langchain 0.2.6__tar.gz → 0.2.7__tar.gz

langchain-0.2.7/PKG-INFO

@@ -0,0 +1,120 @@
+Metadata-Version: 2.1
+Name: langchain
+Version: 0.2.7
+Summary: Building applications with LLMs through composability
+Home-page: https://github.com/langchain-ai/langchain
+License: MIT
+Requires-Python: >=3.8.1,<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: PyYAML (>=5.3)
+Requires-Dist: SQLAlchemy (>=1.4,<3)
+Requires-Dist: aiohttp (>=3.8.3,<4.0.0)
+Requires-Dist: async-timeout (>=4.0.0,<5.0.0) ; python_version < "3.11"
+Requires-Dist: langchain-core (>=0.2.12,<0.3.0)
+Requires-Dist: langchain-text-splitters (>=0.2.0,<0.3.0)
+Requires-Dist: langsmith (>=0.1.17,<0.2.0)
+Requires-Dist: numpy (>=1,<2) ; python_version < "3.12"
+Requires-Dist: numpy (>=1.26.0,<2.0.0) ; python_version >= "3.12"
+Requires-Dist: pydantic (>=1,<3)
+Requires-Dist: requests (>=2,<3)
+Requires-Dist: tenacity (>=8.1.0,<9.0.0,!=8.4.0)
+Project-URL: Repository, https://github.com/langchain-ai/langchain
+Description-Content-Type: text/markdown
+
+# 🦜️🔗 LangChain
+
+⚡ Building applications with LLMs through composability ⚡
+
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
+[![lint](https://github.com/langchain-ai/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/lint.yml)
+[![test](https://github.com/langchain-ai/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/test.yml)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
+
+
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
+
+## Quick Install
+
+`pip install langchain`
+or
+`pip install langsmith && conda install langchain -c conda-forge`
+
+## 🤔 What is this?
+
+Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
+
+This library aims to assist in the development of those types of applications. Common examples of these applications include:
+
+**❓ Question answering with RAG**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
+
+**🧱 Extracting structured output**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
+
+**🤖 Chatbots**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
+- End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
+
+## 📖 Documentation
+
+Please see [here](https://python.langchain.com) for full documentation on:
+
+- Getting started (installation, setting up the environment, simple examples)
+- How-To examples (demos, integrations, helper functions)
+- Reference (full API docs)
+- Resources (high-level explanation of core concepts)
+
+## 🚀 What can this help with?
+
+There are five main areas that LangChain is designed to help with.
+These are, in increasing order of complexity:
+
+**📃 Models and Prompts:**
+
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with chat models and LLMs.
+
+**🔗 Chains:**
+
+Chains go beyond a single LLM call and involve sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
+
+**📚 Retrieval Augmented Generation:**
+
+Retrieval Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. Examples include summarization of long pieces of text and question/answering over specific data sources.
+
+**🤖 Agents:**
+
+Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents.
+
+**🧐 Evaluation:**
+
+[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+
+For more information on these concepts, please see our [full documentation](https://python.langchain.com).
+
+## 💁 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-0.2.7/README.md

@@ -0,0 +1,91 @@
+# 🦜️🔗 LangChain
+
+⚡ Building applications with LLMs through composability ⚡
+
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
+[![lint](https://github.com/langchain-ai/langchain/actions/workflows/lint.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/lint.yml)
+[![test](https://github.com/langchain-ai/langchain/actions/workflows/test.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/test.yml)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
+[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
+
+
+Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
+
+## Quick Install
+
+`pip install langchain`
+or
+`pip install langsmith && conda install langchain -c conda-forge`
+
+## 🤔 What is this?
+
+Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. However, using these LLMs in isolation is often insufficient for creating a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.
+
+This library aims to assist in the development of those types of applications. Common examples of these applications include:
+
+**❓ Question answering with RAG**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
+
+**🧱 Extracting structured output**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
+
+**🤖 Chatbots**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
+- End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
+
+## 📖 Documentation
+
+Please see [here](https://python.langchain.com) for full documentation on:
+
+- Getting started (installation, setting up the environment, simple examples)
+- How-To examples (demos, integrations, helper functions)
+- Reference (full API docs)
+- Resources (high-level explanation of core concepts)
+
+## 🚀 What can this help with?
+
+There are five main areas that LangChain is designed to help with.
+These are, in increasing order of complexity:
+
+**📃 Models and Prompts:**
+
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with chat models and LLMs.
+
+**🔗 Chains:**
+
+Chains go beyond a single LLM call and involve sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
+
+**📚 Retrieval Augmented Generation:**
+
+Retrieval Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. Examples include summarization of long pieces of text and question/answering over specific data sources.
+
+**🤖 Agents:**
+
+Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents.
+
+**🧐 Evaluation:**
+
+[BETA] Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+
+For more information on these concepts, please see our [full documentation](https://python.langchain.com).
+
+## 💁 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-0.2.7/langchain/__init__.py

@@ -0,0 +1,439 @@
+# ruff: noqa: E402
+"""Main entrypoint into package."""
+
+import warnings
+from importlib import metadata
+from typing import Any, Optional
+
+from langchain_core._api.deprecation import surface_langchain_deprecation_warnings
+
+try:
+    __version__ = metadata.version(__package__)
+except metadata.PackageNotFoundError:
+    # Case where package metadata is not available.
+    __version__ = ""
+del metadata  # optional, avoids polluting the results of dir(__package__)
+
+
+def _warn_on_import(name: str, replacement: Optional[str] = None) -> None:
+    """Warn on import of deprecated module."""
+    from langchain._api.interactive_env import is_interactive_env
+
+    if is_interactive_env():
+        # No warnings for interactive environments.
+        # This is done to avoid polluting the output of interactive environments
+        # where users rely on auto-complete and may trigger this warning
+        # even if they are not using any deprecated modules
+        return
+
+    if replacement:
+        warnings.warn(
+            f"Importing {name} from langchain root module is no longer supported. "
+            f"Please use {replacement} instead."
+        )
+    else:
+        warnings.warn(
+            f"Importing {name} from langchain root module is no longer supported."
+        )
+
+
+# Surfaces Deprecation and Pending Deprecation warnings from langchain.
+surface_langchain_deprecation_warnings()
+
+
+def __getattr__(name: str) -> Any:
+    if name == "MRKLChain":
+        from langchain.agents import MRKLChain
+
+        _warn_on_import(name, replacement="langchain.agents.MRKLChain")
+
+        return MRKLChain
+    elif name == "ReActChain":
+        from langchain.agents import ReActChain
+
+        _warn_on_import(name, replacement="langchain.agents.ReActChain")
+
+        return ReActChain
+    elif name == "SelfAskWithSearchChain":
+        from langchain.agents import SelfAskWithSearchChain
+
+        _warn_on_import(name, replacement="langchain.agents.SelfAskWithSearchChain")
+
+        return SelfAskWithSearchChain
+    elif name == "ConversationChain":
+        from langchain.chains import ConversationChain
+
+        _warn_on_import(name, replacement="langchain.chains.ConversationChain")
+
+        return ConversationChain
+    elif name == "LLMBashChain":
+        raise ImportError(
+            "This module has been moved to langchain-experimental. "
+            "For more details: "
+            "https://github.com/langchain-ai/langchain/discussions/11352."
+            "To access this code, install it with `pip install langchain-experimental`."
+            "`from langchain_experimental.llm_bash.base "
+            "import LLMBashChain`"
+        )
+
+    elif name == "LLMChain":
+        from langchain.chains import LLMChain
+
+        _warn_on_import(name, replacement="langchain.chains.LLMChain")
+
+        return LLMChain
+    elif name == "LLMCheckerChain":
+        from langchain.chains import LLMCheckerChain
+
+        _warn_on_import(name, replacement="langchain.chains.LLMCheckerChain")
+
+        return LLMCheckerChain
+    elif name == "LLMMathChain":
+        from langchain.chains import LLMMathChain
+
+        _warn_on_import(name, replacement="langchain.chains.LLMMathChain")
+
+        return LLMMathChain
+    elif name == "QAWithSourcesChain":
+        from langchain.chains import QAWithSourcesChain
+
+        _warn_on_import(name, replacement="langchain.chains.QAWithSourcesChain")
+
+        return QAWithSourcesChain
+    elif name == "VectorDBQA":
+        from langchain.chains import VectorDBQA
+
+        _warn_on_import(name, replacement="langchain.chains.VectorDBQA")
+
+        return VectorDBQA
+    elif name == "VectorDBQAWithSourcesChain":
+        from langchain.chains import VectorDBQAWithSourcesChain
+
+        _warn_on_import(name, replacement="langchain.chains.VectorDBQAWithSourcesChain")
+
+        return VectorDBQAWithSourcesChain
+    elif name == "InMemoryDocstore":
+        from langchain_community.docstore import InMemoryDocstore
+
+        _warn_on_import(name, replacement="langchain.docstore.InMemoryDocstore")
+
+        return InMemoryDocstore
+    elif name == "Wikipedia":
+        from langchain_community.docstore import Wikipedia
+
+        _warn_on_import(name, replacement="langchain.docstore.Wikipedia")
+
+        return Wikipedia
+    elif name == "Anthropic":
+        from langchain_community.llms import Anthropic
+
+        _warn_on_import(name, replacement="langchain_community.llms.Anthropic")
+
+        return Anthropic
+    elif name == "Banana":
+        from langchain_community.llms import Banana
+
+        _warn_on_import(name, replacement="langchain_community.llms.Banana")
+
+        return Banana
+    elif name == "CerebriumAI":
+        from langchain_community.llms import CerebriumAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.CerebriumAI")
+
+        return CerebriumAI
+    elif name == "Cohere":
+        from langchain_community.llms import Cohere
+
+        _warn_on_import(name, replacement="langchain_community.llms.Cohere")
+
+        return Cohere
+    elif name == "ForefrontAI":
+        from langchain_community.llms import ForefrontAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.ForefrontAI")
+
+        return ForefrontAI
+    elif name == "GooseAI":
+        from langchain_community.llms import GooseAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.GooseAI")
+
+        return GooseAI
+    elif name == "HuggingFaceHub":
+        from langchain_community.llms import HuggingFaceHub
+
+        _warn_on_import(name, replacement="langchain_community.llms.HuggingFaceHub")
+
+        return HuggingFaceHub
+    elif name == "HuggingFaceTextGenInference":
+        from langchain_community.llms import HuggingFaceTextGenInference
+
+        _warn_on_import(
+            name, replacement="langchain_community.llms.HuggingFaceTextGenInference"
+        )
+
+        return HuggingFaceTextGenInference
+    elif name == "LlamaCpp":
+        from langchain_community.llms import LlamaCpp
+
+        _warn_on_import(name, replacement="langchain_community.llms.LlamaCpp")
+
+        return LlamaCpp
+    elif name == "Modal":
+        from langchain_community.llms import Modal
+
+        _warn_on_import(name, replacement="langchain_community.llms.Modal")
+
+        return Modal
+    elif name == "OpenAI":
+        from langchain_community.llms import OpenAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.OpenAI")
+
+        return OpenAI
+    elif name == "Petals":
+        from langchain_community.llms import Petals
+
+        _warn_on_import(name, replacement="langchain_community.llms.Petals")
+
+        return Petals
+    elif name == "PipelineAI":
+        from langchain_community.llms import PipelineAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.PipelineAI")
+
+        return PipelineAI
+    elif name == "SagemakerEndpoint":
+        from langchain_community.llms import SagemakerEndpoint
+
+        _warn_on_import(name, replacement="langchain_community.llms.SagemakerEndpoint")
+
+        return SagemakerEndpoint
+    elif name == "StochasticAI":
+        from langchain_community.llms import StochasticAI
+
+        _warn_on_import(name, replacement="langchain_community.llms.StochasticAI")
+
+        return StochasticAI
+    elif name == "Writer":
+        from langchain_community.llms import Writer
+
+        _warn_on_import(name, replacement="langchain_community.llms.Writer")
+
+        return Writer
+    elif name == "HuggingFacePipeline":
+        from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
+
+        _warn_on_import(
+            name,
+            replacement="langchain_community.llms.huggingface_pipeline.HuggingFacePipeline",
+        )
+
+        return HuggingFacePipeline
+    elif name == "FewShotPromptTemplate":
+        from langchain_core.prompts import FewShotPromptTemplate
+
+        _warn_on_import(
+            name, replacement="langchain_core.prompts.FewShotPromptTemplate"
+        )
+
+        return FewShotPromptTemplate
+    elif name == "Prompt":
+        from langchain_core.prompts import PromptTemplate
+
+        _warn_on_import(name, replacement="langchain_core.prompts.PromptTemplate")
+
+        # it's renamed as prompt template anyways
+        # this is just for backwards compat
+        return PromptTemplate
+    elif name == "PromptTemplate":
+        from langchain_core.prompts import PromptTemplate
+
+        _warn_on_import(name, replacement="langchain_core.prompts.PromptTemplate")
+
+        return PromptTemplate
+    elif name == "BasePromptTemplate":
+        from langchain_core.prompts import BasePromptTemplate
+
+        _warn_on_import(name, replacement="langchain_core.prompts.BasePromptTemplate")
+
+        return BasePromptTemplate
+    elif name == "ArxivAPIWrapper":
+        from langchain_community.utilities import ArxivAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.ArxivAPIWrapper"
+        )
+
+        return ArxivAPIWrapper
+    elif name == "GoldenQueryAPIWrapper":
+        from langchain_community.utilities import GoldenQueryAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.GoldenQueryAPIWrapper"
+        )
+
+        return GoldenQueryAPIWrapper
+    elif name == "GoogleSearchAPIWrapper":
+        from langchain_community.utilities import GoogleSearchAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.GoogleSearchAPIWrapper"
+        )
+
+        return GoogleSearchAPIWrapper
+    elif name == "GoogleSerperAPIWrapper":
+        from langchain_community.utilities import GoogleSerperAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.GoogleSerperAPIWrapper"
+        )
+
+        return GoogleSerperAPIWrapper
+    elif name == "PowerBIDataset":
+        from langchain_community.utilities import PowerBIDataset
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.PowerBIDataset"
+        )
+
+        return PowerBIDataset
+    elif name == "SearxSearchWrapper":
+        from langchain_community.utilities import SearxSearchWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.SearxSearchWrapper"
+        )
+
+        return SearxSearchWrapper
+    elif name == "WikipediaAPIWrapper":
+        from langchain_community.utilities import WikipediaAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.WikipediaAPIWrapper"
+        )
+
+        return WikipediaAPIWrapper
+    elif name == "WolframAlphaAPIWrapper":
+        from langchain_community.utilities import WolframAlphaAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.WolframAlphaAPIWrapper"
+        )
+
+        return WolframAlphaAPIWrapper
+    elif name == "SQLDatabase":
+        from langchain_community.utilities import SQLDatabase
+
+        _warn_on_import(name, replacement="langchain_community.utilities.SQLDatabase")
+
+        return SQLDatabase
+    elif name == "FAISS":
+        from langchain_community.vectorstores import FAISS
+
+        _warn_on_import(name, replacement="langchain_community.vectorstores.FAISS")
+
+        return FAISS
+    elif name == "ElasticVectorSearch":
+        from langchain_community.vectorstores import ElasticVectorSearch
+
+        _warn_on_import(
+            name, replacement="langchain_community.vectorstores.ElasticVectorSearch"
+        )
+
+        return ElasticVectorSearch
+    # For backwards compatibility
+    elif name == "SerpAPIChain" or name == "SerpAPIWrapper":
+        from langchain_community.utilities import SerpAPIWrapper
+
+        _warn_on_import(
+            name, replacement="langchain_community.utilities.SerpAPIWrapper"
+        )
+
+        return SerpAPIWrapper
+    elif name == "verbose":
+        from langchain.globals import _verbose
+
+        _warn_on_import(
+            name,
+            replacement=(
+                "langchain.globals.set_verbose() / langchain.globals.get_verbose()"
+            ),
+        )
+
+        return _verbose
+    elif name == "debug":
+        from langchain.globals import _debug
+
+        _warn_on_import(
+            name,
+            replacement=(
+                "langchain.globals.set_debug() / langchain.globals.get_debug()"
+            ),
+        )
+
+        return _debug
+    elif name == "llm_cache":
+        from langchain.globals import _llm_cache
+
+        _warn_on_import(
+            name,
+            replacement=(
+                "langchain.globals.set_llm_cache() / langchain.globals.get_llm_cache()"
+            ),
+        )
+
+        return _llm_cache
+    else:
+        raise AttributeError(f"Could not find: {name}")
+
+
+__all__ = [
+    "LLMChain",
+    "LLMCheckerChain",
+    "LLMMathChain",
+    "ArxivAPIWrapper",
+    "GoldenQueryAPIWrapper",
+    "SelfAskWithSearchChain",
+    "SerpAPIWrapper",
+    "SerpAPIChain",
+    "SearxSearchWrapper",
+    "GoogleSearchAPIWrapper",
+    "GoogleSerperAPIWrapper",
+    "WolframAlphaAPIWrapper",
+    "WikipediaAPIWrapper",
+    "Anthropic",
+    "Banana",
+    "CerebriumAI",
+    "Cohere",
+    "ForefrontAI",
+    "GooseAI",
+    "Modal",
+    "OpenAI",
+    "Petals",
+    "PipelineAI",
+    "StochasticAI",
+    "Writer",
+    "BasePromptTemplate",
+    "Prompt",
+    "FewShotPromptTemplate",
+    "PromptTemplate",
+    "ReActChain",
+    "Wikipedia",
+    "HuggingFaceHub",
+    "SagemakerEndpoint",
+    "HuggingFacePipeline",
+    "SQLDatabase",
+    "PowerBIDataset",
+    "FAISS",
+    "MRKLChain",
+    "VectorDBQA",
+    "ElasticVectorSearch",
+    "InMemoryDocstore",
+    "ConversationChain",
+    "VectorDBQAWithSourcesChain",
+    "QAWithSourcesChain",
+    "LlamaCpp",
+    "HuggingFaceTextGenInference",
+]