What's new

Third-party text embedding models are available in watsonx.ai

16 May 2024

The following third-party text embedding models are now available in addition to the IBM Slate models for enhanced text matching and retrieval:

• all-minilm-l12-v2
• bge-large-en-v1.5
• multilingual-e5-large

Submit sentences or passages to one of the supported embedding models by using the watsonx.ai Python library or REST API to convert input text into vectors to more accurately compare and retrieve similar text.

For more information about these models, see Supported embedding models.

For more information about converting text, see Text embedding generation.

New Granite Code Instruct models are available in the Dallas region

9 May 2024

You can now inference the following Granite Code Instruct foundation models provided by IBM from watsonx.ai:

• granite-3b-code-instruct
• granite-8b-code-instruct
• granite-20b-code-instruct
• granite-34b-code-instruct

Use the new Granite Code Instruct foundation models for programmatic coding tasks. The foundation models are fine-tuned on a combination of instruction data to enhance instruction-following capabilities including logical reasoning and problem solving.

For more information, see Supported foundation models.

InstructLab foundation models are available in watsonx.ai

7 May 2024

InstructLab is an open source initiative by Red Hat and IBM that provides a platform for augmenting the capabilities of a foundation model. The following foundation models support knowledge and skills that are contributed from InstructLab:

• granite-7b-lab
• granite-13-chat-v2
• granite-20b-multilingual
• merlinite-7b

You can explore the open source community contributions from the foundation model's taxonomy page.

For more information, see InstructLab-compatible foundation models.

Organize project assets into folders

2 May 2024

You can now create folders in your projects to organize assets. An administrator of the project must enable folders, and administrators and editors can create and manage them. Folders are in beta and are not yet supported for use in production environments. For more information, see Organizing assets with folders (beta).

IBM watsonx.ai is available in the London region

25 Apr 2023

Watsonx.ai is now generally available in the London data center and London can be selected as the preferred region when signing-up.

• The foundation models that are fully supported in Dallas are also available for inferencing in the London data center from the Prompt Lab or by using the API. The exceptions are mt0-xxl-13b and the llama-2-70b-chat foundation model, which is superseded by the llama-3-70b-instruct foundation model that is now available.
• Prompt-tune the three tunable foundation models from the Tuning Studio or by using the API.
• The two IBM embedding models and the embeddings API are supported.

For more information, see Regional availability for services and features.

Start a chat in Prompt Lab directly from the home page

25 Apr 2023

Now you can start a conversation with a foundation model from the IBM watsonx.ai home page. Enter a question to send to a foundation model in chat mode or click Open Prompt Lab to choose a foundation model and model parameters before you submit model input.

New Meta Llama 3 foundation models are now available

18 Apr 2024

The following Llama 3 foundation models provided by Meta are available for inferencing from watsonx.ai:

• llama-3-8b-instruct
• llama-3-70b-instruct

The new Llama 3 foundation models are instruction fine-tuned language models that can support various use cases.

This latest release of Llama is trained with more tokens and applies new post-training procedures. The result is foundation models with better language comprehension, reasoning, code generation, and instruction-following capabilities.

For more information, see Supported foundation models.

Introducing IBM embedding support for enhanced text matching and retrieval

18 Apr 2024

You can now use the IBM embeddings API and IBM embedding models for transforming input text into vectors to more accurately compare and retrieve similar text.

The following IBM Slate embedding models are available:

• slate.125m.english.rtrvr
• slate.30m.english.rtrvr

For more information, see Text embedding generation.

For pricing details, see Watson Machine Learning plans.

IBM watsonx.governance is included when you sign up for IBM watsonx.ai

18 Apr 2024

If you sign up for watsonx.ai in the Dallas region, watsonx.governance is now included automatically. See Signing up for IBM watsonx as a Service.

Evaluate machine learning deployments in spaces

18 Apr 2024

Configure watsonx.governance evaluations in your deployment spaces to gain insights about your machine learning model performance. For example, evaluate a deployment for bias or monitor a deployment for drift. When you configure evaluations, you can analyze evaluation results and model transaction records directly in your spaces.

For more information, see Evaluating deployments in spaces.

A Korean-language foundation model is available in the Tokyo region

18 Apr 2024

The llama2-13b-dpo-v7 foundation model provided by Minds & Company and based on the Llama 2 foundation model from Meta is available in the Tokyo region.

The llama2-13b-dpo-v7 foundation model specializes in conversational tasks in Korean and English. You can also use the llama2-13b-dpo-v7 foundation model for general purpose tasks in the Korean language.

For more information, see Supported foundation models.

A mixtral-8x7b-instruct-v01 foundation model is available for inferencing

18 Apr 2024

The mixtral-8x7b-instruct-v01 foundation model from Mistral AI is available for inferencing from watsonx.ai. The mixtral-8x7b-instruct-v01 foundation model is a pretrained generative model that uses a sparse mixture-of-experts network to generate text more efficiently.

You can use the mixtral-8x7b-instruct-v01 model for general-purpose tasks, including classification, summarization, code generation, language translation, and more. For more information, see Supported foundation models.

The mixtral-8x7b-instruct-v01-q foundation model is deprecated and will be withdrawn on 23 May 2024. Revise any prompts that use this foundation model.

• Deprecation date: 19 April 2024
• Withdrawal date: 20 June 2024
• Alternative model: mixtral-8x7b-instruct-v01

Inference requests that are submitted to the mixtral-8x7b-instruct-v01-q model by using the API continue to generate output, but include a warning message about the upcoming model withdrawal. Starting on 20 June 2024, API requests for inferencing the models will not generate output.

For more information about deprecation and withdrawal, see Foundation model lifecycle.

A modification to the granite-20b-multilingual foundation model is introduced

18 Apr 2024

The latest version of the granite-20b-multilingual is 1.1.0. The modification includes improvements that were gained by applying a novel AI alignment technique to the version 1.0 model. AI alignment involves using fine-tuning and reinforcement learning techniques to guide the model to return outputs that are as helpful, truthful, and transparent as possible.

For more information about this foundation model, see Supported foundation models.

Prompt-tune the granite-13b-instruct-v2 foundation model

11 Apr 2024

The Tuning Studio now supports tuning the granite-13b-instruct-v2 foundation model in addition to the flan-t5-xl-3b and llama-2-13b-chat foundation models. For more information, see Tuning a foundation model.

The experiment configuration settings for tuning the granite-13b-instruct-v2 foundation model change to apply the best default values depending on your task. The tuning evaluation guidelines help you to analyze the experiment results and adjust experiment configuration settings based on your findings. For more information, see Evaluating the results of a tuning experiment.

An Arabic-language foundation model is available in the Frankfurt region

11 Apr 2024

The jais-13b-chat foundation model provided by Inception, Mohamed bin Zayed University of Artificial Intelligence, and Cerebras Systems is available in the Frankfurt region.

The jais-13b-chat foundation model specializes in conversational tasks in Arabic and English. You can also use the jais-13b-chat foundation model for general purpose tasks in the Arabic language, including language translation between Arabic and English.

For more information, see Supported foundation models.

View the full text of a prompt in Prompt Lab

11 Apr 2024

Now you can review the full prompt text that will be submitted to the foundation model, which is useful when your prompt includes prompt variables or when you're working in structured mode or chat mode.

For more information, see Prompt Lab.

The deprecated Granite version 1 models are withdrawn

11 Apr 2024

The following foundation models are now withdrawn:

• granite-13b-chat-v1
• granite-13b-instruct-v1

Revise any prompts that use these foundation models to use the IBM Granite v2 foundation models. For more information about foundation model deprecation and withdrawal, see Foundation model lifecycle.

Use pivot tables to display data aggregated in Decision Optimization experiments

5 Apr 2024

You can now use pivot tables to display both input and output data aggregated in the Visualization view in Decision Optimization experiments. For more information, see Visualization widgets in Decision Optimization experiments.

New watsonx.ai tutorial and video

04 Apr 2024

Try the new tutorial to see how to use watsonx.ai in an end-to-end use case from data preparation through prompt engineering.

The watsonx.ai API is available

14 Mar 2024

The watsonx.ai API is generally available. Use the watsonx.ai API to work with foundation models programmatically. For more information, see the API reference.

The API version is 2024-03-14.

You can continue to use the Python library that is available for working with foundation models from a notebook. For more information, see Python library.

New foundation models are available in Dallas, Frankfurt, and Tokyo

14 Mar 2024

The following foundation models are now available for inferencing from watsonx.ai:

• granite-20b-multilingual: A foundation model from the IBM Granite family that you can use for various generative tasks in English, German, Spanish, French, and Portuguese.

• codellama-34b-instruct-hf: A programmatic code generation model from Code Llama that is based on Llama 2 from Meta. You can use codellama-34b-instruct-hf to create prompts for generating code based on natural language inputs, and for completing and debugging code.

For more information, see Supported foundation models.

The Tuning Studio is available in Frankfurt

7 Mar 2024

The Tuning Studio is now available to users of paid plans in the Frankfurt region. Tuning Studio helps you to guide a foundation model to return useful output. You can tune both the flan-t5-xl-3b and llama-2-70b-chat foundation models when you use the Tuning Studio in Frankfurt.

For more information, see Tuning Studio.

Prompt-tune the llama-2-13b-chat foundation model in the Tokyo region

7 Mar 2024

The Tuning Studio now supports tuning the llama-2-13b-chat foundation model in the Tokyo region. First, engineer prompts for the larger llama-2-70b-chat model in the Prompt Lab to find effective prompt inputs for your use case. Then tune the smaller version of the Llama 2 model to generate comparable, if not better outputs with zero-shot prompts.

For more information, see Tuning Studio.

Lower price for Mixtral8x7b model

5 Mar 2024

The foundation model mixtral-8x7b-instruct-v01-q is reclassified from Class 2: $0.0018/Resource Unit to Class 1: $0.0006/Resource Unit, making it more cost effective to run inferencing tasks against this model. The reclassification applies to all regions where mixtral-8x7b-instruct-v01-q is available.

For more information, see Supported foundation models.

For pricing details, see Watson Machine Learning plans.

AI risk atlas is updated and enhanced

5 Mar 2024

You can now find the following new and enhanced content in the AI risk atlas:

• A new category of non-technical risks that spans governance, legal compliance, and societal impact risks
• New examples for risks
• Clearer definitions of risks

See AI risk atlas.

New use cases for watsonx

5 Mar 2024

The watsonx uses cases are available to help you see how you can use our products, services, and tools:

• watsonx.ai use case: This use case covers how you can transform your business processes with AI-driven solutions by integrating machine learning and generative AI into your operational framework.
• watsonx.governance use case: This use case covers how you can erive responsible, transparent, and explainable AI workflows with an integrated system for tracking, monitoring, and retraining AI models.

See watsonx use cases.

Chat mode is available in Prompt Lab

29 Feb 2024

Chat mode in Prompt Lab is a simple chat interface that makes it easier to experiment with foundation models. Chat mode augments the already available structured and freeform modes that are useful when building few- or many-shot prompts for tasks such as extraction, summarization, and classification. Use Chat mode to simulate question-answering or conversational interactions for chatbot and virtual assistant use cases.

For more information, see Prompt Lab.

A Japanese-language Granite model is available in the Tokyo region

29 Feb 2024

The granite-8b-japanese foundation model provided by IBM is available from watsonx.ai in the Tokyo region. The granite-8b-japanese foundation model is based on the IBM Granite Instruct model and is trained to understand and generate Japanese text.

You can use the granite-8b-japanese foundation model for general purpose tasks in the Japanese language, such as classification, extraction, question-answering, and for language translation between Japanese and English.

For more information, see Supported foundation models.

Lower price for Granite-13b models

21 Feb 2024

Granite-13b models are reclassified from Class 2: $0.0018/Resource Unit to Class 1: $0.0006/Resource Unit, making it more cost effective to run inferencing tasks against these models. The reclassification applies to the following models in all regions where they are available:

• granite-13b-chat-v2
• granite-13b-chat-v1
• granite-13b-instruct-v2
• granite-13b-instruct-v1

For more information on these models, see Supported foundation models.

For pricing details, see Watson Machine Learning plans.

New shortcut to start working on common tasks

15 Feb 2024

You can now start a common task in your project by clicking on a tile in the Start working section in the Overview tab. Use these shortcuts to start adding collaborators and data, and to experiment with and build models. Click View all to jump to a selection of tools.

New mixtral-8x7b-instruct-v01-q foundation model for general-purpose tasks

15 Feb 2024

The mixtral-8x7b-instruct-v01-q foundation model provided by Mistral AI and quantized by IBM is available from watsonx.ai. The mixtral-8x7b-instruct-v01-q foundation model is a quantized version of the Mixtral 8x7B Instruct foundation model from Mistral AI.

You can use this new model for general-purpose tasks, including classification, summarization, code generation, language translation, and more. For more information, see Supported foundation models.

The following models are deprecated and will be withdrawn soon. Revise any prompts that use these foundation models to use another foundation model, such as mixtral-8x7b-instruct-v01-q.

Inference requests that are submitted to these models by using the API continue to generate output, but include a warning message about the upcoming model withdrawal. When the withdrawal date is reached, API requests for inferencing the models will not generate output.

For more information about deprecation and withdrawal, see Foundation model lifecycle.

A modification to the granite-13b-chat-v2 foundation model is available

15 Feb 2024

The latest version of the granite-13b-chat-v2 is 2.1.0. The modification includes improvements that were gained by applying a novel AI alignment technique to the version 2.0.0 model. AI alignment involves using fine-tuning and reinforcement learning techniques to guide the model to return outputs that are as helpful, truthful, and transparent as possible. For more information, see the What is AI alignment? blog post from IBM Research.

New watsonx tutorial and video

15 Feb 2024

Try the new watsonx.governance tutorial to help you learn how to evaluate a machine learning model for fairness, accuracy, drift, and explainability with Watson OpenScale.

More task-oriented Decision Optimization documentation

9 Feb 2024

You can now more easily find the right information for creating and configuring Decision Optimization experiments. See Decision Optimization experiments and its subsections.

IBM Cloud Data Engine connection is deprecated

8 Feb 2022

The IBM Cloud Data Engine connection is deprecated and will be discontinued in a future release. See Deprecation of Data Engine for important dates and details.

New Spark 3.4 environment for running Data Refinery flow jobs

9 Feb 2024

When you select an environment for a Data Refinery flow job, you can now select Default Spark 3.4 & R 4.2, which includes enhancements from Spark.

The Default Spark 3.3 & R 4.2 environment is deprecated and will be removed in a future update.

Update your Data Refinery flow jobs to use the new Default Spark 3.4 & R 4.2 environment. For details, see Compute resource options for Data Refinery in projects.

Samples collection renamed to Resource hub

2 Feb 2024

The Samples collection is renamed to Resource hub to better reflect the content. The Resource hub contains foundation models and sample projects, data sets, and notebooks. See Resource hub.

IBM Cloud Databases for DataStax connection is discontinued

2 Feb 2024

The IBM Cloud Databases for DataStax connection has been removed from IBM watsonx.ai.

Dremio connection requires updates

2 Feb 2024

Previously the Dremio connection used a JDBC driver. Now the connection uses a driver based on Arrow Flight.

Action required Important: Update the connection properties. Different changes apply to a connection for a Dremio Software (on-prem) instance or a Dremio Cloud instance.

Prompt-tune the llama-2-13b-chat foundation model

1 Feb 2024

The Tuning Studio now supports tuning the llama-2-13b-chat foundation model. First, engineer prompts for the larger llama-2-70b-chat model in the Prompt Lab to find effective prompt inputs for your use case. Then tune the smaller version of the Llama 2 model to generate comparable, if not better outputs with zero-shot prompts. The llama-2-13b-model is available for prompt tuning in the Dallas region. For more information, see Tuning Studio.

AutoAI supports ordered data for all experiments

25 Jan 2024

You can now specify ordered data for all AutoAI experiments rather than just time series experiments. Specify if your training data is ordered sequentially, according to a row index. When input data is sequential, model performance is evaluated on newest records instead of a random sampling, and holdout data uses the last n records of the set rather than n random records. Sequential data is required for time series experiments but optional for classification and regression experiments.

Q&A with RAG accelerator

26 Jan 2024

You can now implement a question and answer solution that uses retrieval augmented generation by importing a sample project. The sample project contains notebooks and other assets that convert documents from HTML or PDF to plain text, import document segments into an Elasticsearch vector index, deploy a Python function that queries the vector index, retrieve top N results, run LLM inference to generate an answer to the question, and check the answer for hallucinations.

Try the Q&A with RAG accelerator.

Set to dark theme

25 Jan 2024

You can now set your watsonx user interface to dark theme. Click your avatar and select Profile and settings to open your account profile. Then, set the Dark theme switch to on. Dark theme is not supported in RStudio and Jupyter notebooks. For information on managing your profile, see Managing your settings.

IBM watsonx.ai is available in the Tokyo region

25 Jan 2024

Watsonx.ai is now generally available in the Tokyo data center and can be selected as the preferred region when signing-up. The Prompt Lab and foundation model inferencing are supported in the Tokyo region for these models:

• elyza-japanese-llama-2-7b-instruct
• flan-t5-xl-3b
• flan-t5-xxl-11b
• flan-ul2-20b
• granite-13b-chat-v2
• granite-13b-instruct-v2
• llama-2-70b-chat
• llama-2-13b-chat

Also available from the Tokyo region:

• Prompt tuning the flan-t5-xl-3b foundation model with the Tuning Studio
• Generating tabular data with the Synthetic Data Generator to use for training models

For more information on the supported models, see Supported foundation models available with watsonx.ai.

A Japanese-language Llama 2 model is available in the Tokyo region

25 Jan 2024

The elyza-japanese-llama-2-7b-instruct foundation model provided by ELYZA, Inc is available from watsonx.ai instances in the Tokyo data center. The elyza-japanese-llama-2-7b-instruct model is a version of the Llama 2 model from Meta that was trained to understand and generate Japanese text.

You can use this new model for general purpose tasks. It works well for Japanese-language classification and extraction and for translation between Japanese and English.

Support for IBM Runtime 22.2 deprecated in Watson Machine Learning

11 Jan 2024

IBM Runtime 22.2 is deprecated and will be removed on 11 April 2024. Beginning 7 March 2024, you cannot create notebooks or custom environments by using the 22.2 runtimes. Also, you cannot train new models with software specifications that are based on the 22.2 runtime. Action required Update your assets and deployments to use IBM Runtime 23.1 before 7 March 2024.

• To learn more about migrating an asset to a supported framework and software specification, see Managing outdated software specifications or frameworks.
• To learn more about the notebook environment, see Compute resource options for the notebook editor in projects.
• To learn more about changing your environment, see Changing the environment of a notebook.

IBM Granite v1 foundation models are deprecated

11 Jan 2024

The IBM Granite 13 billion-parameter v1 foundation models are deprecated and will be withdrawn on 11 April 2024. If you are using version 1 of the models, switch to using version 2 of the models instead.

Inference requests that are submitted to the version 1 models by using the API continue to generate output, but include a warning message about the upcoming model withdrawal. Starting on 11 April 2024, API requests for inferencing the models will not generate output.

For more information about IBM Granite foundation models, see Foundation models built by IBM. For more information about deprecation and withdrawal, see Foundation model lifecycle.

Create user API keys for jobs and other operations

15 Dec 2023

Certain runtime operations in IBM watsonx, such as jobs and model training, require an API key as a credential for secure authorization. With user API keys, you can now generate and rotate an API key directly in IBM watsonx as needed to help ensure your operations run smoothly. The API keys are managed in IBM Cloud, but you can conveniently create and rotate them in IBM watsonx.

The user API key is account-specific and is created from Profile and settings under your account profile.

For more information, see Managing the user API key.

New watsonx tutorials and videos

15 Dec 2023

Try the new watsonx.governance and watsonx.ai tutorials to help you learn how to tune a foundation model, and evaluate and track a prompt template.

Find more watsonx.governance and watsonx.ai videos in the Video library.

New login session expiration and sign out due to inactivity

15 Dec 2023

You are now signed out of IBM Cloud due to session expiration. Your session can expire due to login session expiration (24 hours by default) or inactivity (2 hours by default). You can change the default durations in the Access (IAM) settings in IBM Cloud. For more information, see Set the login session expiration.

IBM Cloud Databases for DataStax connector is deprecated

15 Dec 2023

The IBM Cloud Databases for DataStax connector is deprecated and will be discontinued in a future release.

The Tuning Studio is available

7 Dec 2023

The Tuning Studio helps you to guide a foundation model to return useful output. With the Tuning Studio, you can prompt tune the flan-t5-xl-3b foundation model to improve its performance on natural language processing tasks such as classification, summarization, and generation. Prompt tuning helps smaller, more computationally-efficient foundation models achieve results comparable to larger models in the same model family. By tuning and deploying a tuned version of a smaller model, you can reduce long-term inference costs. The Tuning Studio is available to users of paid plans in the Dallas region.

• For more information, see Tuning Studio.
• To get started, see Quick start: Tune a foundation model.
• To run a sample notebook, go to Tune a model to classify CFPB documents in watsonx.

New client properties in Db2 connections for workload management

8 Dec 2023

You can now specify properties in the following fields for monitoring purposes: Application name, Client accounting information, Client hostname, and Client user. These fields are optional and are available for the following connections:

• IBM Db2
• IBM Db2 for z/OS
• IBM Db2 Warehouse
• IBM Data Virtualization

Watsonx.governance is available!

1 Dec 2023

Watsonx.governance extends the governance capabilities of Watson OpenScale to evaluate foundation model assets as well as machine learning assets. For example, evaluate foundation model prompt templates for dimensions such as accuracy or to detect the presence of hateful and abusive speech. You can also define AI use cases to address business problems, then track prompt templates or model data in factsheets to support compliance and governance goals. Watsonx.governance plans and features are available only in the Dallas region.

• To view plan details, see watsonx.governance plans.
• For details on governance features, see watsonx.governance overview.
• To get started, see Provisioning and launching watsonx.governance.

Explore with the AI risk atlas

1 Dec 2023

You can now explore some of the risks of working with generative AI, foundation models, and machine learning models. Read about risks for privacy, fairness, explainability, value alignment, and other areas. See AI risk atlas.

New versions of the IBM Granite models are available

30 Nov 2023

The latest versions of the Granite models include these changes:

granite-13b-chat-v2: Tuned to be better at question-answering, summarization, and generative tasks. With sufficient context, generates responses with the following improvements over the previous version:

• Generates longer, higher-quality responses with a professional tone
• Supports chain-of-thought responses
• Recognizes mentions of people and can detect tone and sentiment better
• Handles white spaces in input more gracefully

Due to extensive changes, test and revise any prompts that were engineered for v1 before you switch to the latest version.

granite-13b-instruct-v2: Tuned specifically for classification, extraction, and summarization tasks. The latest version differs from the previous version in the following ways:

• Returns more coherent answers of varied lengths and with a diverse vocabulary
• Recognizes mentions of people and can summarize longer inputs
• Handles white spaces in input more gracefully

Engineered prompts that work well with v1 are likely to work well with v2 also, but be sure to test before you switch models.

The latest versions of the Granite models are categorized as Class 2 models.

Some foundation models are now available at lower cost

30 Nov 2023

Some popular foundation models were recategorized into lower-cost billing classes.

The following foundation models changed from Class 3 to Class 2:

• granite-13b-chat-v1
• granite-13b-instruct-v1
• llama-2-70b

The following foundation model changed from Class 2 to Class 1:

• llama-2-13b

For more information about the billing classes, see Watson Machine Learning plans.

A new sample notebook is available: Introduction to RAG with Discovery

30 Nov 2023

Use the Introduction to RAG with Discovery notebook to learn how to apply the retrieval-augmented generation pattern in IBM watsonx.ai with IBM Watson Discovery as the search component. For more information, see Introduction to RAG with Discovery.

Understand feature differences between watsonx as a service and software deployments

30 Nov 2023

You can now compare the features and implementation of IBM watsonx as a Service and watsonx on Cloud Pak for Data software, version 4.8. See Feature differences between watsonx deployments.

Change to how stop sequences are handled

30 Nov 2023

When a stop sequence, such as a newline character, is specified in the Prompt Lab, the model output text ends after the first occurrence of the stop sequence. The model output stops even if the occurrence comes at the beginning of the output. Previously, the stop sequence was ignored if it was specified at the start of the model output.

A smaller version of the Llama-2 Chat model is available

9 Nov 2023

You can now choose between using the 13b or 70b versions of the Llama-2 Chat model. Consider these factors when you make your choice:

• Cost
• Performance

The 13b version is a Class 2 model, which means it is cheaper to use than the 70b version. To compare benchmarks and other factors, such as carbon emissions for each model size, see the Model card.

Use prompt variables to build reusable prompts

Add flexibility to your prompts with prompt variables. Prompt variables function as placeholders in the static text of your prompt input that you can replace with text dynamically at inference time. You can save prompt variable names and default values in a prompt template asset to reuse yourself or share with collaborators in your project. For more information, see Building reusable prompts.

Announcing support for Python 3.10 and R4.2 frameworks and software specifications on runtime 23.1

9 Nov 2023

Action required You can now use IBM Runtime 23.1, which includes the latest data science frameworks based on Python 3.10 and R 4.2, to run Watson Studio Jupyter notebooks and R scripts, train models, and run Watson Machine Learning deployments. Update your assets and deployments to use IBM Runtime 23.1 frameworks and software specifications.

• For information on the IBM Runtime 23.1 release and the included environments for Python 3.10 and R 4.2, see Changing notebook environments.
• For details on deployment frameworks, see Managing frameworks and software specifications.

Use Apache Spark 3.4 to run notebooks and scripts

Spark 3.4 with Python 3.10 and R 4.2 is now supported as a runtime for notebooks and RStudio scripts in projects. For details on available notebook environments, see Compute resource options for the notebook editor in projects and Compute resource options for RStudio in projects.

Use a Satellite Connector to connect to an on-prem database

26 Oct 2023

Use the new Satellite Connector to connect to a database that is not accessible via the internet (for example, behind a firewall). Satellite Connector uses a lightweight Docker-based communication that creates secure and auditable communications from your on-prem environment back to IBM Cloud. For instructions, see Connecting to data behind a firewall.

Secure Gateway is deprecated

26 Oct 2023

IBM Cloud announced the deprecation of Secure Gateway. For information, see the Overview and timeline.

Action required If you currently have connections that are set up with Secure Gateway, plan to use an alternative communication method. In IBM watsonx, you can use the Satellite Connector as a replacement for Secure Gateway. See Connecting to data behind a firewall.

Maximum token sizes increased

16 Oct 2023

Limits that were previously applied to the maximum number of tokens allowed in the output from foundation models are removed from paid plans. You can use larger maximum token values during prompt engineering from both the Prompt Lab and the Python library. The exact number of tokens allowed differs by model. For more information about token limits for paid and Lite plans, see Supported foundation models.

New notebooks in Samples

12 Oct 2023

Two new notebooks are available that use a vector database from Elasticsearch in the retrieval phase of the retrieval-augmented generation pattern. The notebooks demonstrate how to find matches based on the semantic similarity between the indexed documents and the query text that is submitted from a user.

• Sample notebook: Use watsonx, Elasticsearch, and LangChain to answer questions (RAG)
• Sample notebook: Use watsonx, and Elasticsearch Python SDK to answer questions (RAG)

Intermediate solutions in Decision Optimization

12 Oct 2023

You can now choose to see a sample of intermediate solutions while a Decision Optimization experiment is running. This can be useful for debugging or to see how the solver is progressing. For large models that take longer to solve, with intermediate solutions you can now quickly and easily identify any potential problems with the solve, without having to wait for the solve to complete. You can configure the Intermediate solution delivery parameter in the Run configuration and select a frequency for these solutions. For more information, see Intermediate solutions and Run configuration parameters.

New Decision Optimization saved model dialog

When you save a model for deployment from the Decision Optimization user interface, you can now review the input and output schema, and more easily select the tables that you want to include. You can also add, modify or delete run configuration parameters, review the environment, and the model files used. All these items are displayed in the same Save as model for deployment dialog. For more information, see Deploying a Decision Optimization model by using the user interface.

Additional foundation models in Frankfurt

5 Oct 2023

All foundation models that are available in the Dallas data center are now also available in the Frankfurt data center. The watsonx.ai Prompt Lab and foundation model inferencing are now supported in the Frankfurt region for these models:

• granite-13b-chat-v1
• granite-13b-instruct-v1
• llama-2-70b-chat
• gpt-neox-20b
• mt0-xxl-13b
• starcoder-15.5b

For more information on these models, see Supported foundation models available with watsonx.ai.

For pricing details, see Watson Machine Learning plans.

Control the placement of a new column in the Concatenate operation (Data Refinery)

6 Oct 2023

You now have two options to specify the position of the new column that results from the Concatenate operation: As the right-most column in the data set or next to the original column.

Previously, the new column was placed at the beginning of the data set.

For information about Data Refinery operations, see GUI operations in Data Refinery.

IBM Granite foundation models for natural language generation

28 Sept 2023

The first two models from the Granite family of IBM foundation models are now available in the Dallas region:

• granite-13b-chat-v1: General use model that is optimized for dialog use cases
• granite-13b-instruct-v1: General use model that is optimized for question answering

Both models are 13B-parameter decoder models that can efficiently predict and generate language in English. They, like all models in the Granite family, are designed for business. Granite models are pretrained on multiple terabytes of data from both general-language sources, such as the public internet, and industry-specific data sources from the academic, scientific, legal, and financial fields.

Try them out today in the Prompt Lab or run a sample notebook that uses the granite-13b-instruct-v1 model for sentiment analysis.

Read the Building AI for business: IBM’s Granite foundation models blog post to learn more.

• For more information on these models, see Supported foundation models available with watsonx.ai.
• For a description of sample prompts, see Sample foundation model prompts for common tasks.
• For pricing details, see Watson Machine Learning plans.

Decision Optimization Java models

20 Sept 2023

Decision Optimization Java models can now be deployed in Watson Machine Learning. By using the Java worker API, you can create optimization models with OPL, CPLEX, and CP Optimizer Java APIs. You can now easily create your models locally, package them and deploy them on Watson Machine Learning by using the boilerplate that is provided in the public Java worker GitHub. For more information, see Deploying Java models for Decision Optimization.

New notebooks in Resource hub

21 Sept 2023

You can use the following new notebooks in Resource hub:

• Use watsonx and LangChain to answer questions using RAG
• Use watsonx and BigCode starcoder-15.5b to generate code

Prompt engineering and synthetic data quick start tutorials

14 Sept 2023

Try the new tutorials to help you learn how to:

• Prompt foundation models: There are usually multiple ways to prompt a foundation model for a successful result. In the Prompt Lab, you can experiment with prompting different foundation models, explore sample prompts, as well as save and share your best prompts. One way to improve the accuracy of generated output is to provide the needed facts as context in your prompt text using the retrieval-augmented generation pattern.
• Generate synthetic data: You can generate synthetic tabular data in watsonx.ai. The benefit to synthetic data is that you can procure the data on-demand, then customize to fit your use case, and produce it in large quantities.

Watsonx.ai Community

14 Sept 2023

You can now join the watsonx.ai Community for AI architects and builders to learn, share ideas, and connect with others.

Generate synthetic tabular data with Synthetic Data Generator

7 Sept 2023

Now available in the Dallas and Frankfurt regions, Synthetic Data Generator is a new graphical editor tool on watsonx.ai that you can use to generate tabular data to use for training models. Using visual flows and a statistical model, you can create synthetic data based on your existing data or a custom data schema. You can choose to mask your original data and export your synthetic data to a database or as a file.

To get started, see Synthetic data.

Llama-2 Foundation Model for natural language generation and chat

7 Sept 2023

The Llama-2 Foundation Model from Meta is now available in the Dallas region. Llama-2 Chat model is an auto-regressive language model that uses an optimized transformer architecture. The model is pretrained with publicly available online data, and then fine-tuned using reinforcement learning from human feedback. The model is intended for commercial and research use in English-language assistant-like chat scenarios.

• For more information on the Llama-2 model, see Supported foundation models available with watsonx.ai.
• For a description of sample prompts, see Sample foundation model prompts for common tasks.
• For pricing details for Llama-2, see Watson Machine Learning plans.

LangChain extension for the foundation models Python library

7 Sept 2023

You can now use the LangChain framework with foundation models in watsonx.ai with the new LangChain extension for the foundation models Python library.

This sample notebook demonstrates how to use the new extension: Sample notebook

Introductory sample for the retrieval-augmented generation pattern

7 Sept 2023

Retrieval-augmented generation is a simple, powerful technique for leveraging a knowledge base to get factually accurate output from foundation models.

See: Introduction to retrieval-augmented generation

Deprecation of comments in notebooks

31 Aug 2023

As of today it is not possible to add comments to a notebook from the notebook action bar. Any existing comments were removed.

StarCoder Foundation Model for code generation and code translation

31 Aug 2023

The StarCoder model from Hugging Face is now available in the Dallas region. Use StarCoder to create prompts for generating code or for transforming code from one programming language to another. One sample prompt demonstrates how to use StarCoder to generate Python code from a set of instruction. A second sample prompt demonstrates how to use StarCoder to transform code written in C++ to Python code.

• For more information on the StarCoder model, see Supported foundation models available with watsonx.ai.
• For a description of the sample prompts, see Sample foundation model prompts for common tasks.

IBM watsonx.ai is available in the Frankfurt region

31 Aug 2023

Watsonx.ai is now generally available in the Frankfurt data center and can be selected as the preferred region when signing-up. The Prompt Lab and foundation model inferencing are supported in the Frankfurt region for these models:

• mpt-7b-instruct2

• flan-t5-xxl-11b

• flan-ul2-20b

• For more information on the supported models, see Supported foundation models available with watsonx.ai.

Additional cache enhancements available for Watson Pipelines

21 August 2023

More options are available for customizing your pipeline flow settings. You can now exercise greater control over when the cache is used for pipeline runs. For details, see Managing default settings.

Plan name updates for Watson Machine Learning service

18 August 2023

Starting immediately, plan names are updated for the IBM Watson Machine Learning service, as follows:

• The v2 Standard plan is now the Essentials plan. The plan is designed to give your organization the resources required to get started working with foundation models and machine learning assets.

• The v2 Professional plan is now the Standard plan. This plan provides resources designed to support most organizations through asset creation to productive use.

Changes to the plan names do not change your terms of service. That is, if you are registered to use the v2 Standard plan, it will now be named Essentials, but all of the plan details will remain the same. Similarly, if you are registered to use the v2 Professional plan, there are no changes other than the plan name change to Standard.

For details on what is included with each plan, see Watson Machine Learning plans. For pricing information, find your plan on the Watson Machine Learning plan page in the IBM Cloud catalog.

Deprecation of comments in notebooks

7 August 2023

On 31 August 2023, you will no longer be able to add comments to a notebook from the notebook action bar. Any existing comments that were added that way will be removed.

Increased token limit for Lite plan

4 August 2023

If you are using the Lite plan to test foundation models, the token limit for prompt input and output is now increased from 25,000 to 50,000 per account per month. This gives you more flexibility for exploring foundation models and experimenting with prompts.

• For details on watsonx.ai plans, see Watson Machine Learning plans.
• For details on working with prompts, see Engineer prompts with the Prompt Lab.

Custom text analytics template (SPSS Modeler)

4 August 2023

For SPSS Modeler, you can now upload a custom text analytics template to a project. This provides you with more flexibility to capture and extract key concepts in a way that is unique to your context.

Foundation models Python library available

27 July 2023

You can now prompt foundation models in watsonx.ai programmatically using a Python library.

See: Foundation models Python library

Control AI guardrails

14 July 2023

You can now control whether AI guardrails are on or off in the Prompt Lab. AI guardrails remove potentially harmful text from both the input and output fields. Harmful text can include hate speech, abuse, and profanity. To prevent the removal of potentially harmful text, set the AI guardrails switch to off. See Hate speech, abuse, and profanity.

Microsoft Azure SQL Database connection supports Azure Active Directory authentication (Azure AD)

14 July 2023

You can now select Active Directory for the Microsoft Azure SQL Database connection. Active Directory authentication is an alternative to SQL Server authentication. With this enhancement, administrators can centrally manage user permissions to Azure. For more information, see Microsoft Azure SQL Database connection.

Welcome to IBM watsonx.ai!

7 July 2023

IBM watsonx.ai delivers all the tools that you need to work with machine learning and foundation models.

Get started:

• Learn about watsonx.ai
• Learn about foundation models
• Engineer prompts with the Prompt Lab
• Take quick start tutorials
• Watson Natural Language Processing

Try generative AI search and answer in this documentation

7 July 2023

You can see generative AI in action by trying the new generative AI search and answer option in the watsonx.ai documentation. The answers are generated by a large language model running in watsonx.ai and based on the documentation content. This feature is only available when you are viewing the documentation while logged in to watsonx.ai.

Enter a question in the documentation search field and click the Try generative AI search and answer icon (). The Generative AI search and answer pane opens and answers your question.