langchain-core 0.3.75__py3-none-any.whl → 0.3.76__py3-none-any.whl

langchain_core/vectorstores/in_memory.py

@@ -27,6 +27,13 @@ if TYPE_CHECKING:
     from langchain_core.embeddings import Embeddings
     from langchain_core.indexing import UpsertResponse
 
+try:
+    import numpy as np
+
+    _HAS_NUMPY = True
+except ImportError:
+    _HAS_NUMPY = False
+
 
 class InMemoryVectorStore(VectorStore):
     """In-memory vector store implementation.
@@ -83,7 +90,7 @@ class InMemoryVectorStore(VectorStore):
     Search:
         .. code-block:: python
 
-            results = vector_store.similarity_search(query="thud",k=1)
+            results = vector_store.similarity_search(query="thud", k=1)
             for doc in results:
                 print(f"* {doc.page_content} [{doc.metadata}]")
 
@@ -97,6 +104,7 @@ class InMemoryVectorStore(VectorStore):
             def _filter_function(doc: Document) -> bool:
                 return doc.metadata.get("bar") == "baz"
 
+
             results = vector_store.similarity_search(
                 query="thud", k=1, filter=_filter_function
             )
@@ -111,9 +119,7 @@ class InMemoryVectorStore(VectorStore):
     Search with score:
         .. code-block:: python
 
-            results = vector_store.similarity_search_with_score(
-                query="qux", k=1
-            )
+            results = vector_store.similarity_search_with_score(query="qux", k=1)
             for doc, score in results:
                 print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")
 
@@ -135,7 +141,7 @@ class InMemoryVectorStore(VectorStore):
 
             # search with score
             results = await vector_store.asimilarity_search_with_score(query="qux", k=1)
-            for doc,score in results:
+            for doc, score in results:
                 print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")
 
         .. code-block:: none
@@ -190,7 +196,6 @@ class InMemoryVectorStore(VectorStore):
         ids: Optional[list[str]] = None,
         **kwargs: Any,
     ) -> list[str]:
-        """Add documents to the store."""
         texts = [doc.page_content for doc in documents]
         vectors = self.embedding.embed_documents(texts)
 
@@ -224,7 +229,6 @@ class InMemoryVectorStore(VectorStore):
     async def aadd_documents(
         self, documents: list[Document], ids: Optional[list[str]] = None, **kwargs: Any
     ) -> list[str]:
-        """Add documents to the store."""
         texts = [doc.page_content for doc in documents]
         vectors = await self.embedding.aembed_documents(texts)
 
@@ -372,7 +376,11 @@ class InMemoryVectorStore(VectorStore):
             docs = [
                 doc
                 for doc in docs
-                if filter(Document(page_content=doc["text"], metadata=doc["metadata"]))
+                if filter(
+                    Document(
+                        id=doc["id"], page_content=doc["text"], metadata=doc["metadata"]
+                    )
+                )
             ]
 
         if not docs:
@@ -499,14 +507,12 @@ class InMemoryVectorStore(VectorStore):
             filter=filter,
         )
 
-        try:
-            import numpy as np
-        except ImportError as e:
+        if not _HAS_NUMPY:
             msg = (
                 "numpy must be installed to use max_marginal_relevance_search "
                 "pip install numpy"
             )
-            raise ImportError(msg) from e
+            raise ImportError(msg)
 
         mmr_chosen_indices = maximal_marginal_relevance(
             np.array(embedding, dtype=np.float32),

langchain_core/vectorstores/utils.py

@@ -10,9 +10,21 @@ import logging
 import warnings
 from typing import TYPE_CHECKING, Union
 
-if TYPE_CHECKING:
+try:
     import numpy as np
 
+    _HAS_NUMPY = True
+except ImportError:
+    _HAS_NUMPY = False
+
+try:
+    import simsimd as simd  # type: ignore[import-not-found]
+
+    _HAS_SIMSIMD = True
+except ImportError:
+    _HAS_SIMSIMD = False
+
+if TYPE_CHECKING:
     Matrix = Union[list[list[float]], list[np.ndarray], np.ndarray]
 
 logger = logging.getLogger(__name__)
@@ -33,14 +45,12 @@ def _cosine_similarity(x: Matrix, y: Matrix) -> np.ndarray:
         ValueError: If the number of columns in X and Y are not the same.
         ImportError: If numpy is not installed.
     """
-    try:
-        import numpy as np
-    except ImportError as e:
+    if not _HAS_NUMPY:
         msg = (
             "cosine_similarity requires numpy to be installed. "
             "Please install numpy with `pip install numpy`."
         )
-        raise ImportError(msg) from e
+        raise ImportError(msg)
 
     if len(x) == 0 or len(y) == 0:
         return np.array([[]])
@@ -70,9 +80,7 @@ def _cosine_similarity(x: Matrix, y: Matrix) -> np.ndarray:
             f"and Y has shape {y.shape}."
         )
         raise ValueError(msg)
-    try:
-        import simsimd as simd  # type: ignore[import-not-found]
-    except ImportError:
+    if not _HAS_SIMSIMD:
         logger.debug(
             "Unable to import simsimd, defaulting to NumPy implementation. If you want "
             "to use simsimd please install with `pip install simsimd`."
@@ -113,14 +121,12 @@ def maximal_marginal_relevance(
     Raises:
         ImportError: If numpy is not installed.
     """
-    try:
-        import numpy as np
-    except ImportError as e:
+    if not _HAS_NUMPY:
         msg = (
             "maximal_marginal_relevance requires numpy to be installed. "
             "Please install numpy with `pip install numpy`."
         )
-        raise ImportError(msg) from e
+        raise ImportError(msg)
 
     if min(k, len(embedding_list)) <= 0:
         return []

langchain_core/version.py

@@ -1,3 +1,3 @@
 """langchain-core version information and utilities."""
 
-VERSION = "0.3.75"
+VERSION = "0.3.76"

langchain_core-0.3.76.dist-info/METADATA

@@ -0,0 +1,77 @@
+Metadata-Version: 2.1
+Name: langchain-core
+Version: 0.3.76
+Summary: Building applications with LLMs through composability
+License: MIT
+Project-URL: Source Code, https://github.com/langchain-ai/langchain/tree/master/libs/core
+Project-URL: Release Notes, https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-core%3D%3D0%22&expanded=true
+Project-URL: repository, https://github.com/langchain-ai/langchain
+Requires-Python: >=3.9
+Requires-Dist: langsmith>=0.3.45
+Requires-Dist: tenacity!=8.4.0,<10.0.0,>=8.1.0
+Requires-Dist: jsonpatch<2.0,>=1.33
+Requires-Dist: PyYAML>=5.3
+Requires-Dist: typing-extensions>=4.7
+Requires-Dist: packaging>=23.2
+Requires-Dist: pydantic>=2.7.4
+Description-Content-Type: text/markdown
+
+# 🦜🍎️ LangChain Core
+
+[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
+[![PyPI - Downloads](https://img.shields.io/pepy/dt/langchain-core)](https://pypistats.org/packages/langchain-core)
+
+## Quick Install
+
+```bash
+pip install langchain-core
+```
+
+## What is it?
+
+LangChain Core contains the base abstractions that power the the LangChain ecosystem.
+
+These abstractions are designed to be as modular and simple as possible.
+
+The benefit of having these abstractions is that any provider can implement the required interface and then easily be used in the rest of the LangChain ecosystem.
+
+For full documentation see the [API reference](https://python.langchain.com/api_reference/core/index.html).
+
+## ⛰️ Why build on top of LangChain Core?
+
+The LangChain ecosystem is built on top of `langchain-core`. Some of the benefits:
+
+- **Modularity**: We've designed Core around abstractions that are independent of each other, and not tied to any specific model provider.
+- **Stability**: We are committed to a stable versioning scheme, and will communicate any breaking changes with advance notice and version bumps.
+- **Battle-tested**: Core components have the largest install base in the LLM ecosystem, and are used in production by many companies.
+
+## 1️⃣ Core Interface: Runnables
+
+The concept of a `Runnable` is central to LangChain Core – it is the interface that most LangChain Core components implement, giving them
+
+- A common invocation interface (`invoke()`, `batch()`, `stream()`, etc.)
+- Built-in utilities for retries, fallbacks, schemas and runtime configurability
+- Easy deployment with [LangGraph](https://github.com/langchain-ai/langgraph)
+
+For more check out the [`Runnable` docs](https://python.langchain.com/docs/concepts/runnables/). Examples of components that implement the interface include: Chat Models, Tools, Retrievers, and Output Parsers.
+
+## 📕 Releases & Versioning
+
+As `langchain-core` contains the base abstractions and runtime for the whole LangChain ecosystem, we will communicate any breaking changes with advance notice and version bumps. The exception for this is anything in `langchain_core.beta`. The reason for `langchain_core.beta` is that given the rate of change of the field, being able to move quickly is still a priority, and this module is our attempt to do so.
+
+Minor version increases will occur for:
+
+- Breaking changes for any public interfaces NOT in `langchain_core.beta`
+
+Patch version increases will occur for:
+
+- Bug fixes
+- New features
+- Any changes to private interfaces
+- Any changes to `langchain_core.beta`
+
+## 💁 Contributing
+
+As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
+
+For detailed information on how to contribute, see the [Contributing Guide](https://python.langchain.com/docs/contributing/).

langchain_core-0.3.76.dist-info/RECORD

@@ -0,0 +1,174 @@
+langchain_core-0.3.76.dist-info/METADATA,sha256=ZhBB9FyNj2n3utI8osSza8-x4fbLyMPQA5QCldNiOZM,3724
+langchain_core-0.3.76.dist-info/WHEEL,sha256=9P2ygRxDrTJz3gsagc0Z96ukrxjr-LFBGOgv3AuKlCA,90
+langchain_core-0.3.76.dist-info/entry_points.txt,sha256=6OYgBcLyFCUgeqLgnvMyOJxPCWzgy7se4rLPKtNonMs,34
+langchain_core/__init__.py,sha256=TgvhxbrjCRVJwr2HddiyHvtH8W94K-uLM6-6ifNIBXo,713
+langchain_core/_api/__init__.py,sha256=WDOMw4faVuscjDCL5ttnRQNienJP_M9vGMmJUXS6L5w,1976
+langchain_core/_api/beta_decorator.py,sha256=LM5C32LB7_KNLfePssM2hgFRt7aPvqddf9J_TiOWIsw,8877
+langchain_core/_api/deprecation.py,sha256=fHtx24pEGMOl20xWWtWafPL4QO7-Rt9MUrINRF1Pdqo,20952
+langchain_core/_api/internal.py,sha256=aOZkYANu747LyWzyAk-0KE4RjdTYj18Wtlh7F9_qyPM,683
+langchain_core/_api/path.py,sha256=raXCzfgMf6AoPo8UP6I1qHRKlIBcBuR18qMHaFyIvhU,1405
+langchain_core/_import_utils.py,sha256=NvAiw5PLvsKCux8LcRndpbZL9m_rHkL1-iWZcNLzQMc,1458
+langchain_core/agents.py,sha256=Z9AFByLkZp__LM_icC699Ge-8dCxPiYQNOdEqrZUiDw,8468
+langchain_core/beta/__init__.py,sha256=8phOlCdTByvzqN1DR4CU_rvaO4SDRebKATmFKj0B5Nw,68
+langchain_core/beta/runnables/__init__.py,sha256=KPVZTs2phF46kEB7mn0M75UeSw8nylbTZ4HYpLT0ywE,17
+langchain_core/beta/runnables/context.py,sha256=kiaDITMNJ8en7n5H5cofFNQ74VChHRsq6VbB1s5Y9F4,13400
+langchain_core/caches.py,sha256=d_6h0Bb0h7sLK0mrQ1BwSljJKnLBvKvoXQMVSnpcqlI,9665
+langchain_core/callbacks/__init__.py,sha256=jXp7StVQk5GeWudGtnnkFV_L-WHCl44ESznc6-0pOVg,4347
+langchain_core/callbacks/base.py,sha256=6A5vPF9W-0vSjZ3WBoRfpjfKApK8oS4vdAky5FByeSo,37154
+langchain_core/callbacks/file.py,sha256=dLBuDRqeLxOBTB9k6c9KEh8dx5UgGfQ9uUF-dhiykZM,8532
+langchain_core/callbacks/manager.py,sha256=hLyjHpS07NwlAwsgHcoM-nv7U12tyS5PTk-o7rJFJ84,90999
+langchain_core/callbacks/stdout.py,sha256=hQ1gjpshNHGdbCS8cH6_oTc4nM8tCWzGNXrbm9dJeaY,4113
+langchain_core/callbacks/streaming_stdout.py,sha256=92UQWxL9HBzdCpn47AF-ZE_jGkkebMn2Z_l24ndMBMI,4646
+langchain_core/callbacks/usage.py,sha256=S2sBShC_0br6HtRB5Cow6ILOl_gX7TaDcEAge2MyjYo,5107
+langchain_core/chat_history.py,sha256=BXJBhyRS806BXf3m6eRRHsAwC_l9mNAe0zMGxycpZQ8,8388
+langchain_core/chat_loaders.py,sha256=b57Gl3KGPxq9gYJjetsHfJm1I6kSqi7bDE91fJJOR84,601
+langchain_core/chat_sessions.py,sha256=YEO3ck5_wRGd3a2EnGD7M_wTvNC_4T1IVjQWekagwaM,564
+langchain_core/document_loaders/__init__.py,sha256=DkZPp9cEVmsnz9SM1xtuefH_fGQFvA2WtpRG6iePPBs,975
+langchain_core/document_loaders/base.py,sha256=nBv07847NrsB9EZpC0YU7Zv_Y08T7pisLREMrJwE7Bg,4666
+langchain_core/document_loaders/blob_loaders.py,sha256=4m1k8boiwXw3z4yMYT8bnYUA-eGTPtEZyUxZvI3GbTs,1077
+langchain_core/document_loaders/langsmith.py,sha256=QGgBhyr0uq3_84nTzuBB8Bk-DiubjuTVsfvSj-Y8RvU,5513
+langchain_core/documents/__init__.py,sha256=KT_l-TSINKrTXldw5n57wx1yGBtJmGAGxAQL0ceQefc,850
+langchain_core/documents/base.py,sha256=qxf8E06ga9kblxvTECyNXViHoLx1_MWPTM92ATSWlX8,10598
+langchain_core/documents/compressor.py,sha256=91aCQC3W4XMoFXtAmlOCSPb8pSdrirY6Lg8ZLBxTX4s,2001
+langchain_core/documents/transformers.py,sha256=lL0BdmL8xkNO_NqY3vqaLPhPdzte0BUKVoG2IMJqe2s,2584
+langchain_core/embeddings/__init__.py,sha256=0SfcdkVSSXmTFXznUyeZq_b1ajpwIGDueGAAfwyMpUY,774
+langchain_core/embeddings/embeddings.py,sha256=u50T2VxLLyfGBCKcVtWfSiZrtKua8sOSHwSSHRKtcno,2405
+langchain_core/embeddings/fake.py,sha256=iEFwd3j7zGG6EUoCPK-Y9On9C3-q-Lu0Syld27UhsnQ,3954
+langchain_core/env.py,sha256=RHExSWJ2bW-6Wxb6UyBGxU5flLoNYOAeslZ9iTjomQE,598
+langchain_core/example_selectors/__init__.py,sha256=k8y0chtEhaHf8Y1_nZVDsb9CWDdRIWFb9U806mnbGvo,1394
+langchain_core/example_selectors/base.py,sha256=4wRCERHak6Ci5JEKHeidQ_pbBgzQyc-vnQsz2sqBFzA,1716
+langchain_core/example_selectors/length_based.py,sha256=VlWoGhppKrKYKRyi0qBdhq4TbD-6pDHobx3fMGWoqfY,3375
+langchain_core/example_selectors/semantic_similarity.py,sha256=flhao1yNBnaDkM2MlwFd2m4m2dBc_IlEMnmSWV61IVE,13739
+langchain_core/exceptions.py,sha256=JurkMF4p-DOmv7SQJqif7A-5kfKOHCcl8R_wXmMUfSE,3327
+langchain_core/globals.py,sha256=yl9GRxC3INm6AqRplHmKjxr0bn1YWXSU34iul5dnBl8,8823
+langchain_core/indexing/__init__.py,sha256=VOvbbBJYY_UZdMKAeJCdQdszMiAOhAo3Cbht1HEkk8g,1274
+langchain_core/indexing/api.py,sha256=tQPaAQZ-luJb8xq6438YN3jVWViKWLSwNLVU4eDdXpA,38473
+langchain_core/indexing/base.py,sha256=PWxwX4bH1xq8gKaVnGiNnThPRmwhoDKrJRlEotjtERo,23015
+langchain_core/indexing/in_memory.py,sha256=YPVOGKE3d5-APCy7T0sJvSPjJJUcshSfPeCpq7BA4j0,3326
+langchain_core/language_models/__init__.py,sha256=LBszonEJ6Zu56rVJfSWQt4Q_mr5hD-epcPvSaTClC4E,3764
+langchain_core/language_models/_utils.py,sha256=4TS92kBO5ee4QNH68FFWhX-2uCTe8QaxTXVFMiJLXt4,4786
+langchain_core/language_models/base.py,sha256=cvZOME14JI90NkuDw2Vr1yYx7xKap1dkXgCM8yMu31U,14566
+langchain_core/language_models/chat_models.py,sha256=EXkeArgGkfUJl1JxVZHzdX52GCEQBRRJCOW9u-796Ec,72619
+langchain_core/language_models/fake.py,sha256=h9LhVTkmYLXkJ1_VvsKhqYVpkQsM7eAr9geXF_IVkPs,3772
+langchain_core/language_models/fake_chat_models.py,sha256=cihlKSiec-bDDdHAgpuejKlkXpCgKVK4zabo0eSydNg,12818
+langchain_core/language_models/llms.py,sha256=0KNfdoTHwJv_wFoY8Ng8It0E6tt_mtMcXYuLFTqp5PQ,57887
+langchain_core/load/__init__.py,sha256=m3_6Fk2gpYZO0xqyTnZzdQigvsYHjMariLq_L2KwJFk,1150
+langchain_core/load/dump.py,sha256=N34h-I3VeLFzuwrYlVSY_gFx0iaZhEi72D04yxkx3cc,2654
+langchain_core/load/load.py,sha256=eDyYNBGbfVDLGOA3p2cAOWY0rLqbf9E9qNfstw0PKDY,9729
+langchain_core/load/mapping.py,sha256=nnFXiTdQkfdv41_wP38aWGtpp9svxW6fwVyC3LmRkok,29633
+langchain_core/load/serializable.py,sha256=P29Coe7ZE8-13goAmAtSt0rl85fKaUd96znRQuIHG9k,11722
+langchain_core/memory.py,sha256=bYgZGSldIa79GqpEd2m9Ve78euCq6SJatzTsHAHKosk,3693
+langchain_core/messages/__init__.py,sha256=8H1BnLGi2oSXdIz_LWtVAwmxFvK_6_CqiDRq2jnGtw0,4253
+langchain_core/messages/ai.py,sha256=QLYd2875WnyQ-7EBxz_PKwhyia64aZVLxP3mQbeV74M,18370
+langchain_core/messages/base.py,sha256=tuyXQ6tXxayPkEmCFqJ9s0qH_9sbRzML16I93r2rMAY,9605
+langchain_core/messages/chat.py,sha256=Vgk3y03F9NP-wKkXAjBDLOtrH43NpEMN2xaWRp6qhRA,2260
+langchain_core/messages/content_blocks.py,sha256=E_AvS5yy1JHPquyKN7Wj5A7Gl9AvxOAGgR770FVhhtk,5487
+langchain_core/messages/function.py,sha256=QO2WgKmJ5nm7QL-xXG11Fmz3qFkHm1lL0k41WjDeEZE,2157
+langchain_core/messages/human.py,sha256=5xh31bLYeqbU3NxBaPjFNj5YzSUxPysrftx-48rW_Gc,1854
+langchain_core/messages/modifier.py,sha256=ch0RedUM_uA7wOEJHk8mkoJSNR0Rli_32BmOfdbS1dU,894
+langchain_core/messages/system.py,sha256=8vhHi99gjkY84ca6GhPiNyjgZ2MtaPkv6UvWUpba_qA,1666
+langchain_core/messages/tool.py,sha256=lIgW9geAMCeSfVYjCeoq6spDAJxUG6QyAjQUydnO0yQ,12567
+langchain_core/messages/utils.py,sha256=qYR_E3sN7EMVD1AOS-SYQOZjLtLSV1H9hpRTytDyY5c,69837
+langchain_core/output_parsers/__init__.py,sha256=R8L0GwY-vD9qvqze3EVELXF6i45IYUJ_FbSfno_IREg,2873
+langchain_core/output_parsers/base.py,sha256=53Yt9dOlR686ku0dP2LK9hHKGprxw_YEsAsY04dejmE,11225
+langchain_core/output_parsers/format_instructions.py,sha256=8oUbeysnVGvXWyNd5gqXlEL850D31gMTy74GflsuvRU,553
+langchain_core/output_parsers/json.py,sha256=Z_mcfO9jdAH96dZXrSi4rEx3o7Z9Oqn_IBkOjLBDpaQ,4589
+langchain_core/output_parsers/list.py,sha256=WJ1fgGH2vnh_TRgGd83WZKVKGGpcqu-Q8zjDseqIA0Y,7294
+langchain_core/output_parsers/openai_functions.py,sha256=FFy2Wh39wPFM1mO222gMzQU_wrpIFiCo5unZM8PM3jQ,10793
+langchain_core/output_parsers/openai_tools.py,sha256=2zBuswllEu_gwN7iAd3Yvifr6XIJcvyMIVa1ER68-_k,12606
+langchain_core/output_parsers/pydantic.py,sha256=mwB5HNa4KHLt_kD7gbwWyXSX-GnM1gX0nsM00b0OVAE,4490
+langchain_core/output_parsers/string.py,sha256=jlUsciPkCmZ3MOfhz-KUJDjSaR0VswnzH8z0KlIfAoQ,965
+langchain_core/output_parsers/transform.py,sha256=ntWW0SKk6GUHXQNXHZvT1PhyedQrvF61oIo_fP63fRQ,5923
+langchain_core/output_parsers/xml.py,sha256=MDjZHJY2KeYREPLlEQJ1M2r0ALa0nb1Wec7MJ4Nk6LA,10974
+langchain_core/outputs/__init__.py,sha256=uy2aeRTvvIfyWeLtPs0KaCw0VpG6QTkC0esmj268BIM,2119
+langchain_core/outputs/chat_generation.py,sha256=XLJCeok5mliejMlzJka8v8aqLDs6HORd813PcxeeBRk,4681
+langchain_core/outputs/chat_result.py,sha256=us15wVh00AYkIVNmf0VETEI9aoEQy-cT-SIXMX-98Zc,1356
+langchain_core/outputs/generation.py,sha256=zroWD-bJxmdKJWbt1Rv-jVImyOng5s8rEn8bHMtjaLo,2644
+langchain_core/outputs/llm_result.py,sha256=aX81609Z5JrLQGx9u2l6UDdzMLRoLgvdr5k1xDmB4UI,3935
+langchain_core/outputs/run_info.py,sha256=xCMWdsHfgnnodaf4OCMvZaWUfS836X7mV15JPkqvZjo,594
+langchain_core/prompt_values.py,sha256=ML6TgOes1I6-6S9BYg6KK7xYVQc7wFYSsfU6gtcQDxk,4023
+langchain_core/prompts/__init__.py,sha256=sp3NU858CEf4YUuDYiY_-iF1x1Gb5msSyoyrk2FUI94,4123
+langchain_core/prompts/base.py,sha256=g95varYAcsNY-2ILWrLhvQOMOw_qYr9ft7XqHgMkKbE,15971
+langchain_core/prompts/chat.py,sha256=Q9oAvYtz1qWNtSRxly7UYYFSERap79uno1JsU7z6_x0,52635
+langchain_core/prompts/dict.py,sha256=e4rxVs2IkMjxN_NqYtRpb9NYLyE9mimMMSzawbubrfA,4732
+langchain_core/prompts/few_shot.py,sha256=nd1KtIw_pv8MdM49Q1V_szu4u6Wil0VAVqmiHLKzr64,16141
+langchain_core/prompts/few_shot_with_templates.py,sha256=z1fSlcHunfdVQc7BuM9tudCWMquUn2Zztw7ROXOEOgE,7839
+langchain_core/prompts/image.py,sha256=rrwpPo3nb2k_8I1DYF3cZv3go0T_CmSUrJsIktrQtgA,4786
+langchain_core/prompts/loading.py,sha256=_T26PCTuZuOsCkHk_uv-h_zoIMonXojBdYJA3UsWHXE,6907
+langchain_core/prompts/message.py,sha256=9I5IZXFn2Bwv8CIZ0zMp7k8C48xQyiAOqyv6uAYJdY0,2624
+langchain_core/prompts/pipeline.py,sha256=Zj6aqIcU874mnYG__0I4nHmz4p7uaNAdYsJpMDb1LyQ,4612
+langchain_core/prompts/prompt.py,sha256=RfD-w7GKolgptGB72UVIb1q3iIOm4pv2hby6EmJf9kk,11667
+langchain_core/prompts/string.py,sha256=biN76hgwqZx-SjtXgy3qe9QmM2I2STSg8DylD0Mf0RE,10361
+langchain_core/prompts/structured.py,sha256=V5qfOpSPWBnF5xcRl_qEmrv1u7T_IfzONHJ-rUFiTyE,5957
+langchain_core/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langchain_core/pydantic_v1/__init__.py,sha256=hqAsQjsfqLduCo5E0oAAAt21Nkls0S6bCQ4tD2moFfU,1080
+langchain_core/pydantic_v1/dataclasses.py,sha256=q4Qst8I0g7odncWZ3-MvW-Xadfu6DQYxCo-DFZgwLPE,889
+langchain_core/pydantic_v1/main.py,sha256=uTB_757DTfo-mFKJUn_a4qS_GxmSxlqYmL2WOCJLdS0,882
+langchain_core/rate_limiters.py,sha256=EZtViY5BZLPBg_JBvv_kYywV9Cl3wd6AC-SDEA0fPPg,9550
+langchain_core/retrievers.py,sha256=622gKRLmBSUXi_o4z57EoctT32XRbqCk_5f_NU7MEFE,16710
+langchain_core/runnables/__init__.py,sha256=efTnFjwN_QSAv5ThLmKuWeu8P1BLARH-cWKZBuimfDM,3858
+langchain_core/runnables/base.py,sha256=5MTTej3NO0mpgvwaaFgSywBayCo9WjtWa3sHBW5Nxuo,228986
+langchain_core/runnables/branch.py,sha256=enKt0Qgc3b2UQSWGtQLcTlhOUNJGXfqNeaQwSq9AEkg,16338
+langchain_core/runnables/config.py,sha256=lT2RORiOlFPalxPB11TV_eSAMIi1dAiIzCyfmZariZw,20297
+langchain_core/runnables/configurable.py,sha256=Ios0MDPViYO9nO_EltAlkDkNNxdz4zXuNcZ1cuHZwzw,24695
+langchain_core/runnables/fallbacks.py,sha256=VeHCrW_Ci9p8G9KojNp5dC7Yo6l5jdZtst9O_yt2sM0,24497
+langchain_core/runnables/graph.py,sha256=aSPJxmUoG3J0lPaVYXJ2ulf6q5hfxBOZfK_Aro6Bdn4,23738
+langchain_core/runnables/graph_ascii.py,sha256=DYdH8pv9dJcQHYcNupEs-XCasDd-jrGeEMTbS6K5OAk,10446
+langchain_core/runnables/graph_mermaid.py,sha256=U04DalCmgNTamyR2gBNDo8_3zzSbSU6NqpXH9Y1-U8E,16794
+langchain_core/runnables/graph_png.py,sha256=md4NFNKMY7SkAr3Ysf1FNOU-SIZioSkniT__IPkoUSA,5566
+langchain_core/runnables/history.py,sha256=CeFI41kBoowUKsCuFu1HeEgBIuyhh2oEhcuUyPs_j6M,24775
+langchain_core/runnables/passthrough.py,sha256=HvwNeGVVzhS6EkSurbjU8Ah-UXUj3nsrhiY-gmeyxhE,26443
+langchain_core/runnables/retry.py,sha256=r5rEJ1nMqd5W-g9YJU0zKmyhgUSBhBeAJ8zFVaMhdvc,12824
+langchain_core/runnables/router.py,sha256=HYGMfOYhpdyL3OlrEjYj1bKqEjDFyWEvFDXx2BoV3s4,7236
+langchain_core/runnables/schema.py,sha256=ff7PsRswAeQgVEeGybzC3rvaoDHV2S8pNCwpwppRjAY,5545
+langchain_core/runnables/utils.py,sha256=zfC4orjXPcj_zpTO2yTvz04RPAwTt2HxW6kFPYkximQ,22843
+langchain_core/stores.py,sha256=IEsHB9kp1QnzYOBfl_eVMAnopP9M3lRgg2i-ypsV9NI,10496
+langchain_core/structured_query.py,sha256=SmeP7cYTx2OCxOEo9UsSiHO3seqIoZPjb0CQd8JDWRk,5164
+langchain_core/sys_info.py,sha256=HG1fu2ayPvRQmrlowyO-NdUj_I8Le1S-bPAbYB9VJTY,4045
+langchain_core/tools/__init__.py,sha256=Uqcn6gFAoFbMM4aRXd8ACL4D-owdevGc37Gn-KOB8JU,2860
+langchain_core/tools/base.py,sha256=DMlpWU1ekAy68pmrHgtqtqcDuo6eu0qTq13TvOhqdew,50243
+langchain_core/tools/convert.py,sha256=ll3XrBhWtPWULONB-QlXEwAnT5FDjK9aP-kKuoi26Ds,16247
+langchain_core/tools/render.py,sha256=BosvIWrSvOJgRg_gaSDBS58j99gwQHsLhprOXeJP53I,1842
+langchain_core/tools/retriever.py,sha256=zlSV3HnWhhmtZtkNGbNQW9wxv8GptJKmDhzqZj8e36o,3873
+langchain_core/tools/simple.py,sha256=f6H5VgYpSU7LI1a-zE8RvH6PMvbZ66GV35OM-hRfSf0,6957
+langchain_core/tools/structured.py,sha256=jJOeELTZZDE3aQHFCWF4xeepeJybMks2r-YBs__k7R8,9803
+langchain_core/tracers/__init__.py,sha256=ixZmLjtoMEPqYEFUtAxleiDDRNIaHrS01VRDo9mCPk8,1611
+langchain_core/tracers/_streaming.py,sha256=U9pWQDJNUDH4oOYF3zvUMUtgkCecJzXQvfo-wYARmhQ,982
+langchain_core/tracers/base.py,sha256=rbIJgMaDga3jFeCWCmzjqUZLMmp9ZczT4wFecVPL2hk,26013
+langchain_core/tracers/context.py,sha256=xCgMjCoulBm3QXjLaVDFC8-93emgsunYcCtZCiVKcTo,7199
+langchain_core/tracers/core.py,sha256=a40PCXd_2Yh8-drVfr1MJynvw9eUecocTWu-EIFwaDU,23773
+langchain_core/tracers/evaluation.py,sha256=o0iIcuYx_mlD8q5_N7yxiVIaGeC3JaepHlZks0xm0nQ,8426
+langchain_core/tracers/event_stream.py,sha256=BR8NJSmWqPvfgqWltipH-rk2UO6db0I3RH5lN6E-aHk,33810
+langchain_core/tracers/langchain.py,sha256=bvavDPE5t2J2BNexot0cHsD0asSeoofNtWAQqYbBvTQ,10620
+langchain_core/tracers/langchain_v1.py,sha256=QteCXOsETqngvigalofcKR3l6le6barotAtWHaE8a1w,898
+langchain_core/tracers/log_stream.py,sha256=jaW3tOvBxR4FgSZj4lS9pjVCdc4Y8_DUJoudAEcC-wQ,25491
+langchain_core/tracers/memory_stream.py,sha256=3A-cwA3-lq5YFbCZWYM8kglVv1bPT4kwM2L_q8axkhU,5032
+langchain_core/tracers/root_listeners.py,sha256=44cr4itZknl2VaYS3pNitJIy2DOKmZC09WWeHIBjOnU,4184
+langchain_core/tracers/run_collector.py,sha256=FZkocT41EichTy2QyETbhZjlOptyj-peOhEQUqEcJGg,1305
+langchain_core/tracers/schemas.py,sha256=y16K_c1ji3LHD-addSkn4-n73eknS2RlNRAhTSgs_YM,3826
+langchain_core/tracers/stdout.py,sha256=aZN-yz545zj34kYfrEmYzWeSz83pbqN8wNqi-ZvS1Iw,6732
+langchain_core/utils/__init__.py,sha256=N0ZeV09FHvZIVITLJlqGibb0JNtmmLvvoareFtG0DuI,3169
+langchain_core/utils/_merge.py,sha256=uo_n2mJ0_FuRJZUUgJemsXQ8rAC9fyYGOMmnPfbbDUg,5785
+langchain_core/utils/aiter.py,sha256=R3_2TqQHAUbRig9BddP8NQZdeDDnW6uS9kK9gZAIRr8,10892
+langchain_core/utils/env.py,sha256=5EnSNXr4oHAkGkKfrNf0xl_vqz2ejVKVMUQaQePXv9s,2536
+langchain_core/utils/formatting.py,sha256=fkieArzKXxSsLcEa3B-MX60O4ZLeeLjiPtVtxCJPcOU,1480
+langchain_core/utils/function_calling.py,sha256=qD0mEH2Wr1UwW-zwDE-cHNJzqxiN99SNWJkeUDSumc4,29398
+langchain_core/utils/html.py,sha256=fUogMGhd-VoUbsGnMyY6v_gv9nbxJy-vmC4yfICcflM,3780
+langchain_core/utils/image.py,sha256=1MH8Lbg0f2HfhTC4zobKMvpVoHRfpsyvWHq9ae4xENo,532
+langchain_core/utils/input.py,sha256=z3tubdUtsoHqfTyiBGfELLr1xemSe-pGvhfAeGE6O2g,1958
+langchain_core/utils/interactive_env.py,sha256=nm06cucX9ez9H3GBAIRDsivSp0V--2HnBIMogI4gHpQ,287
+langchain_core/utils/iter.py,sha256=IysrW22N5R3V8QFJp1CMCRrrtllWYuwOg-7Oi7wVV_s,7560
+langchain_core/utils/json.py,sha256=Hmyk97Ll3lGLpoFAST2PM8d-fQVNu3VHxwd1JfGdtYE,6311
+langchain_core/utils/json_schema.py,sha256=s7g_tfXDhj-uP49DONmKljAbnEJ1waAkjMPBvckmum0,3983
+langchain_core/utils/loading.py,sha256=zHY3y-eW_quqgJDJNY24dO7YDZW9P103Mc77dnGbEpA,1023
+langchain_core/utils/mustache.py,sha256=j_BJH-axSkE-_DHPXx4xuIO_eqMsd9YaHm0VMtculvg,21373
+langchain_core/utils/pydantic.py,sha256=kSwwMv9st03BT4eVbkARtPwQVv34zXF1YlFZ-d8G1Ns,18578
+langchain_core/utils/strings.py,sha256=0LaQiqpshHwMrWBGvNfFPc-AxihLGMM9vsQcSx3uAkI,1804
+langchain_core/utils/usage.py,sha256=EYv0poDqA7VejEsPyoA19lEt9M4L24Tppf4OPtOjGwI,1202
+langchain_core/utils/utils.py,sha256=cE94qWbUEtuGVJZCPby997ppjly4kt9cxh2pOhKR6ZQ,15455
+langchain_core/vectorstores/__init__.py,sha256=5P0eoeoH5LHab64JjmEeWa6SxX4eMy-etAP1MEHsETY,804
+langchain_core/vectorstores/base.py,sha256=nWlfzbkVdOObfbPpvfdLKHw9J0PryACVohHC_Y6wWZM,41529
+langchain_core/vectorstores/in_memory.py,sha256=RyXuB3dCr-Dgq30PhRgPwh8j8iH8GNIZAr8b9C7FHA4,18101
+langchain_core/vectorstores/utils.py,sha256=D6St53Xg1kO73dnw4MPd8vlkro4C3gmCpcghUzcepi0,4971
+langchain_core/version.py,sha256=7aYZr_aVmy4AITHPWIVrAMX1d3_LbCpyKUbQcD33QW4,76
+langchain_core-0.3.76.dist-info/RECORD,,

langchain_core-0.3.75.dist-info/METADATA

@@ -1,106 +0,0 @@
-Metadata-Version: 2.1
-Name: langchain-core
-Version: 0.3.75
-Summary: Building applications with LLMs through composability
-License: MIT
-Project-URL: Source Code, https://github.com/langchain-ai/langchain/tree/master/libs/core
-Project-URL: Release Notes, https://github.com/langchain-ai/langchain/releases?q=tag%3A%22langchain-core%3D%3D0%22&expanded=true
-Project-URL: repository, https://github.com/langchain-ai/langchain
-Requires-Python: >=3.9
-Requires-Dist: langsmith>=0.3.45
-Requires-Dist: tenacity!=8.4.0,<10.0.0,>=8.1.0
-Requires-Dist: jsonpatch<2.0,>=1.33
-Requires-Dist: PyYAML>=5.3
-Requires-Dist: typing-extensions>=4.7
-Requires-Dist: packaging>=23.2
-Requires-Dist: pydantic>=2.7.4
-Description-Content-Type: text/markdown
-
-# 🦜🍎️ LangChain Core
-
-[![Downloads](https://static.pepy.tech/badge/langchain_core/month)](https://pepy.tech/project/langchain_core)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-
-## Quick Install
-
-```bash
-pip install langchain-core
-```
-
-## What is it?
-
-LangChain Core contains the base abstractions that power the rest of the LangChain ecosystem.
-
-These abstractions are designed to be as modular and simple as possible. Examples of these abstractions include those for language models, document loaders, embedding models, vectorstores, retrievers, and more.
-
-The benefit of having these abstractions is that any provider can implement the required interface and then easily be used in the rest of the LangChain ecosystem.
-
-For full documentation see the [API reference](https://python.langchain.com/api_reference/core/index.html).
-
-## 1️⃣ Core Interface: Runnables
-
-The concept of a `Runnable` is central to LangChain Core – it is the interface that most LangChain Core components implement, giving them
-
-- a common invocation interface (`invoke()`, `batch()`, `stream()`, etc.)
-- built-in utilities for retries, fallbacks, schemas and runtime configurability
-- easy deployment with [LangGraph](https://github.com/langchain-ai/langgraph)
-
-For more check out the [runnable docs](https://python.langchain.com/docs/concepts/runnables/). Examples of components that implement the interface include: LLMs, Chat Models, Prompts, Retrievers, Tools, Output Parsers.
-
-You can use LangChain Core objects in two ways:
-
-1. **imperative**, ie. call them directly, eg. `model.invoke(...)`
-
-2. **declarative**, with LangChain Expression Language (LCEL)
-
-3. or a mix of both! eg. one of the steps in your LCEL sequence can be a custom function
-
-| Feature   | Imperative                      | Declarative    |
-| --------- | ------------------------------- | -------------- |
-| Syntax    | All of Python                   | LCEL           |
-| Tracing   | ✅ – Automatic                  | ✅ – Automatic |
-| Parallel  | ✅ – with threads or coroutines | ✅ – Automatic |
-| Streaming | ✅ – by yielding                | ✅ – Automatic |
-| Async     | ✅ – by writing async functions | ✅ – Automatic |
-
-## ⚡️ What is LangChain Expression Language?
-
-LangChain Expression Language (LCEL) is a _declarative language_ for composing LangChain Core runnables into sequences (or DAGs), covering the most common patterns when building with LLMs.
-
-LangChain Core compiles LCEL sequences to an _optimized execution plan_, with automatic parallelization, streaming, tracing, and async support.
-
-For more check out the [LCEL docs](https://python.langchain.com/docs/concepts/lcel/).
-
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](https://raw.githubusercontent.com/langchain-ai/langchain/master/docs/static/svg/langchain_stack_112024.svg "LangChain Framework Overview")
-
-For more advanced use cases, also check out [LangGraph](https://github.com/langchain-ai/langgraph), which is a graph-based runner for cyclic and recursive LLM workflows.
-
-## 📕 Releases & Versioning
-
-As `langchain-core` contains the base abstractions and runtime for the whole LangChain ecosystem, we will communicate any breaking changes with advance notice and version bumps. The exception for this is anything in `langchain_core.beta`. The reason for `langchain_core.beta` is that given the rate of change of the field, being able to move quickly is still a priority, and this module is our attempt to do so.
-
-Minor version increases will occur for:
-
-- Breaking changes for any public interfaces NOT in `langchain_core.beta`
-
-Patch version increases will occur for:
-
-- Bug fixes
-- New features
-- Any changes to private interfaces
-- Any changes to `langchain_core.beta`
-
-## 💁 Contributing
-
-As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
-
-For detailed information on how to contribute, see the [Contributing Guide](https://python.langchain.com/docs/contributing/).
-
-## ⛰️ Why build on top of LangChain Core?
-
-The whole LangChain ecosystem is built on top of LangChain Core, so you're in good company when building on top of it. Some of the benefits:
-
-- **Modularity**: LangChain Core is designed around abstractions that are independent of each other, and not tied to any specific model provider.
-- **Stability**: We are committed to a stable versioning scheme, and will communicate any breaking changes with advance notice and version bumps.
-- **Battle-tested**: LangChain Core components have the largest install base in the LLM ecosystem, and are used in production by many companies.
-- **Community**: LangChain Core is developed in the open, and we welcome contributions from the community.