deepset-mcp 0.0.2rc1__py3-none-any.whl

deepset_mcp/benchmark/tasks/pipelines/chat_agent_jinja_str.yml

@@ -0,0 +1,141 @@
+# 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:
+  adapter:
+    init_parameters:
+      custom_filters: {}
+      output_type: List[str]
+      template: ' {{ [(messages|last).text] }} '
+      unsafe: false
+    type: haystack.components.converters.output_adapter.OutputAdapter
+  agent:
+    init_parameters:
+      chat_generator:
+        init_parameters:
+          api_base_url:
+          api_key:
+            env_vars:
+            - OPENAI_API_KEY
+            strict: false
+            type: env_var
+          generation_kwargs: {}
+          max_retries:
+          model: gpt-4o
+          organization:
+          streaming_callback:
+          timeout:
+          tools:
+          tools_strict: false
+        type: haystack.components.generators.chat.openai.OpenAIChatGenerator
+      exit_conditions:
+      - text
+      max_agent_steps: 100
+      raise_on_tool_invocation_failure: false
+      state_schema: {}
+      streaming_callback:
+      system_prompt: |-
+        You are a deep research assistant.
+        You create comprehensive research reports to answer the user's questions.
+        You use the 'search'-tool to answer any questions.
+        You perform multiple searches until you have the information you need to answer the question.
+        Make sure you research different aspects of the question.
+        Use markdown to format your response.
+        When you use information from the websearch results, cite your sources using markdown links.
+        It is important that you cite accurately.
+      tools:
+      - data:
+          component:
+            init_parameters:
+              input_mapping:
+                query:
+                - search.query
+              output_mapping:
+                builder.prompt: result
+              pipeline:
+                components:
+                  builder:
+                    init_parameters:
+                      required_variables: "*"
+                      template: |-
+                        {% for doc in docs %}
+                          {% if doc.content and doc.meta.url|length > 0 %}
+                          <search-result url="{{ doc.meta.url }}">
+                              {{ doc.content|truncate(25000) }}
+                          </search-result>
+                          {% endif %}
+                        {% endfor %}
+                      variables:
+                    type: haystack.components.builders.prompt_builder.PromptBuilder
+                  converter:
+                    init_parameters:
+                      extraction_kwargs: {}
+                      store_full_path: false
+                    type: haystack.components.converters.html.HTMLToDocument
+                  fetcher:
+                    init_parameters:
+                      raise_on_failure: false
+                      retry_attempts: 2
+                      timeout: 3
+                      user_agents:
+                      - haystack/LinkContentFetcher/2.11.1
+                    type: haystack.components.fetchers.link_content.LinkContentFetcher
+                  search:
+                    init_parameters:
+                      api_key:
+                        env_vars:
+                        - SERPERDEV_API_KEY
+                        strict: false
+                        type: env_var
+                      search_params: {}
+                      top_k: 10
+                    type: haystack.components.websearch.serper_dev.SerperDevWebSearch
+                connection_type_validation: true
+                connections:
+                - receiver: fetcher.urls
+                  sender: search.links
+                - receiver: converter.sources
+                  sender: fetcher.streams
+                - receiver: builder.docs
+                  sender: converter.documents
+                max_runs_per_component: 100
+                metadata: {}
+            type: haystack.core.super_component.super_component.SuperComponent
+          description: Use this tool to search for information on the internet.
+          inputs_from_state:
+          name: search
+          parameters:
+        type: haystack.tools.component_tool.ComponentTool
+    type: haystack.components.agents.agent.Agent
+  answer_builder:
+    init_parameters:
+      pattern:
+      reference_pattern:
+    type: haystack.components.builders.answer_builder.AnswerBuilder
+  history_parser:
+    init_parameters: {}
+    type: dc_custom_component.components.parsers.chat_history_parser.DeepsetChatHistoryParser
+
+
+connections:
+- receiver: agent.messages
+  sender: history_parser.messages
+- receiver: adapter.messages
+  sender: agent.messages
+- receiver: answer_builder.replies
+  sender: adapter.output
+
+inputs:
+  query:
+  - answer_builder.query
+  - history_parser.history_and_query
+
+outputs:
+  answers: answer_builder.answers
+
+pipeline_output_type: chat
+
+max_runs_per_component: 100
+
+metadata: {}

deepset_mcp/benchmark/tasks/pipelines/chat_agent_jinja_syntax.yml

@@ -0,0 +1,141 @@
+# 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:
+  adapter:
+    init_parameters:
+      custom_filters: {}
+      output_type: List[str]
+      template: '{{ [messages|last.text] }}'
+      unsafe: false
+    type: haystack.components.converters.output_adapter.OutputAdapter
+  agent:
+    init_parameters:
+      chat_generator:
+        init_parameters:
+          api_base_url:
+          api_key:
+            env_vars:
+            - OPENAI_API_KEY
+            strict: false
+            type: env_var
+          generation_kwargs: {}
+          max_retries:
+          model: gpt-4o
+          organization:
+          streaming_callback:
+          timeout:
+          tools:
+          tools_strict: false
+        type: haystack.components.generators.chat.openai.OpenAIChatGenerator
+      exit_conditions:
+      - text
+      max_agent_steps: 100
+      raise_on_tool_invocation_failure: false
+      state_schema: {}
+      streaming_callback:
+      system_prompt: |-
+        You are a deep research assistant.
+        You create comprehensive research reports to answer the user's questions.
+        You use the 'search'-tool to answer any questions.
+        You perform multiple searches until you have the information you need to answer the question.
+        Make sure you research different aspects of the question.
+        Use markdown to format your response.
+        When you use information from the websearch results, cite your sources using markdown links.
+        It is important that you cite accurately.
+      tools:
+      - data:
+          component:
+            init_parameters:
+              input_mapping:
+                query:
+                - search.query
+              output_mapping:
+                builder.prompt: result
+              pipeline:
+                components:
+                  builder:
+                    init_parameters:
+                      required_variables: "*"
+                      template: |-
+                        {% for doc in docs %}
+                          {% if doc.content and doc.meta.url|length > 0 %}
+                          <search-result url="{{ doc.meta.url }}">
+                              {{ doc.content|truncate(25000) }}
+                          </search-result>
+                          {% endif %}
+                        {% endfor %}
+                      variables:
+                    type: haystack.components.builders.prompt_builder.PromptBuilder
+                  converter:
+                    init_parameters:
+                      extraction_kwargs: {}
+                      store_full_path: false
+                    type: haystack.components.converters.html.HTMLToDocument
+                  fetcher:
+                    init_parameters:
+                      raise_on_failure: false
+                      retry_attempts: 2
+                      timeout: 3
+                      user_agents:
+                      - haystack/LinkContentFetcher/2.11.1
+                    type: haystack.components.fetchers.link_content.LinkContentFetcher
+                  search:
+                    init_parameters:
+                      api_key:
+                        env_vars:
+                        - SERPERDEV_API_KEY
+                        strict: false
+                        type: env_var
+                      search_params: {}
+                      top_k: 10
+                    type: haystack.components.websearch.serper_dev.SerperDevWebSearch
+                connection_type_validation: true
+                connections:
+                - receiver: fetcher.urls
+                  sender: search.links
+                - receiver: converter.sources
+                  sender: fetcher.streams
+                - receiver: builder.docs
+                  sender: converter.documents
+                max_runs_per_component: 100
+                metadata: {}
+            type: haystack.core.super_component.super_component.SuperComponent
+          description: Use this tool to search for information on the internet.
+          inputs_from_state:
+          name: search
+          parameters:
+        type: haystack.tools.component_tool.ComponentTool
+    type: haystack.components.agents.agent.Agent
+  answer_builder:
+    init_parameters:
+      pattern:
+      reference_pattern:
+    type: haystack.components.builders.answer_builder.AnswerBuilder
+  history_parser:
+    init_parameters: {}
+    type: dc_custom_component.components.parsers.chat_history_parser.DeepsetChatHistoryParser
+
+
+connections:
+- receiver: agent.messages
+  sender: history_parser.messages
+- receiver: adapter.messages
+  sender: agent.messages
+- receiver: answer_builder.replies
+  sender: adapter.output
+
+inputs:
+  query:
+  - answer_builder.query
+  - history_parser.history_and_query
+
+outputs:
+  answers: answer_builder.answers
+
+pipeline_output_type: chat
+
+max_runs_per_component: 100
+
+metadata: {}

deepset_mcp/benchmark/tasks/pipelines/chat_rag_answers_wrong_format.yml

@@ -0,0 +1,181 @@
+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
+
+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: 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: qa_prompt_builder.prompt
+  receiver: qa_llm.prompt
+
+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:
+  documents: "ranker.documents"
+  answers: "qa_llm.replies"
+
+
+max_runs_per_component: 100
+
+metadata: {}

deepset_mcp/benchmark/tasks/pipelines/chat_rag_missing_output_mapping.yml

@@ -0,0 +1,189 @@
+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"
+
+max_runs_per_component: 100
+
+metadata: {}