langchain-b12 0.1.0__tar.gz

langchain_b12-0.1.0/.gitignore

@@ -0,0 +1,105 @@
+# These are some examples of commonly ignored file patterns.
+# You should customize this list as applicable to your project.
+# Learn more about .gitignore:
+#     https://www.atlassian.com/git/tutorials/saving-changes/gitignore
+
+pyrightconfig.json
+/data
+/outputs
+
+# google
+service_account.json
+
+# folder for experimental scripts you don't want to commit
+dev/
+
+# postgres
+*.sql
+initdb
+postgres_data
+
+# minio
+minio_data
+
+# langchain
+.langgraph_api/
+
+# coverage
+coverage.xml
+.coverage
+
+*.egg-info
+*.env
+*.bin
+*.sqlite3
+.vscode/
+
+# Node artifact files
+node_modules/
+dist/
+
+# Compiled Java class files
+*.class
+
+# Compiled Python bytecode
+*.py[cod]
+
+# Log files
+*.log
+logs
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+# Package files
+*.jar
+
+# Maven
+target/
+dist/
+
+# JetBrains IDE
+.idea/
+
+# Unit test reports
+TEST*.xml
+
+# Generated by MacOS
+.DS_Store
+
+# Generated by Windows
+Thumbs.db
+
+# Applications
+*.app
+*.exe
+*.war
+
+# Large media files
+*.mp4
+*.tiff
+*.avi
+*.flv
+*.mov
+*.wmv
+
+notebooks/.ipynb_checkpoints/
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?
+
+# LangGraph API
+.next/
+next-env.d.ts
+
+# Python
+__pycache__/
+*.local

langchain_b12-0.1.0/.python-version

@@ -0,0 +1 @@
+3.12

langchain_b12-0.1.0/.vscode/extensions.json

@@ -0,0 +1,22 @@
+{
+	// See https://go.microsoft.com/fwlink/?LinkId=827846 to learn about workspace recommendations.
+	// Extension identifier format: ${publisher}.${name}. Example: vscode.csharp
+
+	// List of extensions which should be recommended for users of this workspace.
+	"recommendations": [
+	"charliermarsh.ruff",
+	"github.copilot",
+	"github.copilot-chat",
+	"ms-python.python",
+	"ms-python.vscode-pylance",
+	"ms-vscode-remote.remote-containers",
+	"ms-vscode-remote.remote-ssh",
+	"ms-vscode-remote.remote-ssh-edit",
+	"ms-vscode.remote-explorer",
+	"sonarsource.sonarlint-vscode",
+	],
+	// List of extensions recommended by VS Code that should not be recommended for users of this workspace.
+	"unwantedRecommendations": [
+
+	]
+}

langchain_b12-0.1.0/Makefile

@@ -0,0 +1,5 @@
+install:
+	uv sync --frozen --all-groups
+
+test:
+	uv run pytest

langchain_b12-0.1.0/PKG-INFO

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: langchain-b12
+Version: 0.1.0
+Summary: A reusable collection of tools and implementations for Langchain
+Author-email: Vincent Min <vincent.min@b12-consulting.com>
+Requires-Python: >=3.11
+Requires-Dist: langchain-core>=0.3.60
+Description-Content-Type: text/markdown
+
+# Langchain B12
+
+This repo hosts a collection of custom LangChain components.
+
+- ChatGenAI converts a sequence of LangChain messages to Google GenAI Content objects and vice versa.
+
+## Installation
+
+To install this package, run
+```bash
+pip install langchain-b12
+```
+
+Some components rely on additional packages that may be installed as extras.
+For example, to use the Google chatmodel `ChatGenAI`, you can run
+```bash
+pip install langchain-b12[google]
+```
+
+## Components
+
+The repo contains these components:
+
+- `ChatGenAI`: An implementation of `BaseChatModel` that uses the `google-genai` package. Note that `langchain-google-genai` and `langchain-google-vertexai` exist, but neither uses the latest and recommended `google-genai` package.
+- `GenAIEmbeddings`: An implementation of `Embeddings` that uses the `google-genai` package.
+
+## Comments
+
+This repo exists for easy reuse and extension of custom LangChain components.
+When appropriate, we will create PRs to merge these components directly into LangChain.

langchain_b12-0.1.0/README.md

@@ -0,0 +1,30 @@
+# Langchain B12
+
+This repo hosts a collection of custom LangChain components.
+
+- ChatGenAI converts a sequence of LangChain messages to Google GenAI Content objects and vice versa.
+
+## Installation
+
+To install this package, run
+```bash
+pip install langchain-b12
+```
+
+Some components rely on additional packages that may be installed as extras.
+For example, to use the Google chatmodel `ChatGenAI`, you can run
+```bash
+pip install langchain-b12[google]
+```
+
+## Components
+
+The repo contains these components:
+
+- `ChatGenAI`: An implementation of `BaseChatModel` that uses the `google-genai` package. Note that `langchain-google-genai` and `langchain-google-vertexai` exist, but neither uses the latest and recommended `google-genai` package.
+- `GenAIEmbeddings`: An implementation of `Embeddings` that uses the `google-genai` package.
+
+## Comments
+
+This repo exists for easy reuse and extension of custom LangChain components.
+When appropriate, we will create PRs to merge these components directly into LangChain.

langchain_b12-0.1.0/pyproject.toml

@@ -0,0 +1,61 @@
+[project]
+name = "langchain-b12"
+version = "0.1.0"
+description = "A reusable collection of tools and implementations for Langchain"
+readme = "README.md"
+authors = [
+    { name = "Vincent Min", email = "vincent.min@b12-consulting.com" }
+]
+requires-python = ">=3.11"
+dependencies = [
+    "langchain-core>=0.3.60",
+]
+
+[dependency-groups]
+google = [
+    "google-genai>=1.16.1",
+]
+dev = [
+    "pytest>=8.3.5",
+]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.ruff]
+line-length = 88
+target-version = "py312"
+exclude = ["__pycache__", "**/scripts/*", "**/notebooks/*"]
+show-fixes = true
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+line-ending = "auto"
+
+[tool.ruff.lint]
+select = [
+    "F",   # Pyflakes
+    "W",   # pycodestyle
+    "E",   # pycodestyle
+    "I",   # isort
+    "UP",  # pyupgrade
+    "PL",  # Pylint
+    "T201", # Print Statement
+]
+ignore = [
+    # Ignore complexity
+    "C901", "PLR0911", "PLR0912", "PLR0913", "PLR0915",
+    "EM101",
+    "PLR2004",
+    # Ignore f literals in exceptions
+    "EM102",
+]
+
+# Add Pyright configuration
+[tool.pyright]
+reportUnknownParameterType = false
+reportUnknownMemberType = false
+reportUnknownArgumentType = false
+

langchain_b12-0.1.0/src/langchain_b12/genai/embeddings.py

@@ -0,0 +1,99 @@
+import os
+
+from google.genai import Client
+from google.oauth2 import service_account
+from langchain_core.embeddings import Embeddings
+from pydantic import BaseModel, ConfigDict, Field
+
+
+class GenAIEmbeddings(Embeddings, BaseModel):
+    """Embeddings implementation using `google-genai`."""
+
+    model_name: str = Field(default="text-multilingual-embedding-002")
+    client: Client = Field(
+        default_factory=lambda: Client(
+            credentials=service_account.Credentials.from_service_account_file(
+                filename=os.getenv("GOOGLE_APPLICATION_CREDENTIALS"),
+                scopes=["https://www.googleapis.com/auth/cloud-platform"],
+            )
+        ),
+        exclude=True,
+    )
+    model_config = ConfigDict(
+        arbitrary_types_allowed=True,
+    )
+
+    def embed_documents(self, texts: list[str]) -> list[list[float]]:
+        """Embed a list of text strings using the Google GenAI API.
+
+        Args:
+            texts (list[str]): The text strings to embed.
+
+        Returns:
+            list[list[float]]: The embedding vectors.
+        """
+        embeddings = []
+        for text in texts:
+            response = self.client.models.embed_content(
+                model=self.model_name,
+                contents=[text],
+            )
+            assert (
+                response.embeddings is not None
+            ), "No embeddings found in the response."
+            for embedding in response.embeddings:
+                assert (
+                    embedding.values is not None
+                ), "No embedding values found in the response."
+                embeddings.append(embedding.values)
+        assert len(embeddings) == len(
+            texts
+        ), "The number of embeddings does not match the number of texts."
+        return embeddings
+
+    def embed_query(self, text: str) -> list[float]:
+        """Embed a text string using the Google GenAI API.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list[float]: The embedding vector.
+        """
+        return self.embed_documents([text])[0]
+
+    async def aembed_documents(self, texts: list[str]) -> list[list[float]]:
+        """Embed a list of text strings using the Google GenAI API asynchronously.
+
+        Args:
+            texts (list[str]): The text strings to embed.
+
+        Returns:
+            list[list[float]]: The embedding vectors.
+        """
+        embeddings = []
+        response = await self.client.aio.models.embed_content(
+            model=self.model_name,
+            contents=texts,
+        )
+        assert response.embeddings is not None, "No embeddings found in the response."
+        for embedding in response.embeddings:
+            assert (
+                embedding.values is not None
+            ), "No embedding values found in the response."
+            embeddings.append(embedding.values)
+        assert len(embeddings) == len(
+            texts
+        ), "The number of embeddings does not match the number of texts."
+        return embeddings
+
+    async def aembed_query(self, text: str) -> list[float]:
+        """Embed a text string using the Google GenAI API asynchronously.
+
+        Args:
+            text (str): The text to embed.
+
+        Returns:
+            list[float]: The embedding vector.
+        """
+        return (await self.aembed_documents([text]))[0]