qtype 0.1.11__py3-none-any.whl → 0.1.12__py3-none-any.whl

examples/data_processing/dataflow_pipelines.qtype.yaml

@@ -0,0 +1,108 @@
+id: review_analysis_pipeline
+description: |
+  Automated product review analysis pipeline demonstrating dataflow processing.
+  Reads reviews from SQLite database, analyzes sentiment with LLM, and writes
+  enriched results to a Parquet file.
+
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 256
+
+flows:
+  - type: Flow
+    id: analyze_reviews
+    description: Batch process product reviews with LLM sentiment analysis
+
+    variables:
+      - id: review_id
+        type: int
+      - id: product_name
+        type: text
+      - id: rating
+        type: int
+      - id: review_text
+        type: text
+      - id: analysis_prompt
+        type: text
+      - id: llm_analysis
+        type: text
+      - id: output_path
+        type: text
+      - id: result_file
+        type: text
+
+    inputs:
+      - output_path
+
+    outputs:
+      - result_file
+
+    steps:
+      # Step 1: Read reviews from SQLite database
+      # SQLSource emits one message per database row
+      - id: load_reviews
+        type: SQLSource
+        connection: "sqlite:///examples/data_processing/reviews.db"
+        query: |
+          SELECT
+            review_id,
+            product_name,
+            rating,
+            review_text
+          FROM product_reviews
+          ORDER BY review_id
+        inputs: []
+        outputs:
+          - review_id
+          - product_name
+          - rating
+          - review_text
+
+      # Step 2: Format analysis prompt for each review
+      # PromptTemplate creates structured prompts from review data
+      - id: create_prompt
+        type: PromptTemplate
+        template: |
+          Analyze this product review in 1-2 sentences. Include:
+          - Overall sentiment (positive/negative/mixed)
+          - 2-3 key themes or points
+
+          Product: {product_name}
+          Rating: {rating}/5
+          Review: {review_text}
+        inputs:
+          - product_name
+          - rating
+          - review_text
+        outputs:
+          - analysis_prompt
+
+      # Step 3: Analyze each review with LLM
+      # LLMInference processes each message through the language model
+      - id: analyze_sentiment
+        type: LLMInference
+        model: nova_lite
+        inputs:
+          - analysis_prompt
+        outputs:
+          - llm_analysis
+
+      # Step 4: Write enriched results to Parquet file
+      # FileWriter batches all messages and writes once
+      - id: write_results
+        type: FileWriter
+        path: output_path
+        inputs:
+          - review_id
+          - product_name
+          - rating
+          - review_text
+          - llm_analysis
+          - output_path
+        outputs:
+          - result_file

examples/data_processing/decode_json.qtype.yaml

@@ -0,0 +1,23 @@
+id: decode_json_example
+description: Decode JSON string into structured data
+
+flows:
+  - id: decode_product
+    description: Parse JSON string into variables
+    inputs: [json_string]
+    outputs: [name, price]
+    
+    variables:
+      - id: json_string
+        type: text
+      - id: name
+        type: text
+      - id: price
+        type: float
+    
+    steps:
+      - type: Decoder
+        id: parse_json
+        format: json
+        inputs: [json_string]
+        outputs: [name, price]

examples/data_processing/explode_items.qtype.yaml

@@ -0,0 +1,25 @@
+id: explode_example
+description: Explode a list into individual items for fan-out processing
+
+flows:
+  - type: Flow
+    id: main
+    description: Takes a list and processes each item individually
+
+    variables:
+      - id: items
+        type: list[text]
+      - id: item
+        type: text
+
+    inputs:
+      - items
+
+    outputs:
+      - item
+
+    steps:
+      - type: Explode
+        id: fan_out
+        inputs: [items]
+        outputs: [item]

examples/data_processing/read_file.qtype.yaml

@@ -0,0 +1,60 @@
+id: read_file_example
+description: Read data from a CSV file
+
+models:
+  - type: Model
+    id: nova
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+
+flows:
+  - type: Flow
+    id: process_file_data
+    description: Read and process data from a CSV file
+
+    variables:
+      - id: query
+        type: text
+      - id: topic
+        type: text
+      - id: prompt
+        type: text
+      - id: answer
+        type: text
+
+    inputs: []
+
+    outputs:
+      - query
+      - topic
+      - answer
+
+    steps:
+      - id: read_data
+        type: FileSource
+        path:
+          uri: examples/data_processing/batch_inputs.csv
+        outputs:
+          - query
+          - topic
+  
+      - id: create_prompt
+        type: PromptTemplate
+        template: |
+          Topic: {topic}
+          Question: {query}
+          
+          Provide a concise answer:
+        inputs:
+          - query
+          - topic
+        outputs:
+          - prompt
+
+      - id: generate_answer
+        type: LLMInference
+        model: nova
+        inputs:
+          - prompt
+        outputs:
+          - answer

examples/invoke_models/create_embeddings.qtype.yaml

@@ -0,0 +1,28 @@
+id: create_embeddings
+description: Generate embeddings from text using AWS Bedrock Titan
+
+models:
+  - type: EmbeddingModel
+    id: titan_embed
+    provider: aws-bedrock
+    model_id: amazon.titan-embed-text-v2:0
+    dimensions: 1024
+
+flows:
+  - type: Flow
+    id: main
+    variables:
+      - id: text
+        type: text
+      - id: embedding
+        type: Embedding
+    inputs:
+      - text
+    outputs:
+      - embedding
+    steps:
+      - type: InvokeEmbedding
+        id: embed_text
+        model: titan_embed
+        inputs: [text]
+        outputs: [embedding]

examples/invoke_models/simple_llm_call.qtype.yaml

@@ -0,0 +1,32 @@
+id: simple_llm_call
+description: Simple example of calling a large language model
+
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 500
+
+flows:
+  - type: Flow
+    id: main
+    variables:
+      - id: text
+        type: text
+      - id: response
+        type: text
+    inputs:
+      - text
+    outputs:
+      - response
+    
+    steps:
+      - type: LLMInference
+        id: assistant
+        model: nova_lite
+        system_message: "You are a helpful assistant"
+        inputs: [text]
+        outputs: [response]

examples/language_features/include_raw.qtype.yaml

@@ -0,0 +1,27 @@
+id: include_raw_example
+description: Demonstrates using include_raw to load prompt templates from external files
+
+flows:
+  - type: Flow
+    id: main
+    variables:
+      - id: theme
+        type: text
+      - id: tone
+        type: text
+      - id: story_prompt
+        type: text
+    inputs:
+      - theme
+      - tone
+    outputs:
+      - story_prompt
+    steps:
+      - id: generate_story
+        type: PromptTemplate
+        template: !include_raw story_prompt.txt
+        inputs:
+          - theme
+          - tone
+        outputs:
+          - story_prompt

examples/language_features/ui_hints.qtype.yaml

@@ -0,0 +1,52 @@
+id: ui_hints_example
+description: Demonstrates how to use UI hints to customize input widgets
+
+models:
+  - type: Model
+    id: nova
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 500
+
+flows:
+  - type: Flow
+    id: generate_story
+    description: Generate a creative story based on a detailed prompt
+    
+    variables:
+      # The 'ui' field provides hints to the web UI about how to render inputs
+      # Using 'widget: textarea' renders a multi-line text area instead of single-line input
+      - id: story_prompt
+        type: text
+        ui:
+          widget: textarea  # Options: text (default), textarea
+      
+      # Variables without 'ui' hints use default widgets based on their type
+      - id: max_length
+        type: int
+      
+      - id: story
+        type: text
+    
+    inputs:
+      - story_prompt
+      - max_length
+    
+    outputs:
+      - story
+    
+    steps:
+      - id: generate
+        type: LLMInference
+        model: nova
+        inputs: [story_prompt, max_length]
+        system_message: |
+          Write a creative story based on this prompt:
+          
+          {{story_prompt}}
+          
+          Keep the story under {{max_length}} words.
+        outputs:
+          - story

examples/legacy/bedrock/data_analysis_with_telemetry.qtype.yaml

@@ -0,0 +1,169 @@
+id: data_analysis_pipeline
+description: A multi-step data analysis pipeline with AWS Bedrock and telemetry tracking
+
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 1024
+
+flows:
+  - type: Flow
+    id: analyze_data_flow
+    description: Load sales data, analyze it with LLM, generate insights
+    variables:
+      - id: raw_data
+        type: text
+      - id: analysis_prompt
+        type: text
+      - id: analysis_result
+        type: text
+      - id: insights_prompt
+        type: text
+      - id: key_insights
+        type: text
+      - id: summary_prompt
+        type: text
+      - id: executive_summary
+        type: text
+      - id: final_report
+        type: text
+      - id: output_file
+        type: text
+    inputs:
+      - output_file
+    outputs:
+      - executive_summary
+      - final_report
+    steps:
+      # Step 1: Load sales data from file
+      - id: load_sales_data
+        type: PromptTemplate
+        template: !include_raw sample_data.txt
+        outputs:
+          - raw_data
+          
+      # Step 2: Create analysis prompt
+      - id: create_analysis_prompt
+        type: PromptTemplate
+        template: |
+          You are a data analyst. Analyze the following sales data and provide:
+          1. A summary of what the data contains
+          2. Key patterns or trends you observe
+          3. Any notable observations or anomalies
+          
+          Sales Data:
+          {raw_data}
+          
+          Provide your analysis in a clear, structured format.
+        inputs:
+          - raw_data
+        outputs:
+          - analysis_prompt
+          
+      # Step 3: Generate initial analysis
+      - id: analyze_with_llm
+        type: LLMInference
+        model: nova_lite
+        system_message: You are an expert data analyst with strong analytical and critical thinking skills.
+        inputs:
+          - analysis_prompt
+        outputs:
+          - analysis_result
+          
+      # Step 4: Create insights extraction prompt
+      - id: create_insights_prompt
+        type: PromptTemplate
+        template: |
+          Based on this analysis, extract the 3-5 most important insights or takeaways:
+          
+          {analysis_result}
+          
+          Format as a bullet list with clear, actionable insights.
+        inputs:
+          - analysis_result
+        outputs:
+          - insights_prompt
+          
+      # Step 5: Extract key insights
+      - id: extract_insights
+        type: LLMInference
+        model: nova_lite
+        system_message: You are an expert at distilling complex analysis into clear, actionable insights.
+        inputs:
+          - insights_prompt
+        outputs:
+          - key_insights
+          
+      # Step 6: Create executive summary prompt
+      - id: create_summary_prompt
+        type: PromptTemplate
+        template: |
+          Create a concise executive summary (2-3 paragraphs) that combines:
+          
+          Original Analysis:
+          {analysis_result}
+          
+          Key Insights:
+          {key_insights}
+          
+          Make it suitable for C-level executives - clear, impactful, and action-oriented.
+        inputs:
+          - analysis_result
+          - key_insights
+        outputs:
+          - summary_prompt
+          
+      # Step 7: Generate executive summary
+      - id: generate_summary
+        type: LLMInference
+        model: nova_lite
+        system_message: You are an expert at writing executive summaries for business leaders.
+        inputs:
+          - summary_prompt
+        outputs:
+          - executive_summary
+          
+      # Step 8: Create final report
+      - id: create_final_report
+        type: PromptTemplate
+        template: |
+          ================================================================================
+          DATA ANALYSIS REPORT
+          ================================================================================
+          
+          EXECUTIVE SUMMARY
+          -----------------
+          {executive_summary}
+          
+          KEY INSIGHTS
+          ------------
+          {key_insights}
+          
+          DETAILED ANALYSIS
+          -----------------
+          {analysis_result}
+          
+          ================================================================================
+          Report generated by QType Data Analysis Pipeline
+          ================================================================================
+        inputs:
+          - executive_summary
+          - key_insights
+          - analysis_result
+        outputs:
+          - final_report
+          
+      # Step 9: Write results to file
+      - id: save_report
+        type: FileWriter
+        path: output_file
+        inputs:
+          - final_report
+
+telemetry:
+  id: data_analysis_telemetry
+  endpoint: http://localhost:6006/v1/traces

examples/legacy/bedrock/hello_world.qtype.yaml

@@ -0,0 +1,39 @@
+id: hello_world
+description: A simple hello world application using AWS Bedrock
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 512
+flows:
+  - type: Flow
+    id: simple_example
+    variables:
+      - id: question
+        type: text
+      - id: formatted_prompt
+        type: text
+      - id: answer
+        type: text
+    inputs:
+      - question
+    outputs:
+      - answer
+    steps:
+      - id: question_prompt
+        type: PromptTemplate
+        template: "You are a helpful assistant. Answer the following question:\n{question}\n"
+        inputs:
+          - question
+        outputs:
+          - formatted_prompt
+      - id: llm_inference_step
+        type: LLMInference
+        model: nova_lite
+        inputs:
+          - formatted_prompt
+        outputs:
+          - answer

examples/legacy/bedrock/hello_world_chat.qtype.yaml

@@ -0,0 +1,37 @@
+id: hello_world
+description: A simple stateful chat flow with AWS Bedrock
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 512
+memories:
+  - id: chat_memory
+    token_limit: 10000
+flows:
+  - type: Flow
+    id: simple_chat_example
+    interface:
+      type: Conversational
+    variables:
+      - id: user_message
+        type: ChatMessage
+      - id: response_message
+        type: ChatMessage
+    inputs:
+      - user_message
+    outputs:
+      - response_message
+    steps:
+      - id: llm_inference_step
+        type: LLMInference
+        model: nova_lite
+        system_message: "You are a helpful assistant."
+        memory: chat_memory
+        inputs:
+          - user_message
+        outputs:
+          - response_message

examples/legacy/bedrock/hello_world_chat_with_telemetry.qtype.yaml

@@ -0,0 +1,40 @@
+id: hello_world
+description: A simple chat flow with AWS Bedrock and telemetry
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 512
+memories:
+  - id: chat_memory
+    token_limit: 10000
+flows:
+  - type: Flow
+    id: simple_chat_example
+    interface:
+      type: Conversational
+    variables:
+      - id: user_message
+        type: ChatMessage
+      - id: response_message
+        type: ChatMessage
+    inputs:
+      - user_message
+    outputs:
+      - response_message
+    steps:
+      - id: llm_inference_step
+        type: LLMInference
+        model: nova_lite
+        system_message: 'You are a helpful assistant, but you provide opposite or incorrect answers to any question. For example, if the user asks "What is 2 + 2?", you should respond with "3".'
+        memory: chat_memory
+        inputs:
+          - user_message
+        outputs:
+          - response_message
+telemetry:
+  id: hello_world_telemetry
+  endpoint: http://localhost:6006/v1/traces

examples/legacy/bedrock/hello_world_chat_with_thinking.qtype.yaml

@@ -0,0 +1,40 @@
+id: hello_world
+description: A simple stateful chat flow with AWS Bedrock
+models:
+  - type: Model
+    id: claude-haiku
+    provider: aws-bedrock
+    model_id: us.anthropic.claude-haiku-4-5-20251001-v1:0
+    inference_params:
+      temperature: 1
+      max_tokens: 2048
+      thinking:
+        type: enabled
+        budget_tokens: 1024
+memories:
+  - id: chat_memory
+    token_limit: 10000
+flows:
+  - type: Flow
+    id: simple_chat_example
+    interface:
+      type: Conversational
+    variables:
+      - id: user_message
+        type: ChatMessage
+      - id: response_message
+        type: ChatMessage
+    inputs:
+      - user_message
+    outputs:
+      - response_message
+    steps:
+      - id: llm_inference_step
+        type: LLMInference
+        model: claude-haiku
+        system_message: "You are a helpful assistant."
+        memory: chat_memory
+        inputs:
+          - user_message
+        outputs:
+          - response_message