deepset-mcp 0.0.3rc1__py3-none-any.whl → 0.0.4__py3-none-any.whl

deepset_mcp/benchmark/tasks/pipelines/rag_documents_wrong_format.yml

@@ -1,193 +0,0 @@
-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:
-          hosts:
-          index: 'standard-index'
-          max_chunk_bytes: 104857600
-          embedding_dim: 768
-          return_embedding: false
-          method:
-          mappings:
-          settings:
-          create_index: true
-          http_auth:
-          use_ssl:
-          verify_certs:
-          timeout:
-      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:
-          hosts:
-          index: 'standard-index'
-          max_chunk_bytes: 104857600
-          embedding_dim: 768
-          return_embedding: false
-          method:
-          mappings:
-          settings:
-          create_index: true
-          http_auth:
-          use_ssl:
-          verify_certs:
-          timeout:
-      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:
-        {%- if documents|length > 0 %}
-        {%- for document in documents %}
-        Document [{{ loop.index }}] :
-        Name of Source File: {{ document.meta.file_name }}
-        {{ document.content }}
-        {% endfor -%}
-        {%- else %}
-        No relevant documents found.
-        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
-        {% endif %}
-
-        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
-
-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: "qa_prompt_builder.prompt"  # 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: {}

deepset_mcp/benchmark/tasks/pipelines/rag_no_query_input.yml

@@ -1,191 +0,0 @@
-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:
-          hosts:
-          index: 'standard-index'
-          max_chunk_bytes: 104857600
-          embedding_dim: 768
-          return_embedding: false
-          method:
-          mappings:
-          settings:
-          create_index: true
-          http_auth:
-          use_ssl:
-          verify_certs:
-          timeout:
-      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:
-          hosts:
-          index: 'standard-index'
-          max_chunk_bytes: 104857600
-          embedding_dim: 768
-          return_embedding: false
-          method:
-          mappings:
-          settings:
-          create_index: true
-          http_auth:
-          use_ssl:
-          verify_certs:
-          timeout:
-      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:
-        {%- if documents|length > 0 %}
-        {%- for document in documents %}
-        Document [{{ loop.index }}] :
-        Name of Source File: {{ document.meta.file_name }}
-        {{ document.content }}
-        {% endfor -%}
-        {%- else %}
-        No relevant documents found.
-        Respond with "Sorry, no matching documents were found, please adjust the filters or try a different question."
-        {% endif %}
-
-        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
-
-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
-
-  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: {}

deepset_mcp/benchmark/tasks/pipelines/standard_index.yml

@@ -1,167 +0,0 @@
-# If you need help with the YAML format, have a look at https://docs.cloud.deepset.ai/v2.0/docs/create-a-pipeline#create-a-pipeline-using-pipeline-editor.
-# This section defines components that you want to use in your pipelines. Each component must have a name and a type. You can also set the component's parameters here.
-# The name is up to you, you can give your component a friendly name. You then use components' names when specifying the connections in the pipeline.
-# Type is the class path of the component. You can check the type on the component's documentation page.
-components:
-  file_classifier:
-    type: haystack.components.routers.file_type_router.FileTypeRouter
-    init_parameters:
-      mime_types:
-      - text/plain
-      - application/pdf
-      - text/markdown
-      - text/html
-      - application/vnd.openxmlformats-officedocument.wordprocessingml.document
-      - application/vnd.openxmlformats-officedocument.presentationml.presentation
-      - application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
-      - text/csv
-
-  text_converter:
-    type: haystack.components.converters.txt.TextFileToDocument
-    init_parameters:
-      encoding: utf-8
-
-  pdf_converter:
-    type: haystack.components.converters.pdfminer.PDFMinerToDocument
-    init_parameters:
-      line_overlap: 0.5
-      char_margin: 2
-      line_margin: 0.5
-      word_margin: 0.1
-      boxes_flow: 0.5
-      detect_vertical: true
-      all_texts: false
-      store_full_path: false
-
-  markdown_converter:
-    type: haystack.components.converters.txt.TextFileToDocument
-    init_parameters:
-      encoding: utf-8
-
-  html_converter:
-    type: haystack.components.converters.html.HTMLToDocument
-    init_parameters:
-      # A dictionary of keyword arguments to customize how you want to extract content from your HTML files.
-      # For the full list of available arguments, see
-      # the [Trafilatura documentation](https://trafilatura.readthedocs.io/en/latest/corefunctions.html#extract).
-      extraction_kwargs:
-        output_format: markdown # Extract text from HTML. You can also also choose "txt"
-        target_language:       # You can define a language (using the ISO 639-1 format) to discard documents that don't match that language.
-        include_tables: true  # If true, includes tables in the output
-        include_links: true  # If true, keeps links along with their targets
-
-  docx_converter:
-    type: haystack.components.converters.docx.DOCXToDocument
-    init_parameters:
-      link_format: markdown
-
-  pptx_converter:
-    type: haystack.components.converters.pptx.PPTXToDocument
-    init_parameters: {}
-
-  xlsx_converter:
-    type: haystack.components.converters.xlsx.XLSXToDocument
-    init_parameters: {}
-
-  csv_converter:
-    type: haystack.components.converters.csv.CSVToDocument
-    init_parameters:
-      encoding: utf-8
-
-  joiner:
-    type: haystack.components.joiners.document_joiner.DocumentJoiner
-    init_parameters:
-      join_mode: concatenate
-      sort_by_score: false
-
-  joiner_xlsx:  # merge split documents with non-split xlsx documents
-    type: haystack.components.joiners.document_joiner.DocumentJoiner
-    init_parameters:
-      join_mode: concatenate
-      sort_by_score: false
-
-  splitter:
-    type: haystack.components.preprocessors.document_splitter.DocumentSplitter
-    init_parameters:
-      split_by: word
-      split_length: 250
-      split_overlap: 30
-      respect_sentence_boundary: true
-      language: en
-
-  document_embedder:
-    type: haystack.components.embedders.sentence_transformers_document_embedder.SentenceTransformersDocumentEmbedder
-    init_parameters:
-      normalize_embeddings: true
-      model: intfloat/e5-base-v2
-
-  writer:
-    type: haystack.components.writers.document_writer.DocumentWriter
-    init_parameters:
-      document_store:
-        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
-        init_parameters:
-          hosts:
-          index: ''
-          max_chunk_bytes: 104857600
-          embedding_dim: 768
-          return_embedding: false
-          method:
-          mappings:
-          settings:
-          create_index: true
-          http_auth:
-          use_ssl:
-          verify_certs:
-          timeout:
-      policy: OVERWRITE
-
-connections:  # Defines how the components are connected
-- sender: file_classifier.text/plain
-  receiver: text_converter.sources
-- sender: file_classifier.application/pdf
-  receiver: pdf_converter.sources
-- sender: file_classifier.text/markdown
-  receiver: markdown_converter.sources
-- sender: file_classifier.text/html
-  receiver: html_converter.sources
-- sender: file_classifier.application/vnd.openxmlformats-officedocument.wordprocessingml.document
-  receiver: docx_converter.sources
-- sender: file_classifier.application/vnd.openxmlformats-officedocument.presentationml.presentation
-  receiver: pptx_converter.sources
-- sender: file_classifier.application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
-  receiver: xlsx_converter.sources
-- sender: file_classifier.text/csv
-  receiver: csv_converter.sources
-- sender: text_converter.documents
-  receiver: joiner.documents
-- sender: pdf_converter.documents
-  receiver: joiner.documents
-- sender: markdown_converter.documents
-  receiver: joiner.documents
-- sender: html_converter.documents
-  receiver: joiner.documents
-- sender: docx_converter.documents
-  receiver: joiner.documents
-- sender: pptx_converter.documents
-  receiver: joiner.documents
-- sender: joiner.documents
-  receiver: splitter.documents
-- sender: splitter.documents
-  receiver: joiner_xlsx.documents
-- sender: xlsx_converter.documents
-  receiver: joiner_xlsx.documents
-- sender: csv_converter.documents
-  receiver: joiner_xlsx.documents
-- sender: joiner_xlsx.documents
-  receiver: document_embedder.documents
-- sender: document_embedder.documents
-  receiver: writer.documents
-
-inputs:  # Define the inputs for your pipeline
-  files:                            # This component will receive the files to index as input
-  - file_classifier.sources
-
-max_runs_per_component: 100
-
-metadata: {}