Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
APACHE-2.0 License
Bot releases are visible (Hide)
PromptTask
.DuckDuckGoWebSearchDriver
.Published by collindutter 3 months ago
RagEngine
is an abstraction for implementing modular RAG pipelines.
RagContext
is a container object for passing around RAG context.QueryRagStage
for parsing and expanding queries.RetrievalRagStage
for retrieving content.ResponseRagStage
for augmenting and generating outputs.VectorStoreRetrievalRagModule
for retrieving text chunks from vector stores.TextLoaderRetrievalRagModule
for retrieving data with text loaders in real time.TextChunksRerankRagModule
for re-ranking retrieved results.MetadataBeforeResponseRagModule
for appending metadata.RulesetsBeforeResponseRagModule
for appending rulesets.PromptResponseRagModule
for generating responses based on retrieved text chunks.TextChunksResponseRagModule
for responding with retrieved text chunks.FootnotePromptResponseRagModule
for responding with automatic footnotes from text chunk references.RagClient
tool for exposing RagEngines
to LLM agents.RagTask
task for including RagEngines
in any structure.CohereRerankDriver
for using the Cohere rerank API.utils.execute_futures_list()
for executing a list of futures.LocalVectorStoreDriver.persist_file
for persisting vectors and chunks in a text file.Entry.to_artifact()
for easy vector store entry conversions into Griptape artifacts.BaseVectorStoreDriver.does_entry_exist()
to check if an entry exists in the vector store.GoogleWebSearchDriver
to web search with the Google Customsearch API.DuckDuckGoWebSearchDriver
to web search with the DuckDuckGo search SDK.ProxyWebScraperDriver
to web scrape using proxies.session
on AmazonBedrockStructureConfig
.meta
on TextArtifact
.VectorStoreClient
improvements:
VectorStoreClient.query_params
dict for custom query params.VectorStoreClient.process_query_output_fn
for custom query output processing logic.fail_fast
to Structure
.BooleanArtifact
for handling boolean values.typos
to dev dependencies to catch typos in code/docs.Message
for storing messages in a PromptStack
. Messages consist of a role, content, and usage.DeltaMessage
for storing partial messages in a PromptStack
. Multiple DeltaMessage
can be combined to form a Message
.TextMessageContent
for storing textual content in a Message
.ImageMessageContent
for storing image content in a Message
.TextArtifact
s, ImageArtifact
s, and ListArtifact
s to PromptStack
.OpenAiChatPromptDriver
, AzureOpenAiChatPromptDriver
, AmazonBedrockPromptDriver
, AnthropicPromptDriver
, and GooglePromptDriver
.FinishPromptEvent.input_token_count
and FinishPromptEvent.output_token_count
.Agent.input
for passing Artifacts as input.PromptTask
s to take TextArtifact
s, ImageArtifact
s, and ListArtifact
s as input.sort_key
and sort_key_value
on AmazonDynamoDbConversationMemoryDriver
for tables with sort keys.Reference
for supporting artifact citations in loaders and RAG engine modules.griptape.utils.PromptStack
to griptape.common.PromptStack
.PromptStack.inputs
to PromptStack.messages
.PromptStack.USER_ROLE
, PromptStack.ASSISTANT_ROLE
, and PromptStack.SYSTEM_ROLE
to Message
.PromptDriver.try_run
from TextArtifact
to Message
.PromptDriver.try_stream
from Iterator[TextArtifact]
to Iterator[DeltaMessage]
.BasePromptEvent.token_count
in favor of FinishPromptEvent.input_token_count
and FinishPromptEvent.output_token_count
.StartPromptEvent.prompt
. Use StartPromptEvent.prompt_stack
instead.Agent.input_template
in favor of Agent.input
.BasePromptDriver.run
now returns a Message
instead of a TextArtifact
. For compatibility, Message.value
contains the Message's Artifact valueBaseVectorStoreDriver.upsert_text_artifact()
and BaseVectorStoreDriver.upsert_text()
use artifact/string values to generate vector_id
if it wasn't implicitly passed. This change ensures that we don't generate embeddings for the same content every time.VectorQueryEngine
in favor of RagEngine
.TextQueryTask
in favor of RagTask
.TextArtifactStorage
now requires vector_store_driver
and rag_engine
in place of vector_query_engine
.load_artifacts()
from BaseQueryEngine
to BaseVectorStoreDriver
.BaseVectorStoreDriver.QueryResult
into BaseVectorStoreDriver.Entry
.query_engine
with vector_store_driver
in VectorStoreClient
.google_api_lang
, google_api_key
, google_api_search_id
, google_api_country
on WebSearch
in favor of web_search_driver
.VectorStoreClient.top_n
and VectorStoreClient.namespace
in favor of VectorStoreClient.query_params
.futures_executor
fields renamed to futures_executor_fn
and now accept callables instead of futures; wrapped all future submit
calls with the with
block to address future executor shutdown issues.GriptapeCloudKnowledgeBaseClient
migrated to /search
api.GoogleStructureConfig
to gemini-1.5-pro
.CoherePromptDriver
to properly handle empty history.StructureVisualizer.to_url()
by wrapping task IDs in single quotes.Published by andrewfrench 4 months ago
Full Changelog: https://github.com/griptape-ai/griptape/compare/0.27.0...0.27.2
Published by collindutter 4 months ago
BaseTask.add_child()
to add a child task to a parent task.BaseTask.add_children()
to add multiple child tasks to a parent task.BaseTask.add_parent()
to add a parent task to a child task.BaseTask.add_parents()
to add multiple parent tasks to a child task.Structure.resolve_relationships()
to resolve asymmetrically defined parent/child relationships. In other words, if a parent declares a child, but the child does not declare the parent, the parent will automatically be added as a parent of the child when running this method. The method is invoked automatically by Structure.before_run()
.CohereEmbeddingDriver
for using Cohere's embeddings API.CohereStructureConfig
for providing Structures with quick Cohere configuration.AmazonSageMakerJumpstartPromptDriver.inference_component_name
for setting the InferenceComponentName
parameter when invoking an endpoint.AmazonSageMakerJumpstartEmbeddingDriver.inference_component_name
for setting the InferenceComponentName
parameter when invoking an endpoint.AmazonSageMakerJumpstartEmbeddingDriver.custom_attributes
for setting custom attributes when invoking an endpoint.ToolkitTask.response_stop_sequence
for overriding the default Chain of Thought stop sequence.griptape.utils.StructureVisualizer
for visualizing Workflow structures with Mermaid.jsBaseTask.parents_outputs
to get the textual output of all parent tasks.BaseTask.parents_output_text
to get a concatenated string of all parent tasks' outputs.parents_output_text
to Workflow context.OllamaPromptModelDriver
for using models with Ollama.output
on Structure
as a convenience for output_task.output
Workflow
no longer modifies task relationships when adding tasks via tasks
init param, add_tasks()
or add_task()
. Previously, adding a task would automatically add the previously added task as its parent. Existing code that relies on this behavior will need to be updated to explicitly add parent/child relationships using the API offered by BaseTask
.AmazonBedrockPromptDriver.prompt_model_driver
as it is no longer needed with the AmazonBedrockPromptDriver
Converse API implementation.BedrockClaudePromptModelDriver
.BedrockJurassicPromptModelDriver
.BedrockLlamaPromptModelDriver
.BedrockTitanPromptModelDriver
.BedrockClaudeTokenizer
, use SimpleTokenizer
instead.BedrockJurassicTokenizer
, use SimpleTokenizer
instead.BedrockLlamaTokenizer
, use SimpleTokenizer
instead.BedrockTitanTokenizer
, use SimpleTokenizer
instead.OpenAiChatCompletionPromptDriver
as it uses the legacy OpenAi Completions API.BasePromptDriver.count_tokens()
.BasePromptDriver.max_output_tokens()
.PromptStack.add_to_conversation_memory
to BaseConversationMemory.add_to_prompt_stack
.griptape.constants.RESPONSE_STOP_SEQUENCE
to ToolkitTask
.AmazonSagemakerPromptDriver
to AmazonSageMakerJumpstartPromptDriver
.SagemakerFalconPromptModelDriver
, use AmazonSageMakerJumpstartPromptDriver
instead.SagemakerLlamaPromptModelDriver
, use AmazonSageMakerJumpstartPromptDriver
instead.AmazonSagemakerEmbeddingDriver
to AmazonSageMakerJumpstartEmbeddingDriver
.SagemakerHuggingfaceEmbeddingModelDriver
, use AmazonSageMakerJumpstartEmbeddingDriver
instead.SagemakerTensorflowHubEmbeddingModelDriver
, use AmazonSageMakerJumpstartEmbeddingDriver
instead.AmazonSageMakerJumpstartPromptDriver.model
parameter, which gets passed to SageMakerRuntime.Client.invoke_endpoint
as EndpointName
, is now renamed to AmazonSageMakerPromptDriver.endpoint
.template_generator
on PromptSummaryEngine
and added parameters system_template_generator
and user_template_generator
.engines/summary/prompt_summary.j2
and added templates engines/summary/system.j2
and engines/summary/user.j2
.ToolkitTask.RESPONSE_STOP_SEQUENCE
is now only added when using ToolkitTask
.BasePromptDriver.max_tokens
instead of using BasePromptDriver.max_output_tokens()
.GriptapeCloudKnowledgeBaseClient
does not have a description set.AmazonBedrockPromptDriver
to use Converse API.Structure.before_run()
now automatically resolves asymmetrically defined parent/child relationships using the new Structure.resolve_relationships()
.HuggingFaceHubPromptDriver
to use transformers
's apply_chat_template
.HuggingFacePipelinePromptDriver
to use chat features of transformers.TextGenerationPipeline
.CoherePromptDriver
to use Cohere's latest SDK.Structure.before_run
.PromptSummaryEngine
.templates/tasks/tool_task/system.j2
.Workflow.insert_task()
no longer inserts duplicate tasks when given multiple parent tasks.OpenAiChatPromptDriver
when extracting unused rate-limiting headers.Structure.stream
field.output_task.output
is not None
on all Structures
TextArtifacts
contained in ListArtifact
returned by WebSearch.search
to properly formatted stringified JSON.max_tokens
< 0 on BaseChunker
Published by collindutter 5 months ago
AzureOpenAiStructureConfig
for providing Structures with all Azure OpenAI Driver configuration.AzureOpenAiVisionImageQueryDriver
to support queries on images using Azure's OpenAI Vision models.AudioLoader
for loading audio content into an AudioArtifact
.AudioTranscriptionTask
and AudioTranscriptionClient
for transcribing audio content in Structures.OpenAiAudioTranscriptionDriver
for integration with OpenAI's speech-to-text models, including Whisper.env
to BaseStructureRunDriver
to set environment variables for a Structure Run.PusherEventListenerDriver
to enable sending of framework events over a Pusher WebSocket.StructureConfig.global_drivers
. Pass Drivers directly to the Structure Config instead.StructureConfig.task_memory
in favor of configuring directly on the Structure.off_prompt
now defaults to False
on all Tools, making Task Memory something that must be explicitly opted into.AmazonSageMakerPromptDriver.model
parameter, which gets passed to SageMakerRuntime.Client.invoke_endpoint
as EndpointName
, is now renamed to AmazonSageMakerPromptDriver.endpoint
.AmazonSageMakerPromptDriver.model
parameter is now optional being passed to SageMakerRuntime.Client.invoke_endpoint
as InferenceComponentName
(instead of EndpointName
).SageMakerLlamaPromptModelDriver
modified to exclusively support the Llama 3 Instruct model deployed via SageMaker JumpStart. (Support for Llama 2 models has been removed.)TextArtifactStorage
Engines optional.azure_deployment
on all Azure Drivers to the model the Driver is using.azure_ad_token
on all Azure Drivers is no longer serializable.gpt-4o
.Published by andrewfrench 5 months ago
namespace
in RedisVectorStoreDriver.query()
.meta
, score
, and vector
fields of query result returned from RedisVectorStoreDriver.query()
.ActionsSubtask
.id
field to all events.gpt-4o
for prompt_driver.Published by collindutter 6 months ago
list_files_from_disk
activity to FileManager
Tool.EventListener
.AmazonSqsEventListenerDriver
for sending events to an Amazon SQS queue.AwsIotCoreEventListenerDriver
for sending events to a topic on AWS IoT Core.GriptapeCloudEventListenerDriver
for sending events to Griptape Cloud.WebhookEventListenerDriver
for sending events to a webhook.BaseFileManagerDriver
to abstract file management operations.LocalFileManagerDriver
for managing files on the local file system.BaseLoader.encoding
field.BlobLoader
for loading arbitrary binary data as a BlobArtifact
.model
field to StartPromptEvent
and FinishPromptEvent
.input_task_input
and input_task_output
fields to StartStructureRunEvent
.output_task_input
and output_task_output
fields to FinishStructureRunEvent
.AmazonS3FileManagerDriver
for managing files on Amazon S3.MediaArtifact
as a base class for ImageArtifact
and future media Artifacts.exception
field to ErrorArtifact
.StructureRunClient
for running other Structures via a Tool.StructureRunTask
for running Structures as a Task from within another Structure.GriptapeCloudStructureRunDriver
for running Structures in Griptape Cloud.LocalStructureRunDriver
for running Structures in the same run-time environment as the code that is running the Structure.FileLoader
.CsvLoader
no longer accepts str
file paths as a source. It will now accept the content of the CSV file as a str
or bytes
object.PdfLoader
no longer accepts str
file content, Path
file paths or IO
objects as sources. Instead, it will only accept the content of the PDF file as a bytes
object.TextLoader
no longer accepts Path
file paths as a source. It will now accept the content of the text file as a str
or bytes
object.FileManager.default_loader
is now None
by default.pinecone
from ^2
to ^3
.workdir
, loaders
, default_loader
, and save_file_encoding
fields from FileManager
and added file_manager_driver
.mime_type
field from ImageArtifact
. mime_type
is now a property constructed using the Artifact type and format
field.VectorQueryEngine
.EventListener.handler
's behavior so that the return value will be passed to the EventListenerDriver.try_publish_event_payload
's event_payload
parameter.azure_ad_token_provider
on Azure OpenAI drivers to Optional[Callable[[], str]]
.azure_ad_token
and azure_ad_token_provider
on the default client for AzureOpenAiCompletionPromptDriver
.Published by andrewfrench 7 months ago
jsonschema
dependency by @vasinov in https://github.com/griptape-ai/griptape/pull/718
Full Changelog: https://github.com/griptape-ai/griptape/compare/v0.24.0...v0.24.1
Published by cjkindel 7 months ago
ToolkitTask
can now execute multiple actions in parallel.BaseActionsSubtaskEvent.subtask_actions
.text-embedding-3-small
and text-embedding-3-large
models.GooglePromptDriver
and GoogleTokenizer
for use with gemini-pro
.GoogleEmbeddingDriver
for use with embedding-001
.GoogleStructureConfig
for providing Structures with Google Prompt and Embedding Driver configuration.claude-3-opus
, claude-3-sonnet
, and claude-3-haiku
in AnthropicPromptDriver
.anthropic.claude-3-sonnet-20240229-v1:0
and anthropic.claude-3-haiku-20240307-v1:0
in BedrockClaudePromptModelDriver
.top_k
and top_p
parameters in AnthropicPromptDriver
.AnthropicImageQueryDriver
for Claude-3 multi-modal modelsAmazonBedrockImageQueryDriver
along with BedrockClaudeImageQueryDriverModel
for Claude-3 in Bedrock supportBaseWebScraperDriver
allowing multiple web scraping implementations.TrafilaturaWebScraperDriver
for scraping text from web pages using trafilatura.MarkdownifyWebScraperDriver
for scraping text from web pages using playwright and converting to markdown using markdownify.VoyageAiEmbeddingDriver
for use with VoyageAi's embedding models.AnthropicStructureConfig
for providing Structures with Anthropic Prompt and VoyageAi Embedding Driver configuration.ToolTask
to support more use cases.ActionSubtask
was renamed to ActionsSubtask
.subtask_action_name
, subtask_action_path
, and subtask_action_input
in BaseActionsSubtaskEvent
.OpenAiVisionImageQueryDriver
field model
no longer defaults to gpt-4-vision-preview
and must be specifiedOpenAiEmbeddingDriver
to text-embedding-3-small
.OpenAiStructureConfig
to text-embedding-3-small
.BaseTextLoader
to accept a BaseChunker
.AmazonBedrockStructureConfig
to anthropic.claude-3-sonnet-20240229-v1:0
.AnthropicPromptDriver
and BedrockClaudePromptModelDriver
to use Anthropic's Messages API.OpenAiVisionImageQueryDriver
now has a required field max_tokens
that defaults to 256Published by collindutter 7 months ago
Structure.prompt_driver
, Structure.embedding_driver
, and Structure.stream
.DummyException
error message not fully displaying.StructureConfig.task_memory
not defaulting to using StructureConfig.global_drivers
by default.Published by collindutter 8 months ago
GriptapeCloudKnowledgeBaseClient
's API URLs.Published by andrewfrench 8 months ago
AzureMongoDbVectorStoreDriver
for using CosmosDB with MongoDB vCore API.vector_path
field on MongoDbAtlasVectorStoreDriver
.LeonardoImageGenerationDriver
supports image to image generation.OpenAiStructureConfig
for providing Structures with all OpenAi Driver configuration.AmazonBedrockStructureConfig
for providing Structures with all Amazon Bedrock Driver configuration.StructureConfig
for building your own Structure configuration.JsonExtractionTask
for convenience over using ExtractionTask
with a JsonExtractionEngine
.CsvExtractionTask
for convenience over using ExtractionTask
with a CsvExtractionEngine
.OpenAiVisionImageQueryDriver
to support queries on images using OpenAI's Vision model.ImageQueryClient
allowing an Agent to make queries on images on disk or in Task Memory.ImageQueryTask
and ImageQueryEngine
.RestApiClient
.BedrockStableDiffusionImageGenerationModelDriver
request parameters for SDXLv1.BedrockStableDiffusionImageGenerationModelDriver
correctly handles the CONTENT_FILTERED response case.index_name
on MongoDbAtlasVectorStoreDriver
a required field.create_index()
from MarqoVectorStoreDriver
, OpenSearchVectorStoreDriver
, PineconeVectorStoreDriver
, RedisVectorStoreDriver
.ImageLoader().load()
now accepts image bytes instead of a file path.Structure.prompt_driver
in favor of Structure.config.global_drivers.prompt_driver
.Structure.embedding_driver
in favor of Structure.config.global_drivers.embedding_driver
.Structure.stream
in favor of Structure.config.global_drivers.prompt_driver.stream
.TextSummaryTask.summary_engine
now defaults to a PromptSummaryEngine
with a Prompt Driver default of Structure.config.global_drivers.prompt_driver
.TextQueryTask.query_engine
now defaults to a VectorQueryEngine
with a Prompt Driver default of Structure.config.global_drivers.prompt_driver
and Vector Store Driver default of Structure.config.global_drivers.vector_store_driver
.PromptImageGenerationTask.image_generation_engine
now defaults to a PromptImageGenerationEngine
with an Image Generation Driver default of Structure.config.global_drivers.image_generation_driver
.VariationImageGenerationTask.image_generation_engine
now defaults to a VariationImageGenerationEngine
with an Image Generation Driver default of Structure.config.global_drivers.image_generation_driver
.InpaintingImageGenerationTask.image_generation_engine
now defaults to an InpaintingImageGenerationEngine
with an Image Generation Driver default of Structure.config.global_drivers.image_generation_driver
.OutpaintingImageGenerationTask.image_generation_engine
now defaults to an OutpaintingImageGenerationEngine
with an Image Generation Driver default of Structure.config.global_drivers.image_generation_driver
.AwsS3Client
sets name of returned artifact to downloaded object key.Full Changelog: https://github.com/griptape-ai/griptape/compare/v0.22.3...v0.23.0
Published by collindutter 9 months ago
ToolkitTask
's user subtask prompt occasionally causing the Task to end prematurely.Published by collindutter 9 months ago
ToolkitTask
's user subtask prompt occassionally causing a loop with Chain of Thought.Published by collindutter 9 months ago
Published by collindutter 9 months ago
PromptImageGenerationEngine
for generating images from text prompts.VariationImageGenerationEngine
for generating variations of an input image according to a text prompt.InpaintingImageGenerationEngine
for modifying an input image according to a text prompt within the bounds of a mask defined by a mask image.OutpaintingImageGenerationEngine
for modifying an input image according to a text prompt outside the bounds of a mask defined by a mask image.PromptImageGenerationClient
for enabling an LLM to use the PromptImageGenerationEngine
.VariationImageGenerationClient
for enabling an LLM to use the VariationImageGenerationEngine
.InpaintingImageGenerationClient
for enabling an LLM to use the InpaintingImageGenerationEngine
.OutpaintingImageGenerationClient
for enabling an LLM to use the OutpaintingImageGenerationEngine
.OpenAiImageGenerationDriver
for use with OpenAI's image generation models.LeonardoImageGenerationDriver
for use with Leonoaro AI's image generation models.AmazonBedrockImageGenerationDriver
for use with Amazon Bedrock's image generation models; requires a Image Generation Model Driver.BedrockTitanImageGenerationModelDriver
for use with Amazon Bedrock's Titan image generation.ImageArtifact
for storing image data; used heavily by the image Engines, Tasks, and Drivers.ImageLoader
for loading images files into ImageArtifact
s.OpenAiChatPromptDriver
, enabling OpenAI drop-in clients such as Together AI.AmazonSageMakerEmbeddingDriver
for using Amazon SageMaker to generate embeddings. Thanks @KaushikIyer16!AnthropicPromptDriver
and AmazonBedrockPromptDriver
via BedrockClaudePromptModelDriver
.CodeExecutionTask
for executing code as a Task without the need for an LLM.BedrockLlamaPromptModelDriver
for using Llama models on Amazon Bedrock.MongoDbAtlasVectorStore
namespace not being used properly when querying.ToolTask
system prompt template.input_task
's input
.SqlClient
exception. Thanks @michal-repo!input_template
field to input
in Tasks that take a text input.BedrockTitanEmbeddingDriver
to AmazonBedrockTitanEmbeddingDriver
.AmazonBedrockStableDiffusionImageGenerationModelDriver
to BedrockStableDiffusionImageGenerationModelDriver
.AmazonBedrockTitanImageGenerationModelDriver
to BedrockTitanImageGenerationModelDriver
.ImageGenerationTask
to PromptImageGenerationTask
.ImageGenerationEngine
to PromptImageGenerationEngine
.ImageGenerationTool
to PromptImageGenerationClient
.BaseTextInputTask
to accept a str
, TextArtifact
or callable returning a TextArtifact
.Published by andrewfrench 10 months ago
Published by collindutter 10 months ago
griptape.schemas.utils
.Published by collindutter 10 months ago
hugging_face_hub_prompt_driver.py
to huggingface_hub_prompt_driver.py
.hugging_face_pipeline_prompt_driver.py
to huggingface_pipeline_prompt_driver.py
.hugging_face_tokenizer.py
to huggingface_tokenizer.py
.ProxycurlClient
Tool to dedicated repository.HuggingFaceEmbeddingDriver
.SimpleTokenizer
for use with LLM providers that don't provide tokenization APIs.Chat
util. Thanks @mattma1970!AzureOpenAiDalleImageGenerationDriver
, LeonardoImageGenerationDriver
, and AmazonBedrockImageGenerationDriver
).HuggingFaceHubPromptDriver
.prompt_stack
and prompt
fields to StartPromptEvent
to allow for inspection of the prompt before sending to the LLM.HuggingFaceHubPromptDriver
to use new InferenceClient
.OpenSearchVectorStoreDriver.query
argument order. Thanks @igor-2lemetry!FileManager
working directory not updating when using os.cwd()
.WebLoader
failing when extracting empty pages.SummaryConversationMemory
failing to deserialize.HuggingFaceEmbeddingDriver
.hugging_face
-> huggingface
rename.Published by collindutter 11 months ago
BaseTask.add_child
and BaseTask.add_parent
. Use Workflow.add_task(s)
and Workflow.insert_task(s)
instead.ToolOutputProcessor
to TaskMemoryClient
.TaskMemoryClient
. If your Tools have data that needs to go to the LLM, you must set either set off_prompt=False
on the Tool, or add TaskMemoryClient
with off_prompt=False
.Structure.run
to return a Structure
. This resolves inconsistencies in the run
return values across Agents, Pipelines and Workflows. You can access the output Task value via Structure.output_task.output.value
.AzureOpenAiChatPromptDriver
's deployment_id
and api_base
to azure_deployment
and azure_endpoint
.Structure.tool_memory
to Structure.task_memory
.ToolMemory
to TaskMemory
.Structure.memory
to Structure.conversation_memory
.TextQueryTask.load
method.seed
parameter to OpenAiChatPromptDriver
. Read more about this parameter here.response_format
parameter to OpenAiChatPromptDriver
and AzureOpenAiChatPromptDriver
. Read more about this parameter here.gpt-4-1106-preview
(gpt-4-turbo
) in OpenAiChatPromptDriver
.insert_tasks
. See example usage here.off_prompt
parameter to all Tools. With the exception of TaskMemoryClient
(no default provided), off_prompt
defaults to True
meaning that the Tool results will go into Task Memory. If you'd like the results to go directly back to the LLM, set off_prompt
to False
.namespace
parameter to TextQueryTask
.encoding
parameter to TextLoader
.download_objects
parameter to AwsS3Client
.encoding
parameter to TextLoader
and TextArtifact
.to_bytes
method to TextArtifact
.openai
's sdk to ^1.1.0
.MetaMemory
to store ActionSubtask
results to improve the LLM's reasoning when using ToolkitTask
. Other applications of MetaMemory
will be added in future releases.ToolkitTask
.ToolTask
and ToolkitTask
to reduce action hallucinations.Workflow.insert_tasks
method.seed
and response_format
parameters.TaskMemoryClient
and off_prompt
parameters.