DeepsetOpenAIVisionGenerator

Generate text using text and image capabilities of OpenAI's LLMs.

Deprecation Notice

This component is deprecated. It will continue to work in your existing pipelines for now. You can replace it with the OpenAIChatGenerator component.

DeepsetOpenAIVisionGenerator works with the GPT families of models hosted on Azure. These models can understand images, making it possible to describe them, analyze details, and answer questions based on images. For details and limitations, check OpenAI's Vision documentation.

Key Features

• Accepts both text prompts and images (as Base64Image objects) for multimodal generation.
• Works with GPT-4 and other vision-capable OpenAI models.
• Supports streaming responses token by token.
• Customizable generation via generation_kwargs, including max_tokens, temperature, top_p, and more.

Configuration

1. Drag the DeepsetOpenAIVisionGenerator component onto the canvas from the Component Library.
2. Click on the component to open the configuration panel.
3. On the General tab:
   1. Enter the model name in the Model field (for example, gpt-4o).
   2. Make sure Haystack Platform is connected to OpenAI. You need an OpenAI API key. For help, see Add Integrations.
4. Go to the Advanced tab to configure system_prompt, api_base_url, organization, streaming_callback, generation_kwargs, timeout, and max_retries.

Connections

DeepsetOpenAIVisionGenerator receives a text prompt from PromptBuilder through its prompt input and a list of Base64Image objects (typically from DeepsetPDFDocumentToBase64Image) through its images input. It outputs generated text as a list of strings through its replies output, which you connect to DeepsetAnswerBuilder.

Here's an example of the pipeline in Pipeline Builder:

Usage Examples

Basic Configuration

  DeepsetOpenAIVisionGenerator:
    type: deepset_cloud_custom_nodes.generators.openai_vision.DeepsetOpenAIVisionGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - OPENAI_API_KEY
        strict: false
      model: gpt-4o

Using the Component in a Pipeline

Here's an example of a query pipeline with DeepsetOpenAIVisionGenerator. It's preceded by DeepsetFileDownloader ("image_downloader"), which downloads the documents returned by previous components, such as a Ranker or DocumentJoiner. It then sends the downloaded files to DeepsetPDFDocumentToBase64Image ("pdf_to_image"), which converts them into Base64Image objects that DeepsetOpenAIVisionGenerator can take in. The Generator also receives the prompt from the PromptBuilder. It then sends the generated replies to DeepsetAnswerBuilder.

components:
  bm25_retriever:
    type: haystack_integrations.components.retrievers.opensearch.bm25_retriever.OpenSearchBM25Retriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          use_ssl: true
          verify_certs: false
          hosts:
          - ${OPENSEARCH_HOST}
          http_auth:
          - ${OPENSEARCH_USER}
          - ${OPENSEARCH_PASSWORD}
          embedding_dim: 1024
          similarity: cosine
          index: ''
          max_chunk_bytes: 104857600
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          timeout:
      top_k: 20
  query_embedder:
    type: haystack.components.embedders.sentence_transformers_text_embedder.SentenceTransformersTextEmbedder
    init_parameters:
      model: BAAI/bge-m3
      tokenizer_kwargs:
        model_max_length: 1024
  embedding_retriever:
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          use_ssl: true
          verify_certs: false
          hosts:
          - ${OPENSEARCH_HOST}
          http_auth:
          - ${OPENSEARCH_USER}
          - ${OPENSEARCH_PASSWORD}
          embedding_dim: 1024
          similarity: cosine
          index: ''
          max_chunk_bytes: 104857600
          return_embedding: false
          method:
          mappings:
          settings:
          create_index: true
          timeout:
      top_k: 20
  document_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate
  ranker:
    type: haystack.components.rankers.transformers_similarity.TransformersSimilarityRanker
    init_parameters:
      model: BAAI/bge-reranker-v2-m3
      top_k: 8
      model_kwargs:
        torch_dtype: torch.float16
      tokenizer_kwargs:
        model_max_length: 1024
      meta_fields_to_embed:
      - file_name
  image_downloader:
    type: deepset_cloud_custom_nodes.augmenters.deepset_file_downloader.DeepsetFileDownloader
    init_parameters:
      file_extensions:
      - .pdf
  pdf_to_image:
    type: deepset_cloud_custom_nodes.converters.pdf_to_image.DeepsetPDFDocumentToBase64Image
    init_parameters:
      detail: high
  prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: |-
        Answer the questions briefly and precisely using the images and text passages provided.
        Only use images and text passages that are related to the question to answer it.
        In your answer, only refer to images and text passages that are relevant in answering the query.
        Only use references in the form [NUMBER OF IMAGE] if you are using information from an image.
        Or [NUMBER OF DOCUMENT] if you are using information from a document.

        These are the documents:
        {% for document in documents %}
        Document[ {{ loop.index }} ]:
        File Name: {{ document.meta['file_name'] }}
        Text only version of image number {{ loop.index }} that is also provided.
        {{ document.content }}
        {% endfor %}
        Question: {{ question }}
        Answer: 
  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm
  TopKDocuments:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      top_k: 8
  DeepsetOpenAIVisionGenerator:
    type: deepset_cloud_custom_nodes.generators.openai_vision.DeepsetOpenAIVisionGenerator
    init_parameters:
      api_key:
        type: env_var
        env_vars:
        - OPENAI_API_KEY
        strict: false
      model: gpt-4o
      streaming_callback:
      api_base_url:
      organization:
      system_prompt:
      generation_kwargs:
      timeout:
      max_retries:

connections:
- sender: bm25_retriever.documents
  receiver: document_joiner.documents
- sender: query_embedder.embedding
  receiver: embedding_retriever.query_embedding
- sender: embedding_retriever.documents
  receiver: document_joiner.documents
- sender: document_joiner.documents
  receiver: ranker.documents
- sender: image_downloader.documents
  receiver: pdf_to_image.documents
- sender: prompt_builder.prompt
  receiver: answer_builder.prompt
- sender: ranker.documents
  receiver: prompt_builder.documents
- sender: ranker.documents
  receiver: TopKDocuments.documents
- sender: TopKDocuments.documents
  receiver: image_downloader.documents
- sender: ranker.documents
  receiver: answer_builder.documents
- sender: DeepsetOpenAIVisionGenerator.replies
  receiver: answer_builder.replies
- sender: prompt_builder.prompt
  receiver: DeepsetOpenAIVisionGenerator.prompt
- sender: pdf_to_image.base64_images
  receiver: DeepsetOpenAIVisionGenerator.images

metadata: {}

inputs:
  query:
  - bm25_retriever.query
  - query_embedder.text
  - ranker.query
  - prompt_builder.question
  - answer_builder.query
  filters:
  - embedding_retriever.filters
  - bm25_retriever.filters

outputs:
  answers: answer_builder.answers
  documents: ranker.documents

max_runs_per_component: 100

Parameters

Inputs

Parameter	Type	Description
prompt	str	The prompt with instructions for the model.
images	List[Base64Image]	A list of Base64Images that represent the image content of the message. The base64 encoded images are passed to OpenAI for text generation.
generation_kwargs	Optional[Dict[str, Any]]	Additional keyword arguments for text generation. These parameters potentially override the parameters in pipeline configuration.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	A callback function called when a new token is received from the stream. For more information, see Enable Streaming.

Outputs

Parameter	Type	Description
replies	List[str]	A list of strings containing the generated responses.
meta	List[Dict[str, Any]]	A list of dictionaries containing the metadata for each response.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
api_key	Secret	Secret.from_env_var('OPENAI_API_KEY')	The OpenAI API key.
model	str	gpt-4o	The name of the model to use.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	A callback function called when a new token is received from the stream. For details, see Enable Streaming.
api_base_url	Optional[str]	None	An optional base URL.
organization	Optional[str]	None	The Organization ID. See production best practices.
system_prompt	Optional[str]	None	The system prompt to use for text generation. If not provided, the system prompt is omitted, and the default system prompt of the model is used.
generation_kwargs	Optional[Dict[str, Any]]	None	Other parameters to use for the model. These parameters are all sent directly to the OpenAI endpoint. See OpenAI documentation for more details.
timeout	Optional[float]	None	Timeout for OpenAI Client calls. If not set, it is inferred from the OPENAI_TIMEOUT environment variable or set to 30.
max_retries	Optional[int]	None	Maximum retries to establish contact with OpenAI if it returns an internal error. If not set, it is inferred from the OPENAI_MAX_RETRIES environment variable or set to 5.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
prompt	str		The prompt with instructions for the model.
images	List[Base64Image]		A list of Base64Images that represent the image content of the message.
generation_kwargs	Optional[Dict[str, Any]]	None	Additional keyword arguments for text generation. For more details, refer to the OpenAI documentation.
streaming_callback	Optional[Callable[[StreamingChunk], None]]	None	A callback function called when a new token is received from the stream. For more information, see Enable Streaming.

Related Information

• Add Integrations