Overview

deepset Cloud integrates with the W&B Weave, a powerful tool for tracking and evaluating LLM-based applications. After connecting deepset Cloud to W&B with your W&B API key, you can add the WeaveConnector component to your pipelines. This component collects your pipeline's traces and sends them to W&B for analysis.

Prerequisites

You need an API key from Weights & Biases. For details, see the the W&B Weave documentation.

Use W&B Weave

First, connect deepset Cloud to Weights & Biases through the Connections page:

Click your initials in the top right corner and select Connections.
Click Connect next to the provider.
Enter your API key and submit it.

Then, add the WeaveConnector component to your pipeline, but do not connect it to any other component. Simply set the pipeline_name parameter in WeaveConnectorto your pipeline's name—that's all you need to do. The value you provide for pipeline_name will be used as the name of your Weave tracing project in W&B. Using a pipeline name helps you easily identify which pipeline the traces belong to, especially when managing multiple projects.

Usage Examples

This is an example of a RAG pipeline with WeaveConnector. The component is in the pipeline, but it's not connected to any other component. That's enough to send the pipeline traces to Weights & Biases:

components:
  chat_summary_prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: |-
        You are part of a chatbot.
        You receive a question (Current Question) and a chat history.
        Use the context from the chat history and reformulate the question so that it is suitable for retrieval augmented generation.
        If X is followed by Y, only ask for Y and do not repeat X again.
        If the question does not require any context from the chat history, output it unedited.
        Don't make questions too long, but short and precise.
        Stay as close as possible to the current question.
        Only output the new question, nothing else!

        {{ question }}

        New question:

  chat_summary_llm:
    type: haystack.components.generators.openai.OpenAIGenerator
    init_parameters:
      api_key: {"type": "env_var", "env_vars": ["OPENAI_API_KEY"], "strict": false}
      model: "gpt-4o"
      generation_kwargs:
        max_tokens: 650
        temperature: 0
        seed: 0

  replies_to_query:
    type: haystack.components.converters.output_adapter.OutputAdapter
    init_parameters:
      template: "{{ replies[0] }}"
      output_type: str

  bm25_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.bm25_retriever.OpenSearchBM25Retriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
      top_k: 20 # The number of results to return

  query_embedder:
    type: deepset_cloud_custom_nodes.embedders.nvidia.text_embedder.DeepsetNvidiaTextEmbedder
    init_parameters:
      normalize_embeddings: true
      model: "intfloat/e5-base-v2"


  embedding_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
        init_parameters:
          embedding_dim: 768
      top_k: 20 # The number of results to return

  document_joiner:
    type: haystack.components.joiners.document_joiner.DocumentJoiner
    init_parameters:
      join_mode: concatenate

  ranker:
    type: deepset_cloud_custom_nodes.rankers.nvidia.ranker.DeepsetNvidiaRanker
    init_parameters:
      model: intfloat/simlm-msmarco-reranker
      top_k: 8


  qa_prompt_builder:
    type: haystack.components.builders.prompt_builder.PromptBuilder
    init_parameters:
      template: |-
        You are a technical expert.
        You answer questions truthfully based on provided documents.
        Ignore typing errors in the question.
        For each document check whether it is related to the question.
        Only use documents that are related to the question to answer it.
        Ignore documents that are not related to the question.
        If the answer exists in several documents, summarize them.
        Only answer based on the documents provided. Don't make things up.
        Just output the structured, informative and precise answer and nothing else.
        If the documents can't answer the question, say so.
        Always use references in the form [NUMBER OF DOCUMENT] when using information from a document, e.g. [3] for Document[3].
        Never name the documents, only enter a number in square brackets as a reference.
        The reference must only refer to the number that comes in square brackets after the document.
        Otherwise, do not use brackets in your answer and reference ONLY the number of the document without mentioning the word document.
        These are the documents:
        {% for document in documents %}
        Document[{{ loop.index }}]:
        {{ document.content }}
        {% endfor %}

        Question: {{ question }}
        Answer:

  qa_llm:
    type: haystack.components.generators.openai.OpenAIGenerator
    init_parameters:
      api_key: {"type": "env_var", "env_vars": ["OPENAI_API_KEY"], "strict": false}
      model: "gpt-4o"
      generation_kwargs:
        max_tokens: 650
        temperature: 0
        seed: 0

  answer_builder:
    type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:
      reference_pattern: acm

  WeaveConnector:
    type: deepset_cloud_custom_nodes.connectors.weave_connector.WeaveConnector
    init_parameters:
      pipeline_name: RAG-Chat

connections:  # Defines how the components are connected
- sender: chat_summary_prompt_builder.prompt
  receiver: chat_summary_llm.prompt
- sender: chat_summary_llm.replies
  receiver: replies_to_query.replies
- sender: replies_to_query.output
  receiver: bm25_retriever.query
- sender: replies_to_query.output
  receiver: query_embedder.text
- sender: replies_to_query.output
  receiver: ranker.query
- sender: replies_to_query.output
  receiver: qa_prompt_builder.question
- sender: replies_to_query.output
  receiver: answer_builder.query
- 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: ranker.documents
  receiver: qa_prompt_builder.documents
- sender: ranker.documents
  receiver: answer_builder.documents
- sender: qa_prompt_builder.prompt
  receiver: qa_llm.prompt
- sender: qa_prompt_builder.prompt
  receiver: answer_builder.prompt
- sender: qa_llm.replies
  receiver: answer_builder.replies

inputs:  # Define the inputs for your pipeline
  query:  # These components will receive the query as input
  - "chat_summary_prompt_builder.question"
  filters:  # These components will receive a potential query filter as input
  - "bm25_retriever.filters"
  - "embedding_retriever.filters"

outputs:  # Defines the output of your pipeline
  documents: "ranker.documents"  # The output of the pipeline is the retrieved documents
  answers: "answer_builder.answers"  # The output of the pipeline is the generated answers

max_runs_per_component: 100

metadata: {}

In Pipeline Builder, you simply drag the component from the Connectors group, drop it on the canvas, and pass the name of the pipeline you want to trace in the pipeline_name parameter:

WeaveConnector is not connected to any component.