langchain_experimental 0.2.0rc1

langchain_experimental.agents

Agent is a class that uses an LLM to choose a sequence of actions to take.

In Chains, a sequence of actions is hardcoded. In Agents, a language model is used as a reasoning engine to determine which actions to take and in which order.

Agents select and use Tools and Toolkits for actions.

Functions

agents.agent_toolkits.csv.base.create_csv_agent(...)	Create pandas dataframe agent by loading csv to a dataframe.
agents.agent_toolkits.pandas.base.create_pandas_dataframe_agent(llm, df)	Construct a Pandas agent from an LLM and dataframe(s).
agents.agent_toolkits.python.base.create_python_agent(...)	Construct a python agent from an LLM and tool.
agents.agent_toolkits.spark.base.create_spark_dataframe_agent(llm, df)	Construct a Spark agent from an LLM and dataframe.
agents.agent_toolkits.xorbits.base.create_xorbits_agent(...)	Construct a xorbits agent from an LLM and dataframe.

langchain_experimental.autonomous_agents

Autonomous agents in the Langchain experimental package include [AutoGPT](https://github.com/Significant-Gravitas/AutoGPT), [BabyAGI](https://github.com/yoheinakajima/babyagi), and [HuggingGPT](https://arxiv.org/abs/2303.17580) agents that interact with language models autonomously.

These agents have specific functionalities like memory management, task creation, execution chains, and response generation.

They differ from ordinary agents by their autonomous decision-making capabilities, memory handling, and specialized functionalities for tasks and response.

Classes

autonomous_agents.autogpt.agent.AutoGPT(...)	Agent for interacting with AutoGPT.
autonomous_agents.autogpt.memory.AutoGPTMemory	Memory for AutoGPT.
autonomous_agents.autogpt.output_parser.AutoGPTAction(...)	Action returned by AutoGPTOutputParser.
autonomous_agents.autogpt.output_parser.AutoGPTOutputParser	Output parser for AutoGPT.
autonomous_agents.autogpt.output_parser.BaseAutoGPTOutputParser	Base Output parser for AutoGPT.
autonomous_agents.autogpt.prompt.AutoGPTPrompt	Prompt for AutoGPT.
autonomous_agents.autogpt.prompt_generator.PromptGenerator()	Generator of custom prompt strings.
autonomous_agents.baby_agi.baby_agi.BabyAGI	Controller model for the BabyAGI agent.
autonomous_agents.baby_agi.task_creation.TaskCreationChain	Chain generating tasks.
autonomous_agents.baby_agi.task_execution.TaskExecutionChain	Chain to execute tasks.
autonomous_agents.baby_agi.task_prioritization.TaskPrioritizationChain	Chain to prioritize tasks.
autonomous_agents.hugginggpt.hugginggpt.HuggingGPT(...)	Agent for interacting with HuggingGPT.
autonomous_agents.hugginggpt.repsonse_generator.ResponseGenerationChain	Chain to execute tasks.
autonomous_agents.hugginggpt.repsonse_generator.ResponseGenerator(...)	Generates a response based on the input.
autonomous_agents.hugginggpt.task_executor.Task(...)	Task to be executed.
autonomous_agents.hugginggpt.task_executor.TaskExecutor(plan)	Load tools and execute tasks.
autonomous_agents.hugginggpt.task_planner.BasePlanner	Base class for a planner.
autonomous_agents.hugginggpt.task_planner.Plan(steps)	A plan to execute.
autonomous_agents.hugginggpt.task_planner.PlanningOutputParser	Parses the output of the planning stage.
autonomous_agents.hugginggpt.task_planner.Step(...)	A step in the plan.
autonomous_agents.hugginggpt.task_planner.TaskPlaningChain	Chain to execute tasks.
autonomous_agents.hugginggpt.task_planner.TaskPlanner	Planner for tasks.

Functions

autonomous_agents.autogpt.output_parser.preprocess_json_input(...)	Preprocesses a string to be parsed as json.
autonomous_agents.autogpt.prompt_generator.get_prompt(tools)	Generates a prompt string.
autonomous_agents.hugginggpt.repsonse_generator.load_response_generator(llm)	Load the ResponseGenerator.
autonomous_agents.hugginggpt.task_planner.load_chat_planner(llm)	Load the chat planner.

langchain_experimental.chat_models

Chat Models are a variation on language models.

While Chat Models use language models under the hood, the interface they expose is a bit different. Rather than expose a “text in, text out” API, they expose an interface where “chat messages” are the inputs and outputs.

Class hierarchy:

BaseLanguageModel --> BaseChatModel --> <name>  # Examples: ChatOpenAI, ChatGooglePalm

Main helpers:

AIMessage, BaseMessage, HumanMessage

Classes

chat_models.llm_wrapper.ChatWrapper	Wrapper for chat LLMs.
chat_models.llm_wrapper.Llama2Chat	Wrapper for Llama-2-chat model.
chat_models.llm_wrapper.Mixtral	See https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1#instruction-format
chat_models.llm_wrapper.Orca	Wrapper for Orca-style models.
chat_models.llm_wrapper.Vicuna	Wrapper for Vicuna-style models.

langchain_experimental.comprehend_moderation

Comprehend Moderation is used to detect and handle Personally Identifiable Information (PII), toxicity, and prompt safety in text.

The Langchain experimental package includes the AmazonComprehendModerationChain class for the comprehend moderation tasks. It is based on Amazon Comprehend service. This class can be configured with specific moderation settings like PII labels, redaction, toxicity thresholds, and prompt safety thresholds.

See more at https://aws.amazon.com/comprehend/

Amazon Comprehend service is used by several other classes: - ComprehendToxicity class is used to check the toxicity of text prompts using

AWS Comprehend service and take actions based on the configuration

• ComprehendPromptSafety class is used to validate the safety of given prompt text, raising an error if unsafe content is detected based on the specified threshold

• ComprehendPII class is designed to handle Personally Identifiable Information (PII) moderation tasks, detecting and managing PII entities in text inputs

Classes

comprehend_moderation.amazon_comprehend_moderation.AmazonComprehendModerationChain	Moderation Chain, based on Amazon Comprehend service.
comprehend_moderation.base_moderation.BaseModeration(client)	Base class for moderation.
comprehend_moderation.base_moderation_callbacks.BaseModerationCallbackHandler()	Base class for moderation callback handlers.
comprehend_moderation.base_moderation_config.BaseModerationConfig	Base configuration settings for moderation.
comprehend_moderation.base_moderation_config.ModerationPiiConfig	Configuration for PII moderation filter.
comprehend_moderation.base_moderation_config.ModerationPromptSafetyConfig	Configuration for Prompt Safety moderation filter.
comprehend_moderation.base_moderation_config.ModerationToxicityConfig	Configuration for Toxicity moderation filter.
comprehend_moderation.base_moderation_exceptions.ModerationPiiError([...])	Exception raised if PII entities are detected.
comprehend_moderation.base_moderation_exceptions.ModerationPromptSafetyError([...])	Exception raised if Unsafe prompts are detected.
comprehend_moderation.base_moderation_exceptions.ModerationToxicityError([...])	Exception raised if Toxic entities are detected.
comprehend_moderation.pii.ComprehendPII(client)	Class to handle Personally Identifiable Information (PII) moderation.
comprehend_moderation.prompt_safety.ComprehendPromptSafety(client)	Class to handle prompt safety moderation.
comprehend_moderation.toxicity.ComprehendToxicity(client)	Class to handle toxicity moderation.

langchain_experimental.cpal

Causal program-aided language (CPAL) is a concept implemented in LangChain as a chain for causal modeling and narrative decomposition.

CPAL improves upon the program-aided language (PAL) by incorporating causal structure to prevent hallucination in language models, particularly when dealing with complex narratives and math problems with nested dependencies.

CPAL involves translating causal narratives into a stack of operations, setting hypothetical conditions for causal models, and decomposing narratives into story elements.

It allows for the creation of causal chains that define the relationships between different elements in a narrative, enabling the modeling and analysis of causal relationships within a given context.

Classes

cpal.base.CPALChain	Causal program-aided language (CPAL) chain implementation.
cpal.base.CausalChain	Translate the causal narrative into a stack of operations.
cpal.base.InterventionChain	Set the hypothetical conditions for the causal model.
cpal.base.NarrativeChain	Decompose the narrative into its story elements.
cpal.base.QueryChain	Query the outcome table using SQL.
cpal.constants.Constant(value)	Enum for constants used in the CPAL.
cpal.models.CausalModel	Casual data.
cpal.models.EntityModel	Entity in the story.
cpal.models.EntitySettingModel	Entity initial conditions.
cpal.models.InterventionModel	Intervention data of the story aka initial conditions.
cpal.models.NarrativeModel	Narrative input as three story elements.
cpal.models.QueryModel	Query data of the story.
cpal.models.ResultModel	Result of the story query.
cpal.models.StoryModel	Story data.
cpal.models.SystemSettingModel	System initial conditions.

langchain_experimental.data_anonymizer

Data anonymizer contains both Anonymizers and Deanonymizers. It uses the [Microsoft Presidio](https://microsoft.github.io/presidio/) library.

Anonymizers are used to replace a Personally Identifiable Information (PII) entity text with some other value by applying a certain operator (e.g. replace, mask, redact, encrypt).

Deanonymizers are used to revert the anonymization operation (e.g. to decrypt an encrypted text).

Classes

data_anonymizer.base.AnonymizerBase()	Base abstract class for anonymizers.
data_anonymizer.base.ReversibleAnonymizerBase()	Base abstract class for reversible anonymizers.
data_anonymizer.deanonymizer_mapping.DeanonymizerMapping(...)	Deanonymizer mapping.
data_anonymizer.presidio.PresidioAnonymizer([...])	Anonymizer using Microsoft Presidio.
data_anonymizer.presidio.PresidioAnonymizerBase([...])	Base Anonymizer using Microsoft Presidio.
data_anonymizer.presidio.PresidioReversibleAnonymizer([...])	Reversible Anonymizer using Microsoft Presidio.

Functions

data_anonymizer.deanonymizer_mapping.create_anonymizer_mapping(...)	Create or update the mapping used to anonymize and/or
data_anonymizer.deanonymizer_mapping.format_duplicated_operator(...)	Format the operator name with the count.
data_anonymizer.deanonymizer_matching_strategies.case_insensitive_matching_strategy(...)	Case insensitive matching strategy for deanonymization.
data_anonymizer.deanonymizer_matching_strategies.combined_exact_fuzzy_matching_strategy(...)	Combined exact and fuzzy matching strategy for deanonymization.
data_anonymizer.deanonymizer_matching_strategies.exact_matching_strategy(...)	Exact matching strategy for deanonymization.
data_anonymizer.deanonymizer_matching_strategies.fuzzy_matching_strategy(...)	Fuzzy matching strategy for deanonymization.
data_anonymizer.deanonymizer_matching_strategies.ngram_fuzzy_matching_strategy(...)	N-gram fuzzy matching strategy for deanonymization.
data_anonymizer.faker_presidio_mapping.get_pseudoanonymizer_mapping([seed])	Get a mapping of entities to pseudo anonymize them.

langchain_experimental.fallacy_removal

Fallacy Removal Chain runs a self-review of logical fallacies as determined by paper [Robust and Explainable Identification of Logical Fallacies in Natural Language Arguments](https://arxiv.org/pdf/2212.07425.pdf). It is modeled after Constitutional AI and in the same format, but applying logical fallacies as generalized rules to remove them in output.

Classes

fallacy_removal.base.FallacyChain	Chain for applying logical fallacy evaluations.
fallacy_removal.models.LogicalFallacy	Logical fallacy.

langchain_experimental.generative_agents

Generative Agent primitives.

Classes

generative_agents.generative_agent.GenerativeAgent	Agent as a character with memory and innate characteristics.
generative_agents.memory.GenerativeAgentMemory	Memory for the generative agent.

langchain_experimental.graph_transformers

Graph Transformers transform Documents into Graph Documents.

Classes

graph_transformers.diffbot.DiffbotGraphTransformer(...)	Transform documents into graph documents using Diffbot NLP API.
graph_transformers.diffbot.NodesList()	List of nodes with associated properties.
graph_transformers.diffbot.SimplifiedSchema()	Simplified schema mapping.
graph_transformers.diffbot.TypeOption(value)	An enumeration.
graph_transformers.llm.LLMGraphTransformer(llm)	Transform documents into graph-based documents using a LLM.
graph_transformers.llm.UnstructuredRelation	Create a new model by parsing and validating input data from keyword arguments.

Functions

graph_transformers.diffbot.format_property_key(s)	Formats a string to be used as a property key.
graph_transformers.llm.create_simple_model([...])	Simple model allows to limit node and/or relationship types.
graph_transformers.llm.create_unstructured_prompt([...])
graph_transformers.llm.format_property_key(s)
graph_transformers.llm.map_to_base_node(node)	Map the SimpleNode to the base Node.
graph_transformers.llm.map_to_base_relationship(rel)	Map the SimpleRelationship to the base Relationship.
graph_transformers.llm.optional_enum_field([...])	Utility function to conditionally create a field with an enum constraint.

langchain_experimental.llm_bash

LLM bash is a chain that uses LLM to interpret a prompt and executes bash code.

Classes

llm_bash.base.LLMBashChain	Chain that interprets a prompt and executes bash operations.
llm_bash.bash.BashProcess([strip_newlines, ...])	Wrapper for starting subprocesses.
llm_bash.prompt.BashOutputParser	Parser for bash output.

langchain_experimental.llm_symbolic_math

Chain that interprets a prompt and executes python code to do math.

Heavily borrowed from llm_math, uses the [SymPy](https://www.sympy.org/) package.

Classes

llm_symbolic_math.base.LLMSymbolicMathChain

Chain that interprets a prompt and executes python code to do symbolic math.

langchain_experimental.llms

Experimental LLM classes provide access to the large language model (LLM) APIs and services.

Classes

llms.anthropic_functions.AnthropicFunctions	[Deprecated] Chat model for interacting with Anthropic functions.
llms.anthropic_functions.TagParser()	Parser for the tool tags.
llms.jsonformer_decoder.JsonFormer	Jsonformer wrapped LLM using HuggingFace Pipeline API.
llms.llamaapi.ChatLlamaAPI	Chat model using the Llama API.
llms.lmformatenforcer_decoder.LMFormatEnforcer	LMFormatEnforcer wrapped LLM using HuggingFace Pipeline API.
llms.ollama_functions.OllamaFunctions	Function chat model that uses Ollama API.
llms.rellm_decoder.RELLM	RELLM wrapped LLM using HuggingFace Pipeline API.

Functions

llms.jsonformer_decoder.import_jsonformer()	Lazily import of the jsonformer package.
llms.lmformatenforcer_decoder.import_lmformatenforcer()	Lazily import of the lmformatenforcer package.
llms.ollama_functions.convert_to_ollama_tool(tool)	Convert a tool to an Ollama tool.
llms.ollama_functions.parse_response(message)	Extract function_call from AIMessage.
llms.rellm_decoder.import_rellm()	Lazily import of the rellm package.

langchain_experimental.open_clip

OpenCLIP Embeddings model.

OpenCLIP is a multimodal model that can encode text and images into a shared space.

See this paper for more details: https://arxiv.org/abs/2103.00020 and [this repository](https://github.com/mlfoundations/open_clip) for details.

Classes

open_clip.open_clip.OpenCLIPEmbeddings

OpenCLIP Embeddings model.

langchain_experimental.pal_chain

PAL Chain implements Program-Aided Language Models.

See the paper: https://arxiv.org/pdf/2211.10435.pdf.

This chain is vulnerable to [arbitrary code execution](https://github.com/langchain-ai/langchain/issues/5872).

Classes

pal_chain.base.PALChain	Chain that implements Program-Aided Language Models (PAL).
pal_chain.base.PALValidation([...])	Validation for PAL generated code.

langchain_experimental.plan_and_execute

Plan-and-execute agents are planning tasks with a language model (LLM) and executing them with a separate agent.

Classes

plan_and_execute.agent_executor.PlanAndExecute	Plan and execute a chain of steps.
plan_and_execute.executors.base.BaseExecutor	Base executor.
plan_and_execute.executors.base.ChainExecutor	Chain executor.
plan_and_execute.planners.base.BasePlanner	Base planner.
plan_and_execute.planners.base.LLMPlanner	LLM planner.
plan_and_execute.planners.chat_planner.PlanningOutputParser	Planning output parser.
plan_and_execute.schema.BaseStepContainer	Base step container.
plan_and_execute.schema.ListStepContainer	Container for List of steps.
plan_and_execute.schema.Plan	Plan.
plan_and_execute.schema.PlanOutputParser	Plan output parser.
plan_and_execute.schema.Step	Step.
plan_and_execute.schema.StepResponse	Step response.

Functions

plan_and_execute.executors.agent_executor.load_agent_executor(...)	Load an agent executor.
plan_and_execute.planners.chat_planner.load_chat_planner(llm)	Load a chat planner.

langchain_experimental.prompt_injection_identifier

HuggingFace Injection Identifier is a tool that uses [HuggingFace Prompt Injection model](https://huggingface.co/deepset/deberta-v3-base-injection) to detect prompt injection attacks.

Classes

prompt_injection_identifier.hugging_face_identifier.HuggingFaceInjectionIdentifier	Tool that uses HuggingFace Prompt Injection model to detect prompt injection attacks.
prompt_injection_identifier.hugging_face_identifier.PromptInjectionException([...])	Exception raised when prompt injection attack is detected.

langchain_experimental.recommenders

Amazon Personalize primitives.

[Amazon Personalize](https://docs.aws.amazon.com/personalize/latest/dg/what-is-personalize.html) is a fully managed machine learning service that uses your data to generate item recommendations for your users.

Classes

recommenders.amazon_personalize.AmazonPersonalize([...])	Amazon Personalize Runtime wrapper for executing real-time operations.
recommenders.amazon_personalize_chain.AmazonPersonalizeChain	Chain for retrieving recommendations from Amazon Personalize,

langchain_experimental.retrievers

Retriever class returns Documents given a text query.

It is more general than a vector store. A retriever does not need to be able to store documents, only to return (or retrieve) it.

Classes

retrievers.vector_sql_database.VectorSQLDatabaseChainRetriever

Retriever that uses Vector SQL Database.

langchain_experimental.rl_chain

RL (Reinforcement Learning) Chain leverages the Vowpal Wabbit (VW) models for reinforcement learning with a context, with the goal of modifying the prompt before the LLM call.

[Vowpal Wabbit](https://vowpalwabbit.org/) provides fast, efficient, and flexible online machine learning techniques for reinforcement learning, supervised learning, and more.

Classes

rl_chain.base.AutoSelectionScorer	Auto selection scorer.
rl_chain.base.Embedder(*args, **kwargs)	Abstract class to represent an embedder.
rl_chain.base.Event(inputs[, selected])	Abstract class to represent an event.
rl_chain.base.Policy(**kwargs)	Abstract class to represent a policy.
rl_chain.base.RLChain	Chain that leverages the Vowpal Wabbit (VW) model as a learned policy for reinforcement learning.
rl_chain.base.Selected()	Abstract class to represent the selected item.
rl_chain.base.SelectionScorer	Abstract class to grade the chosen selection or the response of the llm.
rl_chain.base.VwPolicy(model_repo, vw_cmd, ...)	Vowpal Wabbit policy.
rl_chain.metrics.MetricsTrackerAverage(step)	Metrics Tracker Average.
rl_chain.metrics.MetricsTrackerRollingWindow(...)	Metrics Tracker Rolling Window.
rl_chain.model_repository.ModelRepository(folder)	Model Repository.
rl_chain.pick_best_chain.PickBest	Chain that leverages the Vowpal Wabbit (VW) model for reinforcement learning with a context, with the goal of modifying the prompt before the LLM call.
rl_chain.pick_best_chain.PickBestEvent(...)	Event class for PickBest chain.
rl_chain.pick_best_chain.PickBestFeatureEmbedder(...)	Embed the BasedOn and ToSelectFrom inputs into a format that can be used by the learning policy.
rl_chain.pick_best_chain.PickBestRandomPolicy(...)	Random policy for PickBest chain.
rl_chain.pick_best_chain.PickBestSelected([...])	Selected class for PickBest chain.
rl_chain.vw_logger.VwLogger(path)	Vowpal Wabbit custom logger.

Functions

rl_chain.base.BasedOn(anything)	Wrap a value to indicate that it should be based on.
rl_chain.base.Embed(anything[, keep])	Wrap a value to indicate that it should be embedded.
rl_chain.base.EmbedAndKeep(anything)	Wrap a value to indicate that it should be embedded and kept.
rl_chain.base.ToSelectFrom(anything)	Wrap a value to indicate that it should be selected from.
rl_chain.base.embed(to_embed, model[, namespace])	Embed the actions or context using the SentenceTransformer model (or a model that has an encode function).
rl_chain.base.embed_dict_type(item, model)	Embed a dictionary item.
rl_chain.base.embed_list_type(item, model[, ...])	Embed a list item.
rl_chain.base.embed_string_type(item, model)	Embed a string or an _Embed object.
rl_chain.base.get_based_on_and_to_select_from(inputs)	Get the BasedOn and ToSelectFrom from the inputs.
rl_chain.base.is_stringtype_instance(item)	Check if an item is a string.
rl_chain.base.parse_lines(parser, input_str)	Parse the input string into a list of examples.
rl_chain.base.prepare_inputs_for_autoembed(inputs)	Prepare the inputs for auto embedding.
rl_chain.base.stringify_embedding(embedding)	Convert an embedding to a string.

langchain_experimental.smart_llm

SmartGPT chain is applying self-critique using the SmartGPT workflow.

See details at https://youtu.be/wVzuvf9D9BU

The workflow performs these 3 steps: 1. Ideate: Pass the user prompt to an Ideation LLM n_ideas times,

each result is an “idea”

2. Critique: Pass the ideas to a Critique LLM which looks for flaws in the ideas & picks the best one

3. Resolve: Pass the critique to a Resolver LLM which improves upon the best idea & outputs only the (improved version of) the best output

In total, the SmartGPT workflow will use n_ideas+2 LLM calls

Note that SmartLLMChain will only improve results (compared to a basic LLMChain), when the underlying models have the capability for reflection, which smaller models often don’t.

Finally, a SmartLLMChain assumes that each underlying LLM outputs exactly 1 result.

Classes

smart_llm.base.SmartLLMChain

Chain for applying self-critique using the SmartGPT workflow.

langchain_experimental.sql

SQL Chain interacts with SQL Database.

Classes

sql.base.SQLDatabaseChain	Chain for interacting with SQL Database.
sql.base.SQLDatabaseSequentialChain	Chain for querying SQL database that is a sequential chain.
sql.vector_sql.VectorSQLDatabaseChain	Chain for interacting with Vector SQL Database.
sql.vector_sql.VectorSQLOutputParser	Output Parser for Vector SQL.
sql.vector_sql.VectorSQLRetrieveAllOutputParser	Parser based on VectorSQLOutputParser.

Functions

sql.vector_sql.get_result_from_sqldb(db, cmd)

Get result from SQL Database.

langchain_experimental.tabular_synthetic_data

Generate tabular synthetic data using LLM and few-shot template.

Classes

tabular_synthetic_data.base.SyntheticDataGenerator

Generate synthetic data using the given LLM and few-shot template.

Functions

tabular_synthetic_data.openai.create_openai_data_generator(...)

Create an instance of SyntheticDataGenerator tailored for OpenAI models.

langchain_experimental.text_splitter

Experimental text splitter based on semantic similarity.

Classes

text_splitter.SemanticChunker(embeddings[, ...])

Split the text based on semantic similarity.

Functions

text_splitter.calculate_cosine_distances(...)	Calculate cosine distances between sentences.
text_splitter.combine_sentences(sentences[, ...])	Combine sentences based on buffer size.

langchain_experimental.tools

Experimental Python REPL tools.

Classes

tools.python.tool.PythonAstREPLTool	Tool for running python code in a REPL.
tools.python.tool.PythonInputs	Python inputs.
tools.python.tool.PythonREPLTool	Tool for running python code in a REPL.

Functions

tools.python.tool.sanitize_input(query)

Sanitize input to the python REPL.

langchain_experimental.tot

Implementation of a Tree of Thought (ToT) chain based on the paper [Large Language Model Guided Tree-of-Thought](https://arxiv.org/pdf/2305.08291.pdf).

The Tree of Thought (ToT) chain uses a tree structure to explore the space of possible solutions to a problem.

Classes

tot.base.ToTChain	Chain implementing the Tree of Thought (ToT).
tot.checker.ToTChecker	Tree of Thought (ToT) checker.
tot.controller.ToTController([c])	Tree of Thought (ToT) controller.
tot.memory.ToTDFSMemory([stack])	Memory for the Tree of Thought (ToT) chain.
tot.prompts.CheckerOutputParser	Parse and check the output of the language model.
tot.prompts.JSONListOutputParser	Parse the output of a PROPOSE_PROMPT response.
tot.thought.Thought	A thought in the ToT.
tot.thought.ThoughtValidity(value)	Enum for the validity of a thought.
tot.thought_generation.BaseThoughtGenerationStrategy	Base class for a thought generation strategy.
tot.thought_generation.ProposePromptStrategy	Strategy that is sequentially using a "propose prompt".
tot.thought_generation.SampleCoTStrategy	Sample strategy from a Chain-of-Thought (CoT) prompt.

Functions

tot.prompts.get_cot_prompt()	Get the prompt for the Chain of Thought (CoT) chain.
tot.prompts.get_propose_prompt()	Get the prompt for the PROPOSE_PROMPT chain.

langchain_experimental.utilities

Utility that simulates a standalone Python REPL.

Classes

utilities.python.PythonREPL

Simulates a standalone Python REPL.

langchain_experimental.video_captioning

Classes

video_captioning.base.VideoCaptioningChain	Video Captioning Chain.
video_captioning.models.AudioModel(...)
video_captioning.models.BaseModel(...)
video_captioning.models.CaptionModel(...)
video_captioning.models.VideoModel(...)
video_captioning.services.audio_service.AudioProcessor(api_key)
video_captioning.services.caption_service.CaptionProcessor(llm)
video_captioning.services.combine_service.CombineProcessor(llm)
video_captioning.services.image_service.ImageProcessor([...])
video_captioning.services.srt_service.SRTProcessor()