Changelog

1.4.4

🐛 Bug Fixes:

• Change DataConnection.download_folder method in case of NFSLocation

• Check if CPD before checking if datasource type is volumes

• Update RemoteFileStorage conversion

1.4.3

🚀 Features:

• Added support for specifying hardware_spec as dict in batch deployment

• Add Path to public method signatures

🐛 Bug Fixes:

• Support absolute path provided in FSLocation.path for uploading and downloading data

• Use new Vector Store parameters only if set to non-default for CPD <= 5.2

• Set raise_error_for_list to True for all _validate_type calls with lists

• Modify warning read in BaseModelInference._return_guardrails_stats

1.4.2

🚀 Features:

• Added support for knowledge base references in AutoAI RAG

• Added support for specifying BYOM functions

• Support custom text_field/query_field parameter in VectorStore adapters

🐛 Bug Fixes:

• Accept verify as path to cert file

1.4.1

🚀 Features:

• Add SDK support for One-click RAG

• Added methods for listing models with LoRA and QLoRA fine tuning support

• WDU text classification support added

• Added support for custom document_id, sequence_number and text fields in VectorStore

• Add support for int values for holdout_size

1.4.0

🚀 Features:

• Refactored get_model_specs to return all available models (previously limited to text generation). Introduced get_text_generation_model_specs as a dedicated method for retrieving only text generation models

• Support new chat parameters - chat_template_kwargs, reasoning_effort, include_reasoning

• Added limit to Connections.get_details and Connections.list methods

• Add attempt_activation param to Deployments.get_details

• Removed support for IBM Cloud Pak® for Data 4.8.x

🐛 Bug Fixes:

• Fixed default setting of Flight hostname on SOD clusters

1.3.40

🚀 Features:

• Enable APIClient initialization with 5.3 CPD version

🐛 Bug Fixes:

• Added missing imports in Training and BaseDataConnection classes

• Fixed checking software specification lifecycle in shiny

• Fixed APIClient initialization for watsonx.ai lightweight clusters

1.3.39

🚀 Features:

• Added support for chat mode & parameters

• Added RemoteFileStorageLocation class

• Added async methods to Repository class

• Added option to include SPEC_STATE and SPEC_REPLACEMENT columns in client.deployments.list()

• Added async methods to Models class

• Added support for automatically filled documentation.functions and documentation.init

• Added async methods to Deployments class

• Added async methods to AIServices class

• Added async methods to ModelDefinition class

• Added async methods to Functions class

• Added async methods to Pipelines class

• Added async methods to Experiments class

• Added async methods to Assets class

• Added async methods to Spaces class

• Added async methods to SwSpec class

• Added async methods to PkgExtn class

🐛 Bug Fixes:

• Removed deprecated params from get_sample_params

• Fix NoDocumentsLoaded error message

• add empty file check to prevent unclear error

• Removed unsupported arguments for storing HDF5 model using Keras v3

1.3.38

🚀 Features:

• Added filters param in get_model_specs method, added get_text_generation_model_specs method

• remove daub_adaptive_subsampling_max_mem_usage filed from sdk

• Update TextChatResponseFormat and related classes, introduce TextChatResponseJsonSchema

• Add support for chat parameters for DeploymentModelInference on Cloud

🐛 Bug Fixes:

• Raise error when user calls set_token with None

• Improve error handling for service unavailability in authentication flow

• Text extractor converts timestamp while extracting xlsx file

• Added deprecation warnings on AutoAIRAG text gen params

1.3.37

🚀 Features:

• Present AutoAI RAG settings importance as pd.DataFrame

🐛 Bug Fixes:

• Fix destination path for uploading file to FS on CPD with remote_name defined

• Fix for AWS token generation

• Fix source project/space during Batch creation

• Fix download folder without slash in location path on CPD

• Block container use on CPD space

1.3.36

🚀 Features:

• Make instance_id optional in APIClient

• Added support for guided_* parameters in text/chat endpoint

🐛 Bug Fixes:

• unify type of _datasource_type attr

1.3.35

🚀 Features:

• Support for trusted profile with token

🐛 Bug Fixes:

• Updated function parsing using ast library

1.3.34

🚀 Features:

• Add new param for TabularIterableDataset to control casting strings to float and bool

• Added informative error if restricted connection is passed to VectorStores

• Added support for runtime_definitions API

• Support fine-tuning live metrics in FineTuner.plot_learning_curve and FineTuner.summary

• Added delete method to Training class

🐛 Bug Fixes:

• Added prepending of project / space ID to ContainerLocation.path for shared buckets

• Update Batch.run_job to properly import pd.Dataframe

• Accept FLIGHT_SERVICE_LOCATION with schema for backward compatibility

• Extended retry logic in FlightConnection class

• Added “event: error” handling in chat_stream/achat_stream methods

1.3.33

🚀 Features:

• Added FineTuner.get_logs() method to allow getting logs for completed FT training

• Added support for max_completion_tokens param in /ml/v1//text/chat endpoint

• Added support for /ml/v1/audio/transcriptions endpoint

🐛 Bug Fixes:

• Fixed setting SSL parameter in get_db2() method

• Compliance with breaking changes delivered in mcp package

• Added support for .yaml files with end of directives markers

• Used FLIGHT_SERVICE_LOCATION environment variable when provided

1.3.32

🚀 Features:

• Implement dedicated VectorStore for DB2

• Add skip_fallback to DataConnection.read

• Support loading and deploying ONNX models

• Added SEMANTIC_CONFIG to TextExtractionsV2ParametersMetaNames enum

• Added force flag to artifact delete methods

🐛 Bug Fixes:

• Brought back TabularIterableDataset.connection property

• Remove incorrect closing queue in documents loader

• Fix getting fine-tuning run details including metrics on CPD

1.3.31

🚀 Features:

• Trusted profiles authentication support

• Tools support for BYOM chat

🐛 Bug Fixes:

• Fixed downloading AutoAI’s results assets in notebook scenario

• Replace problematic chars in documents with question marks when generating document_id

• Fixed configuration for Git Based Projects

1.3.30

🐛 Bug Fixes:

• Improved writing to file while downloading data_assets with binary=True.

1.3.29

🚀 Features:

• Improved loading all documents from subfolders.

• Load AI service generated in AutoAI RAG experiment in get_pattern method.

• TabularDocumentsIterableDataset added.

1.3.28

🚀 Features:

• Changed AutoAI RAG experiment test_data_references as optional field.

• Added support for FolderAssets.

🐛 Bug Fixes:

• Decreased number of requests to datasource_types API.

• Removed delay in client.spaces.store() method.

1.3.27

🚀 Features:

• Added support for documentation.init and documentation.functions in AI services

🐛 Bug Fixes:

• Fix results_reference.location.path for Fine Tuning

1.3.26

🚀 Features:

• Add future_data as a param in forecast() method instead of kwargs

• Deprecate inference_function and indexing_function

🐛 Bug Fixes:

• Improve elastic strategy

• Added support for initializing Volumes only on CPD

• Add checking for models supporting function chat only

• Handle custom datasource types in list method

• Fixed downloading AutoAI’s artifacts on AWS

• Fix for storing package extensions on AWS

• Lock token generation

1.3.25

🚀 Features:

• Fixed DataConnection methods for AWS IBM Cloud

• Add Semantic Chunker

• Model Gateway - support for beta release

🐛 Bug Fixes:

• Double token generation fix

1.3.24

🚀 Features:

• Add to_langchain_tool method to Retriever class

• Support loading xml files

• Add methods to runtime context

• Add suffix path ai service deployment

• Added support for Vector Index assets

🐛 Bug Fixes:

• Add missing docstring example for TS BYOM

• Map all private AWS wx.ai endpoints to public platform

1.3.23

🐛 Bug Fixes:

• Improvements for private AWS endpoints

1.3.22

🚀 Features:

• Added support for Granite Guardian in generate, generate_stream methods

• get_copy method added to APIClient

• Add async methods for Embeddings

🐛 Bug Fixes:

• Add fallback for adding documents to Elasticsearch vector store

• Add error when external VectorStore used

1.3.21

🐛 Bug Fixes:

• TSModelInference not working when client has project or space is provided

1.3.20

🚀 Features:

• Add support for time_series BYOM on Cloud

1.3.19

🚀 Features:

• Support for container data reference and folder download for FS and Container location on CPD

🐛 Bug Fixes:

• Changed Flight service connection closing time

• Add text field to hybrid strategy

1.3.18

🚀 Features:

• Support for authorization in AWS environments

🐛 Bug Fixes:

• Added retries for client.connections.get_datasource_type_details_by_id()

• Auth method has timedelta set automatically when not provided

1.3.17

🐛 Bug Fixes:

• Fix passing vector field names for Elasticsearch

1.3.16

🐛 Bug Fixes:

• Updated CPD version requirements for TextExtractionsV2 class

• Disable inference function in RagPattern

1.3.15

🚀 Features:

• Support for hybrid search in AutoAI RAG experiments

1.3.14

🚀 Features:

• Deprecation warning for Prompt Tuning with CPD 5.2

• Added support for Python 3.13

• Added support for Guardian (Text Detection)

🐛 Bug Fixes:

• Patch payload generation for CPD 5.2 fixed

1.3.13

🐛 Bug Fixes:

• Use pymilvus<2.5.7 in rag dependencies

1.3.12

🚀 Features:

• WDU 2.0 adaption for TextExtractions

• AutoAI RAG support for BYOM

• Allowed passing connection args without connection_id and langchain VS

• Enable store base Foundation Models on Cloud

🐛 Bug Fixes:

• Removed setting first_line_header Flight interaction property when reading data in binary mode and removed quote_character when reading csv files

• Added support for deleting Deployment Jobs on CPD 5.1 version and lower

1.3.11

🚀 Features:

• AutoAI RAG adjustments for the preview

• Added support for folder download

🐛 Bug Fixes:

• Updated url in load_file_from_file_system

• Fixed logic to check if the deployment update was successful

• Fixed AutoAI-Generated Notebook

• Fixed summary method, added support BYOM for get_pattern

• Modify message for missing cryptography package error in text_loader.py

1.3.8

🚀 Features:

• Rework Toolkit class

🐛 Bug Fixes:

• Improved Deployments.update() to wait for the deployment to be ready

• Improve model store response handling for CPD 5.2

1.3.6

🚀 Features:

• Add converters for utility agent tools

• Improve flight retry logic

• .yaml documents supported in Document Loader

🐛 Bug Fixes:

• ModelInference should set project/space when deployment_id and validate is provided

• Disable TokenBucket for CPD

1.3.5

🚀 Features:

• Implementation of hybrid search - RAG

• .json documents supported in document loader

• Added initial support for CP4D 5.2

• Add get_space_id() to RuntimeContext

• .pptx documents supported in document loader

🐛 Bug Fixes:

• Validation of training data reference type moved to back-end repository Service

• Updated error message for AutoAI RAG run

1.3.3

🚀 Features:

• Added get_headers method to APIClient class

1.3.2

🚀 Features:

• Add default params to RAGPattern AI service

• Added support for retrieval parameter of AutoAI RAG

• Added support for generation parameter of AutoAI RAG

• Add async httpx client

• Expose gradient_checkpointing parameter to users for fine-tuning

• Assets duplicate_action parameter support added

• Support for tooling in Repository.store_ai_service method

• Trashed assets module added to SDK

🐛 Bug Fixes:

• Fix removing tmp file

• Removed requirement for default preset for AI service run

• Fix for hanging of job when the passed benchmark data path is non existing

• Added deprecation for SentenceTransformerEmbeddings class

• Fixed building docs

• Replaced project_lib package removed in RT 25.1 with ibm_watson_studio_lib

• Added support for number columns in CSV-s and Excel files

• Fixed summary method when Fine-Tuning experiment has 1 epoch

1.3.1

🚀 Features:

• Introduce httpx client in deployments, foundation models

🐛 Bug Fixes:

• support data fields to detached prompt template

1.3.0

🚀 Features:

• Introduce httpx client in deployments, foundation models

🐛 Bug Fixes:

• support data fields to detached prompt template

1.2.10

🚀 Features:

• Handle retry more robustly

• add reference documents to ragpattern service stream

• Support for Utility Agent Tools

🐛 Bug Fixes:

• Verify is set correctly for httpx client

• Support for deployment of ai service generated in experiments with chroma vector store

• Fixed validation version parameter only for CPD

• Fixed extra-space for time_limit parameter in GenTextParamsMetaNames

1.2.9

🚀 Features:

• Change authentication method in flight and refactor to allow private RT

• Added support for window search with Elastisearch

🐛 Bug Fixes:

• Change approach to listing limit of resources

• Proxies setting for httpx fixed

• Raise error when adding not chunked documents to vector store

1.2.8

🚀 Features:

• Add get_all param to AutoPipelinesRuns.list() and set 200 as default listed records number

🐛 Bug Fixes:

• Allow inference deployments without providing project_id or space_id

• APIClient.set_token is correctly changing authentication method

• Updated concurrency_limit default value to 8

• Improved CP4D version value handling

• Convert strings with regex causing SyntaxWarning to raw strings

• Added missing parameters to TextChatParameters dataclass

1.2.7

🚀 Features:

• Added get_all param to RAGEngine.get_details()

🐛 Bug Fixes:

• Allow passing concurrency_limit in init Embeddings

• Raise error that AutoAI RAG is not available only if response is 404

• Return usage metadata when running ModelInference.chat_stream() method

1.2.6

🚀 Features:

• Support for reading documents from NFS folder

1.2.5

🚀 Features:

• Support for LoRA/QLoRA Tuning in watsonx.ai Software 5.1.1 and latest

🐛 Bug Fixes:

• Replace only the first occurrence in the response text of stream mode

• Added error to handle method not allowed in run AI Services

• Disable warnings from pypdf.PdfReader in TextLoader

1.2.4

🚀 Features:

• Added support to generate token from zen-service-broker-secret

• Added support for AI Services on CPD 5.1.1 and latest

• Added indexing step to autogenerated inference AI service in ChromaDB scenario in RAGPattern

• Added support for native async stream methods for text generation and chat

🐛 Bug Fixes:

• Fixed authentication error during text generation with using meta-llama/llama-3-1-8b-instruct

• Check file extension with lowercase filename

• Raise error when error event occurs during generating stream

• Removed default list length limit for WML Resources

• Improved error message for creating connections with invalid payload

1.2.2

🚀 Features:

• Added integration with ILAB/wx.ai

🐛 Bug Fixes:

• Import pyarrow only when FlightConnection is used

• Closing httpx.Response in retry mechanism

1.2.1

🚀 Features:

• Introduced support for AI-Service within RAGPattern

• Implemented validation for CPD url to ensure correctness

• Added support for new status object in get AutoAI RAG run response

• Removed potential scheme in flight_location

🐛 Bug Fixes:

• Rename parameter name word_to_token_factor to word_to_token_ratio in prompt builder

• Enhanced AutoPipelinesRuns.get_run_details() to retrieve the latest run across all endpoints and raise an error when resources are unavailable

• Added custom timeout to close persistent connection

• Task Credentials support improvements

• Discover all available assets instead of limited to 100

• Fixed endpoints for API DataPlatform

• Disable warnings logger for LangChainChunker.split_documents()

1.1.26

🐛 Bug Fixes:

• Get the latest run including both endpoints and raise an error if empty resources - TuneRuns.get_run_details()

• Added validation of storage details in project/ space details for Container DataConnection

• Added fs as model supported training data references type

• Updated the cancel_run method in RAGOptimizer to avoid returning cached training details

1.1.25

🚀 Features:

• Add cancel job to the text extractions

• Support for Deploy on Demand

• Added word_to_token_factor parameter to RAGPattern constructor

• Add batch size param to embeddings

• Updated add_documents method in milvus_adapter

🐛 Bug Fixes:

• add batch size to dict only if customized

• Added training data references type validation in repository.store_model

• Disable logging NotS3Connection in one case

• Pagination support added to lookup datasources types

• Pagination added for datasources

1.1.24

🚀 Features:

• Add support for IBM watsonx.data Milvus connection

• Added method to get chat model specs with function calling support

• Add support for achat method

🐛 Bug Fixes:

• Improve storing AI services content

1.1.23

🚀 Features:

• Support for Sydney watsonx.ai API endpoint

• Add ‘Large’ option for HardwareRequestSizes

🐛 Bug Fixes:

• Update connections to enable AutoAI RAG experiment

1.1.22

🚀 Features:

• Adjusted ai_service support to align with recent changes in the AI services backend

• Added deprecation warning on Model class

• Support for writing to FSLocation

• Add get id by name for spaces

🐛 Bug Fixes:

• Downgraded the grpcio version to >=1.54.3

• Remove flag from RagPattern constructor

• Updated show schema method

• Update text extraction delete job

• SSL error fixed on FIPS cluster when downloading documents from COS folder

• save Milvus’s SSL certificate file in temporary file

• Improve error message for creating connections with invalid payload

• Update set_api_client method

1.1.17

🚀 Features:

• Added documentation for Fine-Tuning: Working with TuneExperiment and FineTuner

🐛 Bug Fixes:

• Improved error reporting for DataConnection.read() when attempting to read from a database with the flight service disabled

• Added a generic error message for failed attempts to download datasets due to flight service issues

• Restricted Python version compatibility to versions below 3.13

• Migrated dependencies to LangChain version 0.3.x

1.1.16

🚀 Features:

• Introduced support for loading text from Markdown files in the TextLoader class

• Added an enum for rerank models: client.foundation_models.RerankModels

• Enhanced the get_details method with an optional name parameter

• Implemented the set_api_client method in the ModelInference class

🐛 Bug Fixes:

• Added 429 error handling for the set.default_project method’s project_id component

• Improved error handling during data loading operations

• Fixed an issue where the get_id_by_name method raised an error when no ID was found for the specified name

1.1.15

🚀 Features:

• Introduced support for AI services

• Added support for Rerank functionality: Rerank Documentation

• Added support for Text Extraction results in Markdown format.

🐛 Bug Fixes:

• Updated the route for CPD token generation for CPD versions 5.1 and above

• Disabled AutoAI TSAD in the SDK for CPD versions starting from 5.1

1.1.14

🚀 Features:

• Added support for the Chat API

🐛 Bug Fixes:

• Automatically added the https:// prefix to the COS connection endpoint_url if missing.

1.1.13

🚀 Features:

• Introduced the get_evaluation_results method in the RAGOptimizer class

• Added support for CPD version 5.1

🐛 Bug Fixes:

• Corrected the example value for TextExtractionsMetaNames

• Relaxed version constraints for LangChain packages

1.1.12

🚀 Features:

• Added the option to install langchain_community with the [rag] option

🐛 Bug Fixes:

• Fixed an issue with DataConnection as a container folder.

• Updated the load() method docstring in the documentation.

• Added support for platform URLs in credentials.

1.1.11

🚀 Features:

• Added integration for AutoAI RAG SDK: Working with AutoAI RAG class and rag_optimizer

🐛 Bug Fixes:

• Increased batch_size reduction in AutoAI RAG experiments

1.1.10

🐛 Bug Fixes:

• Added a timeout to DocumentsIterableDataset iteration

• Included a private development URL in the platform map

1.1.9

🚀 Features:

• Introduced support for Fine-Tuning

• Added support for native asynchronous methods for model inference

1.1.8

🚀 Features:

• Added support for MCSP

🐛 Bug Fixes:

• Fixed an issue with reading JSON files without binary mode, resolving problems with reading Prompt Tuning files

1.1.7

🚀 Features:

• Added a timeout for persistent connections

🐛 Bug Fixes:

• Set a default max_sequence_length to avoid model limits errors

1.1.6

🚀 Features:

• Added support for ConnectionAsset without a specified location

🐛 Bug Fixes:

• Resolved an issue where model specification filters were not available in version 4.8

• Fixed a bug related to unsupported connection types

• Aligned logging for improved consistency

1.1.5

🚀 Features:

• Implemented Keep-Alive and persistent connections for tokenization

• Added support for the text extraction endpoint: Text Extractions Documentation

🐛 Bug Fixes:

• Resolved the issue with missing python-docx

1.1.4

🚀 Features:

• Introduced support for Hardware Request field instead of the Hardware Specification

• Added an asynchronous generate method

• Implemented support for the api_client parameter in DocumentIterableDataset

🐛 Bug Fixes:

• Fixed an issue with storing TaskCredential

• Improved de-duplication in the add_documents method of the vector store to include both text and its document ID

1.1.3

🚀 Features:

• Introduced support for Bring Your Own Model (BYOM)

🐛 Bug Fixes:

• Set input_shape during training, addressing issues with dataset training data

• Removed the timeout for reading documents

• Implemented improvements to the Documents Dataset

1.1.2

🐛 Bug Fixes:

• Resolved an issue caused by a breaking change in setuptools version 71.0.1

1.1.1

🐛 Bug Fixes:

• Added a setter for the ServiceInstance.details property

1.1.0

🚀 Features:

• Added Keep-Alive functionality for FoundationModels requests

• Introduced support for the private wml-fvt endpoint

• Added installation support for RAG group packages

🐛 Bug Fixes:

• Improved performance of the APIClient initialization

• Disabled lifecycle checks when validation is turned off

• Updated Scikit-learn for federated learning support

• Resolved issues with reading data from NFS connections in Git-based projects

• Changed the default behavior to read files on the cloud with Flight Service enabled

1.0.10

🚀 Features:

• Added support for different input modes of Prompt Templates(PromptTemplate, FreeformPromptTemplate, DetachedPromptTemplate).

🐛 Bug Fixes:

• Fixed validation for tech preview models.

• Fixed set project for git-based-project in new scenario.

• Fixed used filters for get_model_specs method.

1.0.9

🚀 Features:

• Added support for tech preview models

• Added additional information in request headers.

• Extend VectorStore functionalities via concrete wrappers(For Vector Index notebooks)

1.0.8

🚀 Features:

• Added validate_prompt_variables parameter to generate method in Model and ModelInference class.

• Added hardware_spec support in Batch class.

🐛 Bug Fixes:

• Fixed correct schema for timeseries-anomaly-prediction prediction type.

1.0.6

🐛 Bug Fixes:

• Added more clear Error message when user pass invalid credentials.

• Fixed “Invalid authorization token” error when initializing the client with the “USER_ACCESS_TOKEN” environment variable on a cluster

1.0.5

🚀 Features:

• Added auto-generated Enum classes (TextModels, EmbeddingModels, PromptTunableModels) with available models

🐛 Bug Fixes:

• Better filtering of supported runtimes for r-scripts

• Fixed downloading model content to file

• Improved scaling Prompt Tuning charts

• Provided a clearer error message when a user passes an incorrect URL to the cluster

1.0.4

🚀 Features:

• Added forecast_window parameter support for online deployment scoring

1.0.3

🚀 Features:

• Milvus support for RAG extension

• Autogenerated changelog

• Travis is tagging the version during push into production

🐛 Bug Fixes:

• Reading data assets as binary when flight is unavailable

• next resource generator type fixed, other internal type issues fixed

• Reading tabular dataset with non-unique columns

• Deprecation warnings removed when using fm_model_inference

1.0.2

🚀 Features:

• Added get and get_item methods for better compatibility with SDK v0

🐛 Bug Fixes:

• Relaxed package version checking

• Fixed AutoAI initialization without version in credentials

• Fixed calls to wx endpoints in git base project

• Fixed backward compatibility of WebService and Batch class for credentials in dictionary

1.0.1

🐛 Bug Fixes:

• Hotfix for imports

1.0.0

🚀 Features:

• RAGutils module added

• Getting foundation models specs moved under foundation models object

• Credentials as object + proxies supported

• WCA service support

🐛 Bug Fixes:

• Minor corrections/improvements to Foundation Models module