langchain-google-genai 2.1.10__py3-none-any.whl → 2.1.12__py3-none-any.whl

langchain_google_genai/embeddings.py

@@ -1,3 +1,4 @@
+import asyncio
 import re
 import string
 from typing import Any, Dict, List, Optional
@@ -26,6 +27,14 @@ _MAX_TOKENS_PER_BATCH = 20000
 _DEFAULT_BATCH_SIZE = 100
 
 
+def _is_event_loop_running() -> bool:
+    try:
+        asyncio.get_running_loop()
+        return True
+    except RuntimeError:
+        return False
+
+
 class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
     """`Google Generative AI Embeddings`.
 
@@ -107,15 +116,48 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
             client_options=self.client_options,
             transport=self.transport,
         )
-        self.async_client = build_generative_async_service(
-            credentials=self.credentials,
-            api_key=google_api_key,
-            client_info=client_info,
-            client_options=self.client_options,
-            transport=self.transport,
-        )
+        # Only initialize async client if there's an event loop running
+        # to avoid RuntimeError during synchronous initialization
+        if _is_event_loop_running():
+            # async clients don't support "rest" transport
+            transport = self.transport
+            if transport == "rest":
+                transport = "grpc_asyncio"
+            self.async_client = build_generative_async_service(
+                credentials=self.credentials,
+                api_key=google_api_key,
+                client_info=client_info,
+                client_options=self.client_options,
+                transport=transport,
+            )
+        else:
+            self.async_client = None
         return self
 
+    @property
+    def _async_client(self) -> Any:
+        """Get or create the async client when needed."""
+        if self.async_client is None:
+            if isinstance(self.google_api_key, SecretStr):
+                google_api_key: Optional[str] = self.google_api_key.get_secret_value()
+            else:
+                google_api_key = self.google_api_key
+
+            client_info = get_client_info("GoogleGenerativeAIEmbeddings")
+            # async clients don't support "rest" transport
+            transport = self.transport
+            if transport == "rest":
+                transport = "grpc_asyncio"
+
+            self.async_client = build_generative_async_service(
+                credentials=self.credentials,
+                api_key=google_api_key,
+                client_info=client_info,
+                client_options=self.client_options,
+                transport=transport,
+            )
+        return self.async_client
+
     @staticmethod
     def _split_by_punctuation(text: str) -> List[str]:
         """Splits a string by punctuation and whitespace characters."""
@@ -186,14 +228,13 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
         output_dimensionality: Optional[int] = None,
     ) -> EmbedContentRequest:
         task_type = self.task_type or task_type or "RETRIEVAL_DOCUMENT"
-        request = EmbedContentRequest(
+        return EmbedContentRequest(
             content={"parts": [{"text": text}]},
             model=self.model,
             task_type=task_type.upper(),
             title=title,
             output_dimensionality=output_dimensionality,
         )
-        return request
 
     def embed_documents(
         self,
@@ -215,6 +256,7 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
             titles: An optional list of titles for texts provided.
               Only applicable when TaskType is ``'RETRIEVAL_DOCUMENT'``.
             output_dimensionality: Optional `reduced dimension for the output embedding <https://ai.google.dev/api/embeddings#EmbedContentRequest>`__.
+
         Returns:
             List of embeddings, one for each text.
         """
@@ -244,7 +286,8 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
                     BatchEmbedContentsRequest(requests=requests, model=self.model)
                 )
             except Exception as e:
-                raise GoogleGenerativeAIError(f"Error embedding content: {e}") from e
+                msg = f"Error embedding content: {e}"
+                raise GoogleGenerativeAIError(msg) from e
             embeddings.extend([list(e.values) for e in result.embeddings])
         return embeddings
 
@@ -280,7 +323,8 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
             )
             result: EmbedContentResponse = self.client.embed_content(request)
         except Exception as e:
-            raise GoogleGenerativeAIError(f"Error embedding content: {e}") from e
+            msg = f"Error embedding content: {e}"
+            raise GoogleGenerativeAIError(msg) from e
         return list(result.embedding.values)
 
     async def aembed_documents(
@@ -303,6 +347,7 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
             titles: An optional list of titles for texts provided.
                 Only applicable when TaskType is ``'RETRIEVAL_DOCUMENT'``.
             output_dimensionality: Optional `reduced dimension for the output embedding <https://ai.google.dev/api/embeddings#EmbedContentRequest>`__.
+
         Returns:
             List of embeddings, one for each text.
         """
@@ -328,11 +373,12 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
             ]
 
             try:
-                result = await self.async_client.batch_embed_contents(
+                result = await self._async_client.batch_embed_contents(
                     BatchEmbedContentsRequest(requests=requests, model=self.model)
                 )
             except Exception as e:
-                raise GoogleGenerativeAIError(f"Error embedding content: {e}") from e
+                msg = f"Error embedding content: {e}"
+                raise GoogleGenerativeAIError(msg) from e
             embeddings.extend([list(e.values) for e in result.embeddings])
         return embeddings
 
@@ -366,9 +412,10 @@ class GoogleGenerativeAIEmbeddings(BaseModel, Embeddings):
                 title=title,
                 output_dimensionality=output_dimensionality,
             )
-            result: EmbedContentResponse = await self.async_client.embed_content(
+            result: EmbedContentResponse = await self._async_client.embed_content(
                 request
             )
         except Exception as e:
-            raise GoogleGenerativeAIError(f"Error embedding content: {e}") from e
+            msg = f"Error embedding content: {e}"
+            raise GoogleGenerativeAIError(msg) from e
         return list(result.embedding.values)

langchain_google_genai/genai_aqa.py

@@ -1,9 +1,8 @@
 """Google GenerativeAI Attributed Question and Answering (AQA) service.
 
-The GenAI Semantic AQA API is a managed end to end service that allows
-developers to create responses grounded on specified passages based on
-a user query. For more information visit:
-https://developers.generativeai.google/guide
+The GenAI Semantic AQA API is a managed end to end service that allows developers to
+create responses grounded on specified passages based on a user query. For more
+information visit: https://developers.generativeai.google/guide
 """
 
 from typing import Any, List, Optional
@@ -21,8 +20,8 @@ class AqaInput(BaseModel):
 
     Attributes:
         prompt: The user's inquiry.
-        source_passages: A list of passage that the LLM should use only to
-            answer the user's inquiry.
+        source_passages: A list of passage that the LLM should use only to answer the
+            user's inquiry.
     """
 
     prompt: str
@@ -34,10 +33,10 @@ class AqaOutput(BaseModel):
 
     Attributes:
         answer: The answer to the user's inquiry.
-        attributed_passages: A list of passages that the LLM used to construct
-            the answer.
-        answerable_probability: The probability of the question being answered
-            from the provided passages.
+        attributed_passages: A list of passages that the LLM used to construct the
+            answer.
+        answerable_probability: The probability of the question being answered from the
+            provided passages.
     """
 
     answer: str
@@ -56,10 +55,12 @@ class _AqaModel(BaseModel):
     def __init__(
         self,
         answer_style: int = genai.GenerateAnswerRequest.AnswerStyle.ABSTRACTIVE,
-        safety_settings: List[genai.SafetySetting] = [],
+        safety_settings: Optional[List[genai.SafetySetting]] = None,
         temperature: Optional[float] = None,
         **kwargs: Any,
     ) -> None:
+        if safety_settings is None:
+            safety_settings = []
         super().__init__(**kwargs)
         self._client = genaix.build_generative_service()
         self._answer_style = answer_style
@@ -84,9 +85,9 @@ class _AqaModel(BaseModel):
 class GenAIAqa(RunnableSerializable[AqaInput, AqaOutput]):
     """Google's Attributed Question and Answering service.
 
-    Given a user's query and a list of passages, Google's server will return
-    a response that is grounded to the provided list of passages. It will not
-    base the response on parametric memory.
+    Given a user's query and a list of passages, Google's server will return a response
+    that is grounded to the provided list of passages. It will not base the response on
+    parametric memory.
 
     Attributes:
         answer_style: keyword-only argument. See
@@ -120,7 +121,6 @@ class GenAIAqa(RunnableSerializable[AqaInput, AqaOutput]):
         self, input: AqaInput, config: Optional[RunnableConfig] = None, **kwargs: Any
     ) -> AqaOutput:
         """Generates a grounded response using the provided passages."""
-
         response = self._client.generate_answer(
             prompt=input.prompt, passages=input.source_passages
         )

langchain_google_genai/google_vector_store.py

@@ -1,18 +1,17 @@
 """Google Generative AI Vector Store.
 
-The GenAI Semantic Retriever API is a managed end-to-end service that allows
-developers to create a corpus of documents to perform semantic search on
-related passages given a user query. For more information visit:
-https://developers.generativeai.google/guide
+The GenAI Semantic Retriever API is a managed end-to-end service that allows developers
+to create a corpus of documents to perform semantic search on related passages given a
+user query. For more information visit: https://developers.generativeai.google/guide
 """
 
 import asyncio
+from collections.abc import Iterable
 from functools import partial
 from typing import (
     Any,
     Callable,
     Dict,
-    Iterable,
     List,
     Optional,
     Tuple,
@@ -94,20 +93,22 @@ class _SemanticRetriever(BaseModel):
         document_id: Optional[str] = None,
     ) -> List[str]:
         if self.name.document_id is None and document_id is None:
-            raise NotImplementedError(
+            msg = (
                 "Adding texts to a corpus directly is not supported. "
                 "Please provide a document ID under the corpus first. "
                 "Then add the texts to the document."
             )
+            raise NotImplementedError(msg)
         if (
             self.name.document_id is not None
             and document_id is not None
             and self.name.document_id != document_id
         ):
-            raise NotImplementedError(
+            msg = (
                 f"Parameter `document_id` {document_id} does not match the "
                 f"vector store's `document_id` {self.name.document_id}"
             )
+            raise NotImplementedError(msg)
         assert self.name.document_id or document_id is not None
         new_document_id = self.name.document_id or document_id or ""
 
@@ -115,10 +116,11 @@ class _SemanticRetriever(BaseModel):
         if metadatas is None:
             metadatas = [{} for _ in texts]
         if len(texts) != len(metadatas):
-            raise ValueError(
+            msg = (
                 f"metadatas's length {len(metadatas)} and "
                 f"texts's length {len(texts)} are mismatched"
             )
+            raise ValueError(msg)
 
         chunks = genaix.batch_create_chunk(
             corpus_id=self.name.corpus_id,
@@ -182,7 +184,8 @@ def _delete_chunk(
 ) -> None:
     if chunk_id is not None:
         if document_id is None:
-            raise ValueError(f"Chunk {chunk_id} requires a document ID")
+            msg = f"Chunk {chunk_id} requires a document ID"
+            raise ValueError(msg)
         genaix.delete_chunk(
             corpus_id=corpus_id,
             document_id=document_id,
@@ -249,7 +252,7 @@ class GoogleVectorStore(VectorStore):
 
     def __init__(
         self, *, corpus_id: str, document_id: Optional[str] = None, **kwargs: Any
-    ):
+    ) -> None:
         """Returns an existing Google Semantic Retriever corpus or document.
 
         If just the corpus ID is provided, the vector store operates over all
@@ -353,9 +356,8 @@ class GoogleVectorStore(VectorStore):
                 Google server.
         """
         if corpus_id is None or document_id is None:
-            raise NotImplementedError(
-                "Must provide an existing corpus ID and document ID"
-            )
+            msg = "Must provide an existing corpus ID and document ID"
+            raise NotImplementedError(msg)
 
         doc_store = cls(corpus_id=corpus_id, document_id=document_id, **kwargs)
         doc_store.add_texts(texts, metadatas)
@@ -428,7 +430,7 @@ class GoogleVectorStore(VectorStore):
         ]
 
     def delete(self, ids: Optional[List[str]] = None, **kwargs: Any) -> Optional[bool]:
-        """Delete chunnks.
+        """Delete chunks.
 
         Note that the "ids" are not corpus ID or document ID. Rather, these
         are the entity names returned by `add_texts`.
@@ -441,13 +443,21 @@ class GoogleVectorStore(VectorStore):
     async def adelete(
         self, ids: Optional[List[str]] = None, **kwargs: Any
     ) -> Optional[bool]:
+        """Delete chunks asynchronously.
+
+        Note that the "ids" are not corpus ID or document ID. Rather, these
+        are the entity names returned by `add_texts`.
+
+        Returns:
+            True if successful. Otherwise, you should get an exception anyway.
+        """
         return await asyncio.get_running_loop().run_in_executor(
             None, partial(self.delete, **kwargs), ids
         )
 
     def _select_relevance_score_fn(self) -> Callable[[float], float]:
-        """
-        TODO: Check with the team about this!
+        """TODO: Check with the team about this!
+
         The underlying vector store already returns a "score proper",
         i.e. one in [0, 1] where higher means more *similar*.
         """

langchain_google_genai/llms.py

@@ -1,8 +1,9 @@
 from __future__ import annotations
 
 import logging
+from collections.abc import Iterator
 from difflib import get_close_matches
-from typing import Any, Iterator, List, Optional
+from typing import Any, Optional
 
 from langchain_core.callbacks import (
     CallbackManagerForLLMRun,
@@ -29,6 +30,7 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
         .. code-block:: python
 
             from langchain_google_genai import GoogleGenerativeAI
+
             llm = GoogleGenerativeAI(model="gemini-2.5-pro")
     """
 
@@ -41,7 +43,7 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
         """Needed for arg validation."""
         # Get all valid field names, including aliases
         valid_fields = set()
-        for field_name, field_info in self.model_fields.items():
+        for field_name, field_info in self.__class__.model_fields.items():
             valid_fields.add(field_name)
             if hasattr(field_info, "alias") and field_info.alias is not None:
                 valid_fields.add(field_info.alias)
@@ -62,7 +64,6 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
     @model_validator(mode="after")
     def validate_environment(self) -> Self:
         """Validates params and passes them to google-generativeai package."""
-
         if not any(self.model.startswith(prefix) for prefix in ("models/",)):
             self.model = f"models/{self.model}"
 
@@ -84,7 +85,7 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
         return self
 
     def _get_ls_params(
-        self, stop: Optional[List[str]] = None, **kwargs: Any
+        self, stop: Optional[list[str]] = None, **kwargs: Any
     ) -> LangSmithParams:
         """Get standard params for tracing."""
         ls_params = super()._get_ls_params(stop=stop, **kwargs)
@@ -104,8 +105,8 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
 
     def _generate(
         self,
-        prompts: List[str],
-        stop: Optional[List[str]] = None,
+        prompts: list[str],
+        stop: Optional[list[str]] = None,
         run_manager: Optional[CallbackManagerForLLMRun] = None,
         **kwargs: Any,
     ) -> LLMResult:
@@ -123,7 +124,7 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
                         text=g.message.content,
                         generation_info={
                             **g.generation_info,
-                            **{"usage_metadata": g.message.usage_metadata},
+                            "usage_metadata": g.message.usage_metadata,
                         },
                     )
                     for g in chat_result.generations
@@ -134,7 +135,7 @@ class GoogleGenerativeAI(_BaseGoogleGenerativeAI, BaseLLM):
     def _stream(
         self,
         prompt: str,
-        stop: Optional[List[str]] = None,
+        stop: Optional[list[str]] = None,
         run_manager: Optional[CallbackManagerForLLMRun] = None,
         **kwargs: Any,
     ) -> Iterator[GenerationChunk]:

{langchain_google_genai-2.1.10.dist-info → langchain_google_genai-2.1.12.dist-info}/METADATA

@@ -1,22 +1,16 @@
 Metadata-Version: 2.1
 Name: langchain-google-genai
-Version: 2.1.10
+Version: 2.1.12
 Summary: An integration package connecting Google's genai package and LangChain
-Home-page: https://github.com/langchain-ai/langchain-google
 License: MIT
-Requires-Python: >=3.9,<4.0
-Classifier: License :: OSI Approved :: MIT License
-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
-Requires-Dist: filetype (>=1.2.0,<2.0.0)
-Requires-Dist: google-ai-generativelanguage (>=0.6.18,<0.7.0)
-Requires-Dist: langchain-core (>=0.3.75,<0.4.0)
-Requires-Dist: pydantic (>=2,<3)
-Project-URL: Repository, https://github.com/langchain-ai/langchain-google
 Project-URL: Source Code, https://github.com/langchain-ai/langchain-google/tree/main/libs/genai
+Project-URL: Release Notes, https://github.com/langchain-ai/langchain-google/releases
+Project-URL: repository, https://github.com/langchain-ai/langchain-google
+Requires-Python: >=3.9
+Requires-Dist: langchain-core>=0.3.75
+Requires-Dist: google-ai-generativelanguage<1,>=0.7
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: filetype<2,>=1.2
 Description-Content-Type: text/markdown
 
 # langchain-google-genai
@@ -62,6 +56,9 @@ This package provides LangChain support for Google Gemini models (via the offici
 
 ```bash
 pip install -U langchain-google-genai
+
+# or, with uv:
+uv add langchain-google-genai
 ````
 
 ---
@@ -79,7 +76,7 @@ Then use the `ChatGoogleGenerativeAI` interface:
 ```python
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-llm = ChatGoogleGenerativeAI(model="gemini-pro")
+llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash")
 response = llm.invoke("Sing a ballad of LangChain.")
 print(response.content)
 ```
@@ -88,22 +85,30 @@ print(response.content)
 
 ## Chat Models
 
-The main interface for Gemini chat models is `ChatGoogleGenerativeAI`.
+See the LangChain documentation for general information about [Chat Models](https://docs.langchain.com/oss/python/langchain/models).
+
+The main interface for the Gemini chat models is `ChatGoogleGenerativeAI`.
 
 ### Multimodal Inputs
 
-Gemini vision models support image inputs in single messages.
+Most Gemini models support image inputs.
 
 ```python
 from langchain_core.messages import HumanMessage
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-llm = ChatGoogleGenerativeAI(model="gemini-pro-vision")
+llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash")
 
 message = HumanMessage(
     content=[
-        {"type": "text", "text": "What's in this image?"},
-        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
+        {
+            "type": "text",
+            "text": "What's in this image?"
+        },
+        {
+            "type": "image_url",
+            "image_url": "https://picsum.photos/seed/picsum/200/300"
+        },
     ]
 )
 
@@ -111,7 +116,7 @@ response = llm.invoke([message])
 print(response.content)
 ```
 
-✅ `image_url` can be:
+`image_url` can be:
 
 - A public image URL
 - A Google Cloud Storage path (`gcs://...`)
@@ -121,38 +126,44 @@ print(response.content)
 
 ### Multimodal Outputs
 
-The Gemini 2.0 Flash Experimental model supports both text and inline image outputs.
+Some Gemini models supports both text and inline image outputs.
 
 ```python
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-llm = ChatGoogleGenerativeAI(model="models/gemini-2.0-flash-exp-image-generation")
+llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash-image-preview")
 
 response = llm.invoke(
     "Generate an image of a cat and say meow",
     generation_config=dict(response_modalities=["TEXT", "IMAGE"]),
 )
 
-image_base64 = response.content[0].get("image_url").get("url").split(",")[-1]
-meow_text = response.content[1]
+image_base64 = response.content[1].get("image_url").get("url").split(",")[-1]
+meow_text = response.content[0]
 print(meow_text)
+# In Jupyter, display the image:
+from base64 import b64decode
+from IPython.display import Image, display
+
+img_bytes = b64decode(image_base64)
+display(Image(data=img_bytes))
 ```
 
 ---
 
 ### Audio Output
 
-```
+```python
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-llm = ChatGoogleGenerativeAI(model="models/gemini-2.5-flash-preview-tts")
-# example
+llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash-preview-tts")
+
 response = llm.invoke(
     "Please say The quick brown fox jumps over the lazy dog",
     generation_config=dict(response_modalities=["AUDIO"]),
 )
 
-# Base64 encoded binary data of the image
+# Base64 encoded binary data of the audio
 wav_data = response.additional_kwargs.get("audio")
 with open("output.wav", "wb") as f:
     f.write(wav_data)
@@ -162,15 +173,13 @@ with open("output.wav", "wb") as f:
 
 ### Multimodal Outputs in Chains
 
-You can use Gemini models in a LangChain chain:
-
 ```python
 from langchain_core.runnables import RunnablePassthrough
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_google_genai import ChatGoogleGenerativeAI, Modality
 
 llm = ChatGoogleGenerativeAI(
-    model="models/gemini-2.0-flash-exp-image-generation",
+    model="gemini-2.5-flash-image-preview",
     response_modalities=[Modality.TEXT, Modality.IMAGE],
 )
 
@@ -186,13 +195,11 @@ response = chain.invoke("cat")
 
 ### Thinking Support
 
-Gemini 2.5 Flash Preview supports internal reasoning ("thoughts").
-
 ```python
 from langchain_google_genai import ChatGoogleGenerativeAI
 
 llm = ChatGoogleGenerativeAI(
-    model="models/gemini-2.5-flash-preview-04-17",
+    model="models/gemini-2.5-flash",
     thinking_budget=1024
 )
 
@@ -207,8 +214,6 @@ print("Reasoning tokens used:", reasoning_score)
 
 ## Embeddings
 
-You can use Gemini embeddings in LangChain:
-
 ```python
 from langchain_google_genai import GoogleGenerativeAIEmbeddings
 
@@ -257,5 +262,4 @@ print("Answerable probability:", response.answerable_probability)
 
 - [LangChain Documentation](https://docs.langchain.com/)
 - [Google Generative AI SDK](https://googleapis.github.io/python-genai/)
-- [Gemini Model Documentation](https://ai.google.dev/)
-
+- [Gemini Model Documentation](https://ai.google.dev/gemini-api/docs)

langchain_google_genai-2.1.12.dist-info/RECORD

@@ -0,0 +1,17 @@
+langchain_google_genai-2.1.12.dist-info/METADATA,sha256=cIpzlJRZXFdHG-aZmSE6MJUmSr-JAZzH7pDvU30nzOs,7051
+langchain_google_genai-2.1.12.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+langchain_google_genai-2.1.12.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+langchain_google_genai-2.1.12.dist-info/licenses/LICENSE,sha256=DppmdYJVSc1jd0aio6ptnMUn5tIHrdAhQ12SclEBfBg,1072
+langchain_google_genai/__init__.py,sha256=yVc4wCHzajs8mvDVQLGmkxxivzApvdu7jTytrLr_i7g,2891
+langchain_google_genai/_common.py,sha256=dzzcJeDVnUUI_8Y20F40SZ5NjW6RHD4xJu74naYK58k,6192
+langchain_google_genai/_enums.py,sha256=Zj3BXXLlkm_UybegCi6fLsfFhriJCt_LAJvgatgPWQ0,252
+langchain_google_genai/_function_utils.py,sha256=Pur365t4M8O5dkrnFkDc_jHiPfuI_C7ucSxvxA3tioM,22254
+langchain_google_genai/_genai_extension.py,sha256=LiNa7b6BZp41meJMtgaSEbaGJa59BY3UMCRMHO_CCtQ,21467
+langchain_google_genai/_image_utils.py,sha256=iJ3KrFWQhA0UwsT8ryAFAmNM7-_2ahHAppT8t9WFZGQ,5304
+langchain_google_genai/chat_models.py,sha256=G619buVU9Sef33Ubk9JL8gYLd5y_jsGMgFXeuPq7wJ0,85067
+langchain_google_genai/embeddings.py,sha256=Kar6nHpAJ0rWQZ0nc7_anWETlwCIovd4DhieIviGNQ8,16687
+langchain_google_genai/genai_aqa.py,sha256=NVW8wOWxU7T6VVshFrFlFHa5HzEPAedrgh1fOwFH7Og,4380
+langchain_google_genai/google_vector_store.py,sha256=x4OcXkcYWTubu-AESNzNDJG_dbge16GeNCAOCsBoc4g,16537
+langchain_google_genai/llms.py,sha256=P_e_ImBWexhKqc7LZPo6tQbwLH2-ljr6oqpE5M27TRc,5755
+langchain_google_genai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langchain_google_genai-2.1.12.dist-info/RECORD,,

{langchain_google_genai-2.1.10.dist-info → langchain_google_genai-2.1.12.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.8.1
+Generator: pdm-backend (2.4.5)
 Root-Is-Purelib: true
 Tag: py3-none-any

langchain_google_genai-2.1.12.dist-info/entry_points.txt

@@ -0,0 +1,4 @@
+[console_scripts]
+
+[gui_scripts]
+

langchain_google_genai-2.1.10.dist-info/RECORD

@@ -1,16 +0,0 @@
-langchain_google_genai/__init__.py,sha256=UR61QZZ_8TkdR7yuaKLzfB8c8ZBJdPYqJ8f7Cc5TbFA,2890
-langchain_google_genai/_common.py,sha256=KyCvLpY7iiMAXdtwZDtxEU2C1iTtTGoXsEJ7-7a98cM,5942
-langchain_google_genai/_enums.py,sha256=Zj3BXXLlkm_UybegCi6fLsfFhriJCt_LAJvgatgPWQ0,252
-langchain_google_genai/_function_utils.py,sha256=VX1hj_hN3o8HGmLIiucGL7ggqrqA0Usgu4p_yvb240Q,21994
-langchain_google_genai/_genai_extension.py,sha256=cK1J96xxy_NGFYGYJQVC8q8omURz3OF3KAZJnMhIF18,20795
-langchain_google_genai/_image_utils.py,sha256=wRd-pf190F-GelSl_qPIRy8XifrBNvqTdGaHr63azlQ,5216
-langchain_google_genai/chat_models.py,sha256=CyJfChuJOVq7nrjnwEE4WtUy9hPd40bRxhw4QlpTkds,79311
-langchain_google_genai/embeddings.py,sha256=rLBb2V0j_NkflUdRE01e9Lxw-3dl94OywbyRCXJXRvI,15078
-langchain_google_genai/genai_aqa.py,sha256=qB6h3-BSXqe0YLR3eeVllYzmNKK6ofI6xJLdBahUVZo,4300
-langchain_google_genai/google_vector_store.py,sha256=4wvhIiOmc3Fo046FyafPmT9NBCLek-9bgluvuTfrbpQ,16148
-langchain_google_genai/llms.py,sha256=heRbdOM9Qav1htRromaMyub-KjPYJl7gvLLFzbZWsmg,5728
-langchain_google_genai/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langchain_google_genai-2.1.10.dist-info/LICENSE,sha256=DppmdYJVSc1jd0aio6ptnMUn5tIHrdAhQ12SclEBfBg,1072
-langchain_google_genai-2.1.10.dist-info/METADATA,sha256=OJSsO9We9B62916uCt9AEfmaiypNgIt8KcCU-N7N08A,7180
-langchain_google_genai-2.1.10.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langchain_google_genai-2.1.10.dist-info/RECORD,,