.linalg.norm(X, axis=1)
+        Y_norm = np.linalg.norm(Y, axis=1)
+        # Ignore divide by zero errors run time warnings as those are handled below.
+        with np.errstate(divide="ignore", invalid="ignore"):
+            similarity = np.dot(X, Y.T) / np.outer(X_norm, Y_norm)
+        similarity[np.isnan(similarity) | np.isinf(similarity)] = 0.0
+        return similarity
+
+
+def maximal_marginal_relevance(
+    query_embedding: np.ndarray,
+    embedding_list: list,
+    lambda_mult: float = 0.5,
+    k: int = 4,
+) -> List[int]:
+    """Calculate maximal marginal relevance."""
+    if min(k, len(embedding_list)) <= 0:
+        return []
+    if query_embedding.ndim == 1:
+        query_embedding = np.expand_dims(query_embedding, axis=0)
+    similarity_to_query = cosine_similarity(query_embedding, embedding_list)[0]
+    most_similar = int(np.argmax(similarity_to_query))
+    idxs = [most_similar]
+    selected = np.array([embedding_list[most_similar]])
+    while len(idxs) < min(k, len(embedding_list)):
+        best_score = -np.inf
+        idx_to_add = -1
+        similarity_to_selected = cosine_similarity(embedding_list, selected)
+        for i, query_score in enumerate(similarity_to_query):
+            if i in idxs:
+                continue
+            redundant_score = max(similarity_to_selected[i])
+            equation_score = (
+                lambda_mult * query_score - (1 - lambda_mult) * redundant_score
+            )
+            if equation_score > best_score:
+                best_score = equation_score
+                idx_to_add = i
+        idxs.append(idx_to_add)
+        selected = np.append(selected, [embedding_list[idx_to_add]], axis=0)
+    return idxs