Foundation Models

Warning

Warning! Supported only for IBM watsonx.ai for IBM Cloud and IBM watsonx.ai software with IBM Cloud Pak® for Data 4.8 and later.

Modules

• Embeddings
  • Embeddings
    • Embeddings
      • Embeddings.close_persistent_connection()
      • Embeddings.embed_documents()
      • Embeddings.embed_query()
      • Embeddings.generate()
      • Embeddings.to_dict()
  • BaseEmbeddings
    • BaseEmbeddings
      • BaseEmbeddings.embed_documents()
      • BaseEmbeddings.embed_query()
      • BaseEmbeddings.from_dict()
      • BaseEmbeddings.to_dict()
  • Enums
    • EmbedTextParamsMetaNames
    • EmbeddingModels
    • EmbeddingTypes
• Models
  • Modules
    • ModelInference
      • ModelInference
        • ModelInference.aclose_persistent_connection()
        • ModelInference.agenerate()
        • ModelInference.chat()
        • ModelInference.chat_stream()
        • ModelInference.close_persistent_connection()
        • ModelInference.generate()
        • ModelInference.generate_text()
        • ModelInference.generate_text_stream()
        • ModelInference.get_details()
        • ModelInference.get_identifying_params()
        • ModelInference.set_api_client()
        • ModelInference.to_langchain()
        • ModelInference.tokenize()
      • Enums
        • TextModels
    • Model
      • Model
        • Model.chat()
        • Model.chat_stream()
        • Model.generate()
        • Model.generate_text()
        • Model.generate_text_stream()
        • Model.get_details()
        • Model.to_langchain()
        • Model.tokenize()
      • Enums
        • GenTextParamsMetaNames
        • GenTextReturnOptMetaNames
        • DecodingMethods
          • DecodingMethods.GREEDY
          • DecodingMethods.SAMPLE
        • ModelTypes
    • ModelInference for Deployments
      • Infer text with deployments
      • Creating ModelInference instance
      • Generate methods
• Tuning
  • Working with TuneExperiment and PromptTuner
    • Configure PromptTuner
    • Get configuration parameters
    • Run prompt tuning
    • Get run status, get run details
    • Get data connections
    • Summary
    • Plot learning curves
    • Get the model identifier
  • Working with TuneExperiment and FineTuner
    • Configure FineTuner
    • Get configuration parameters
    • Run fine tuning
    • Get run status, get run details
    • Get data connections
    • Summary
    • Plot learning curves
    • Get the model identifier
  • Tuned Model Inference
    • Working with deployments
    • Creating ModelInference instance
    • Importing data
    • Analyzing satisfaction
    • Generate methods
  • Tune Experiment
    • TuneExperiment
      • TuneExperiment
        • TuneExperiment.fine_tuner()
        • TuneExperiment.prompt_tuner()
        • TuneExperiment.runs()
    • Tune Runs
      • TuneRuns
        • TuneRuns.get_run_details()
        • TuneRuns.get_tuner()
        • TuneRuns.list()
    • Prompt Tuner
      • PromptTuner
        • PromptTuner.cancel_run()
        • PromptTuner.get_data_connections()
        • PromptTuner.get_model_id()
        • PromptTuner.get_params()
        • PromptTuner.get_run_details()
        • PromptTuner.get_run_status()
        • PromptTuner.plot_learning_curve()
        • PromptTuner.run()
        • PromptTuner.summary()
    • Enums
      • PromptTuningTypes
        • PromptTuningTypes.PT
      • PromptTuningInitMethods
        • PromptTuningInitMethods.RANDOM
        • PromptTuningInitMethods.TEXT
      • TuneExperimentTasks
        • TuneExperimentTasks.CLASSIFICATION
        • TuneExperimentTasks.CODE_GENERATION_AND_CONVERSION
        • TuneExperimentTasks.EXTRACTION
        • TuneExperimentTasks.GENERATION
        • TuneExperimentTasks.QUESTION_ANSWERING
        • TuneExperimentTasks.RETRIEVAL_AUGMENTED_GENERATION
        • TuneExperimentTasks.SUMMARIZATION
      • PromptTunableModels
• Prompt Template Manager
  • PromptTemplateManager
    • PromptTemplateManager.delete_prompt()
    • PromptTemplateManager.get_lock()
    • PromptTemplateManager.list()
    • PromptTemplateManager.load_prompt()
    • PromptTemplateManager.lock()
    • PromptTemplateManager.store_prompt()
    • PromptTemplateManager.unlock()
    • PromptTemplateManager.update_prompt()
  • PromptTemplate
  • FreeformPromptTemplate
  • DetachedPromptTemplate
  • Enums
    • PromptTemplateFormats
      • PromptTemplateFormats.LANGCHAIN
      • PromptTemplateFormats.PROMPTTEMPLATE
      • PromptTemplateFormats.STRING
• Extensions
  • LangChain
    • Installation and Setup
    • Chat Model
    • LLMs
    • Embedding Models
    • API reference
  • LlamaIndex
    • Installation and Setup
    • LLMs
    • Embedding Models
    • API reference
  • RAG
    • Chunkers
      • LangChainChunker
        • LangChainChunker
          • LangChainChunker.from_dict()
          • LangChainChunker.split_documents()
          • LangChainChunker.supported_methods
          • LangChainChunker.to_dict()
      • BaseChunker
        • BaseChunker
          • BaseChunker.from_dict()
          • BaseChunker.split_documents()
          • BaseChunker.to_dict()
    • Retrievers
      • Retriever
        • Retriever.from_vector_store()
        • Retriever.retrieve()
        • Retriever.to_dict()
      • RetrievalMethod
        • RetrievalMethod.SIMPLE
        • RetrievalMethod.WINDOW
      • BaseRetriever
        • BaseRetriever.from_vector_store()
        • BaseRetriever.retrieve()
        • BaseRetriever.to_dict()
    • Vector Stores
      • VectorStore
        • VectorStore
          • VectorStore.add_documents()
          • VectorStore.add_documents_async()
          • VectorStore.as_langchain_retriever()
          • VectorStore.clear()
          • VectorStore.count()
          • VectorStore.delete()
          • VectorStore.from_dict()
          • VectorStore.get_client()
          • VectorStore.search()
          • VectorStore.set_embeddings()
          • VectorStore.to_dict()
          • VectorStore.window_search()
      • BaseVectorStore
        • BaseVectorStore
          • BaseVectorStore.add_documents()
          • BaseVectorStore.add_documents_async()
          • BaseVectorStore.as_langchain_retriever()
          • BaseVectorStore.clear()
          • BaseVectorStore.count()
          • BaseVectorStore.delete()
          • BaseVectorStore.get_client()
          • BaseVectorStore.search()
          • BaseVectorStore.set_embeddings()
          • BaseVectorStore.window_search()
      • VectorStoreConnector
        • VectorStoreConnector
          • VectorStoreConnector.get_chroma()
          • VectorStoreConnector.get_elasticsearch()
          • VectorStoreConnector.get_from_type()
          • VectorStoreConnector.get_langchain_adapter()
          • VectorStoreConnector.get_milvus()
          • VectorStoreConnector.get_type_from_langchain_vector_store()
      • VectorStoreDataSourceType
        • VectorStoreDataSourceType
          • VectorStoreDataSourceType.CHROMA
          • VectorStoreDataSourceType.ELASTICSEARCH
          • VectorStoreDataSourceType.MILVUS
          • VectorStoreDataSourceType.UNDEFINED
      • LangChainVectorStoreAdapter
        • LangChainVectorStoreAdapter
          • LangChainVectorStoreAdapter.add_documents()
          • LangChainVectorStoreAdapter.add_documents_async()
          • LangChainVectorStoreAdapter.as_langchain_retriever()
          • LangChainVectorStoreAdapter.clear()
          • LangChainVectorStoreAdapter.count()
          • LangChainVectorStoreAdapter.delete()
          • LangChainVectorStoreAdapter.get_client()
          • LangChainVectorStoreAdapter.search()
          • LangChainVectorStoreAdapter.set_embeddings()
          • LangChainVectorStoreAdapter.window_search()
• Helpers
  • FoundationModelsManager
    • FoundationModelsManager.get_chat_model_specs()
    • FoundationModelsManager.get_custom_model_specs()
    • FoundationModelsManager.get_embeddings_model_specs()
    • FoundationModelsManager.get_model_lifecycle()
    • FoundationModelsManager.get_model_specs()
    • FoundationModelsManager.get_model_specs_with_fine_tuning_support()
    • FoundationModelsManager.get_model_specs_with_prompt_tuning_support()
    • FoundationModelsManager.get_rerank_model_specs()
  • get_model_specs()
  • get_model_lifecycle()
  • get_model_specs_with_prompt_tuning_support()
  • get_supported_tasks()
• Custom models
  • IBM watsonx.ai for IBM Cloud
    • Initialize an APIClient object
    • Add Task Credentials
    • Store the model in the service repository
    • Store the model
    • Deploy the custom foundation model
    • Work with deployments
  • IBM watsonx.ai software with IBM Cloud Pak® for Data
    • Initialize the APIClient object
    • List model specifications
    • Store the model in the service repository
    • Store the model
    • Define the hardware specification
    • Deploy the custom foundation model
    • Work with deployments
• Text Extractions
  • TextExtractions
    • TextExtractions.delete_job()
    • TextExtractions.get_id()
    • TextExtractions.get_job_details()
    • TextExtractions.get_results_reference()
    • TextExtractions.list_jobs()
    • TextExtractions.run_job()
  • Enums
    • TextExtractionsMetaNames
• Parameter Scheme
  • BaseSchema
    • BaseSchema.get_sample_params()
    • BaseSchema.show()
  • Chat Parameters
    • TextChatParameters
      • TextChatParameters.frequency_penalty
      • TextChatParameters.logprobs
      • TextChatParameters.max_tokens
      • TextChatParameters.n
      • TextChatParameters.presence_penalty
      • TextChatParameters.response_format
      • TextChatParameters.temperature
      • TextChatParameters.time_limit
      • TextChatParameters.top_logprobs
      • TextChatParameters.top_p
    • TextChatResponseFormat
      • TextChatResponseFormat.type
    • TextChatResponseFormatType
      • TextChatResponseFormatType.JSON_OBJECT
  • Generate Parameters
    • TextGenParameters
      • TextGenParameters.decoding_method
      • TextGenParameters.include_stop_sequence
      • TextGenParameters.length_penalty
      • TextGenParameters.max_new_tokens
      • TextGenParameters.min_new_tokens
      • TextGenParameters.prompt_variables
      • TextGenParameters.random_seed
      • TextGenParameters.repetition_penalty
      • TextGenParameters.return_options
      • TextGenParameters.stop_sequences
      • TextGenParameters.temperature
      • TextGenParameters.time_limit
      • TextGenParameters.top_k
      • TextGenParameters.top_p
      • TextGenParameters.truncate_input_tokens
    • ReturnOptionProperties
      • ReturnOptionProperties.generated_tokens
      • ReturnOptionProperties.input_text
      • ReturnOptionProperties.input_tokens
      • ReturnOptionProperties.token_logprobs
      • ReturnOptionProperties.token_ranks
      • ReturnOptionProperties.top_n_tokens
    • TextGenLengthPenalty
      • TextGenLengthPenalty.decay_factor
      • TextGenLengthPenalty.start_index
    • TextGenDecodingMethod
      • TextGenDecodingMethod.GREEDY
      • TextGenDecodingMethod.SAMPLE
  • Rerank Parameters
    • RerankParameters
      • RerankParameters.return_options
      • RerankParameters.truncate_input_tokens
    • RerankReturnOptions
      • RerankReturnOptions.inputs
      • RerankReturnOptions.query
      • RerankReturnOptions.top_n
• Rerank
  • Rerank
    • Rerank.generate()