pinecone: init pkg

libs/community/langchain_community/vectorstores/pinecone.py

@@ -7,6 +7,7 @@
 from typing import TYPE_CHECKING, Any, Callable, Iterable, List, Optional, Tuple, Union
 
 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.utils.iter import batch_iterate
@@ -41,24 +42,16 @@ def _is_pinecone_v3() -> bool:
     return version.parse(pinecone_client_version) >= version.parse("3.0.0.dev")
 
 
+@deprecated(
+    since="0.0.15", removal="0.2.0", alternative_import="langchain_pinecone.Pinecone"
+)
 class Pinecone(VectorStore):
     """`Pinecone` vector store.
 
     To use, you should have the ``pinecone-client`` python package installed.
 
-    Example:
-        .. code-block:: python
-
-            from langchain_community.vectorstores import Pinecone
-            from langchain_community.embeddings.openai import OpenAIEmbeddings
-            import pinecone
-
-            # The environment should be the one specified next to the API key
-            # in your Pinecone console
-            pinecone.init(api_key="***", environment="...")
-            index = pinecone.Index("langchain-demo")
-            embeddings = OpenAIEmbeddings()
-            vectorstore = Pinecone(index, embeddings, "text")
+    This version of Pinecone is deprecated. Please use `langchain_pinecone.Pinecone`
+    instead.
     """
 
     def __init__(

libs/partners/pinecone/.gitignore

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

libs/partners/pinecone/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 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/pinecone/Makefile

@@ -0,0 +1,61 @@
+.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_tests: TEST_FILE = tests/integration_tests/
+
+test integration_tests:
+	poetry run pytest $(TEST_FILE)
+
+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/pinecone --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
+lint_package: PYTHON_FILES=langchain_pinecone
+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_pinecone -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/pinecone/README.md

@@ -0,0 +1,27 @@
+# langchain-pinecone
+
+This package contains the LangChain integration with Pinecone.
+
+## Installation
+
+```bash
+pip install -U langchain-pinecone
+```
+
+And you should configure credentials by setting the following environment variables:
+
+- `PINECONE_API_KEY`
+- `PINECONE_INDEX_NAME`
+- `PINECONE_ENVIRONMENT`
+
+## Usage
+
+The `Pinecone` class exposes the connection to the Pinecone vector store.
+
+```python
+from langchain_pinecone import Pinecone
+
+embeddings = ... # use a LangChain Embeddings class
+
+vectorstore = Pinecone(embeddings=embeddings)
+```

libs/partners/pinecone/langchain_pinecone/__init__.py

@@ -0,0 +1,5 @@
+from langchain_pinecone.vectorstores import Pinecone
+
+__all__ = [
+    "Pinecone",
+]

libs/partners/pinecone/langchain_pinecone/_utilities.py

@@ -0,0 +1,71 @@
+from enum import Enum
+from typing import List, Union
+
+import numpy as np
+import simsimd  # type: ignore
+
+Matrix = Union[List[List[float]], List[np.ndarray], np.ndarray]
+
+
+class DistanceStrategy(str, Enum):
+    """Enumerator of the Distance strategies for calculating distances
+    between vectors."""
+
+    EUCLIDEAN_DISTANCE = "EUCLIDEAN_DISTANCE"
+    MAX_INNER_PRODUCT = "MAX_INNER_PRODUCT"
+    COSINE = "COSINE"
+
+
+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
+
+
+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}."
+        )
+
+    X = np.array(X, dtype=np.float32)
+    Y = np.array(Y, dtype=np.float32)
+    Z = 1 - simsimd.cdist(X, Y, metric="cosine")
+    if isinstance(Z, float):
+        return np.array([Z])
+    return Z