qtype 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

qtype/examples/data_processing/invoke_other_flows.qtype.yaml

@@ -0,0 +1,98 @@
+id: text_analysis_pipeline
+description: Demonstrates invoking reusable flows for text analysis
+
+models:
+  - type: Model
+    id: nova_lite
+    provider: aws-bedrock
+    model_id: amazon.nova-lite-v1:0
+
+flows:
+  # Reusable flow for text summarization
+  - type: Flow
+    id: summarize_text
+    description: Summarizes input text
+    variables:
+      - id: input_text
+        type: text
+      - id: output_summary
+        type: text
+    inputs:
+      - input_text
+    outputs:
+      - output_summary
+    steps:
+      - type: LLMInference
+        id: summarize_step
+        model: nova_lite
+        system_message: "You provide concise summaries."
+        inputs: [input_text]
+        outputs: [output_summary]
+
+  # Reusable flow for sentiment analysis
+  - type: Flow
+    id: analyze_sentiment
+    description: Analyzes sentiment of text
+    variables:
+      - id: input_for_sentiment
+        type: text
+      - id: output_sentiment
+        type: text
+    inputs:
+      - input_for_sentiment
+    outputs:
+      - output_sentiment
+    steps:
+      - type: LLMInference
+        id: sentiment_step
+        model: nova_lite
+        system_message: "Analyze sentiment. Respond with only: positive, negative, or neutral."
+        inputs: [input_for_sentiment]
+        outputs: [output_sentiment]
+
+  # Main processing flow
+  - type: Flow
+    id: main
+    description: Orchestrates text analysis using multiple flows
+    variables:
+      - id: article_text
+        type: text
+      - id: summary
+        type: text
+      - id: sentiment
+        type: text
+      - id: report
+        type: text
+    inputs:
+      - article_text
+    outputs:
+      - report
+    steps:
+      # Invoke summarization flow
+      - type: InvokeFlow
+        id: get_summary
+        flow: summarize_text
+        input_bindings:
+          input_text: article_text
+        output_bindings:
+          output_summary: summary
+
+      # Invoke sentiment analysis flow
+      - type: InvokeFlow
+        id: get_sentiment
+        flow: analyze_sentiment
+        input_bindings:
+          input_for_sentiment: article_text
+        output_bindings:
+          output_sentiment: sentiment
+
+      # Combine results into a report
+      - type: PromptTemplate
+        id: create_report
+        template: |
+          Analysis Report
+          ---------------
+          Sentiment: {sentiment}
+          Summary: {summary}
+        inputs: [summary, sentiment]
+        outputs: [report]

qtype/examples/data_processing/load_documents.qtype.yaml

@@ -0,0 +1,31 @@
+# Load all markdown files from docs directory using DocumentSource
+#
+# This example demonstrates using DocumentSource with SimpleDirectoryReader
+# to load documents from a local directory with file filtering.
+
+id: load_documents_example
+description: Load markdown files from docs directory
+
+flows:
+  - type: Flow
+    id: load_md_files
+    description: Load all markdown files from docs directory
+
+    variables:
+      - id: document
+        type: RAGDocument
+
+    inputs: []
+    outputs:
+      - document
+
+    steps:
+      - type: DocumentSource
+        id: md_docs
+        reader_module: llama_index.core.SimpleDirectoryReader
+        args:
+          input_dir: docs
+          required_exts: [".md"]
+          recursive: true
+        outputs:
+          - document

qtype/examples/data_processing/sample_article.txt

@@ -0,0 +1 @@
+Artificial intelligence is revolutionizing healthcare by enabling faster diagnoses and personalized treatment plans. Machine learning algorithms can analyze medical images with incredible accuracy, helping doctors detect diseases earlier. This technology is improving patient outcomes and reducing healthcare costs.

qtype/examples/data_processing/sample_documents.jsonl

@@ -0,0 +1,5 @@
+{"document": "The new quantum computing breakthrough could revolutionize AI processing speeds."}
+{"document": "Federal Reserve announces interest rate changes to combat inflation."}
+{"document": "New clinical trial shows promising results for cancer treatment."}
+{"document": "University expands online learning programs for remote students."}
+{"document": "Cryptocurrency markets experience volatility amid regulatory concerns."}

qtype/examples/invoke_models/invoke_embedding_aws.qtype.yaml

@@ -0,0 +1,45 @@
+id: invoke_embedding_test
+description: Test InvokeEmbedding step with AWS Bedrock embeddings
+
+# AWS Authentication for Bedrock
+auths:
+  - type: aws
+    id: aws_auth
+    profile_name: ${AWS_PROFILE}
+
+models:
+  # Embedding model using AWS Bedrock
+  - type: EmbeddingModel
+    id: titan_embed
+    provider: aws-bedrock
+    model_id: amazon.titan-embed-text-v2:0
+    dimensions: 1024
+    auth: aws_auth
+
+flows:
+  - type: Flow
+    id: test_invoke_embedding
+    description: Generate embeddings for text using AWS Bedrock
+    
+    variables:
+      - id: input_text
+        type: text
+        ui:
+          widget: textarea
+      - id: embedding
+        type: Embedding
+    
+    inputs:
+      - input_text
+    
+    outputs:
+      - embedding
+    
+    steps:
+      - id: generate_embedding
+        type: InvokeEmbedding
+        model: titan_embed
+        inputs:
+          - input_text
+        outputs:
+          - embedding

qtype/examples/language_features/optional_variables.qtype.yaml

@@ -0,0 +1,32 @@
+id: optional_variables_demo
+description: Demonstrates optional variables that can handle missing data gracefully
+
+flows:
+  - id: extract_optional_field
+    variables:
+      - id: user_profile
+        type: text
+      - id: email
+        type: text?
+
+    inputs:
+      - user_profile
+    outputs:
+      - email
+
+    steps:
+      # Try to extract email - may not exist, will return None if missing
+      - type: FieldExtractor
+        id: extract_email
+        inputs:
+          - user_profile
+        outputs:
+          - email
+        json_path: $.email
+
+      - type: Echo
+        id: show_result
+        inputs:
+          - email
+        outputs:
+          - email

qtype/examples/language_features/story_prompt.txt

@@ -0,0 +1,6 @@
+You are a creative storyteller. Write a short, engaging story based on the following theme:
+
+Theme: {theme}
+Tone: {tone}
+
+Create a story that is 3-4 paragraphs long. Make it captivating and appropriate for the specified tone.

qtype/examples/legacy/data/customers.csv

@@ -0,0 +1,6 @@
+name,region,purchases
+Alice,West,5
+Bob,East,3
+Charlie,West,7
+Diana,North,2
+Eve,East,4

qtype/examples/legacy/echo/readme.md

@@ -0,0 +1,29 @@
+# Echo Examples
+
+These examples are intended to be for testing purposes or early stage development. Output will be a replicate of the input.
+
+**Primitive types**
+```
+class PrimitiveTypeEnum(str, Enum):
+    """Represents the type of data a user or system input can accept within the DSL."""
+
+    audio = "audio"
+    boolean = "boolean"
+    bytes = "bytes"
+    citation_document = "citation_document"
+    citation_url = "citation_url"
+    date = "date"
+    datetime = "datetime"
+    int = "int"
+    file = "file"
+    float = "float"
+    image = "image"
+    text = "text"
+    time = "time"
+    video = "video"
+    thinking = "thinking"
+```
+To test out a primitive type:
+
+- Duplicate `examples/echo/video.qtype.yaml`
+- Replace all mentions of video with the primitive type you wish to test

qtype/examples/legacy/qtype_plugin_example.py

@@ -0,0 +1,51 @@
+"""
+Example QType CLI plugin.
+
+This demonstrates how to create a third-party plugin for the QType CLI.
+To use this as a plugin, you would:
+
+1. Put this code in a separate package
+2. Add an entry point in pyproject.toml:
+   [project.entry-points."qtype.commands"]
+   example = "your_package.qtype_example:parser"
+3. Install the package
+"""
+
+import argparse
+
+
+def parser(subparsers: argparse._SubParsersAction) -> None:
+    """Register the 'example' subcommand.
+
+    Args:
+        subparsers: The subparsers object to add the command to.
+    """
+    example_parser = subparsers.add_parser(
+        "example", help="Example plugin command for QType CLI"
+    )
+    example_parser.add_argument(
+        "--message",
+        default="Hello from QType plugin!",
+        help="Message to display (default: Hello from QType plugin!)",
+    )
+    example_parser.add_argument(
+        "--count",
+        type=int,
+        default=1,
+        help="Number of times to display the message (default: 1)",
+    )
+    # Set the function to call when this command is invoked
+    example_parser.set_defaults(func=example_command)
+
+
+def example_command(args: argparse.Namespace) -> None:
+    """Handle the 'example' subcommand.
+
+    Args:
+        args: Command-line arguments containing message and count.
+    """
+    for i in range(args.count):
+        print(f"{i + 1}: {args.message}")
+
+    print("\nThis command was loaded as a plugin!")
+    print("Plugin authors can extend QType CLI functionality this way.")

qtype/examples/legacy/sample_data.txt

@@ -0,0 +1,43 @@
+Sales Data Q1 2024
+==================
+
+Summary Statistics:
+- Total Records: 1,472 transactions
+- Date Range: January 1 - March 31, 2024
+- Products: A, B, C, D
+- Regions: North, South, East, West
+
+Top Performing Products:
+1. Product A: $1,245,890 total sales (avg $847/transaction)
+2. Product C: $1,123,450 total sales (avg $763/transaction)
+3. Product B: $987,230 total sales (avg $671/transaction)
+4. Product D: $856,340 total sales (avg $582/transaction)
+
+Regional Breakdown:
+- North Region: $1,089,450 (26.3% of total)
+- South Region: $1,045,230 (25.2% of total)
+- East Region: $1,012,890 (24.4% of total)
+- West Region: $1,001,340 (24.1% of total)
+
+Key Trends:
+- Product A shows consistent growth throughout Q1 (+15% month-over-month)
+- West region had strongest growth rate despite lower absolute numbers
+- Discount rates ranged from 0% to 20%, with 10% being most common
+- Average transaction size increased 8% from Jan to March
+- Customer count per transaction averaging 25 customers
+
+Notable Patterns:
+- Weekday sales 23% higher than weekend sales
+- Product D underperforming in South region specifically
+- Strong correlation between discount rate and quantity sold
+- North region showing premium pricing power (higher avg transaction)
+
+Concerns:
+- Product D sales declining 5% month-over-month
+- South region discount rates higher than other regions
+- Customer acquisition costs need monitoring
+
+Opportunities:
+- West region expansion showing strong ROI
+- Product A momentum could be leveraged for upselling
+- Cross-regional best practices could improve South region performance

qtype/examples/legacy/vertex/README.md

@@ -0,0 +1,11 @@
+To use a Vertex example, set the following environment variables manually:
+```
+export GOOGLE_CLOUD_PROJECT=
+export GOOGLE_CLOUD_LOCATION=
+export GOOGLE_APPLICATION_CREDENTIALS=
+```
+
+Using gcloud CLI:
+How to setup [Gemini CLI Authentication Setup](https://github.com/google-gemini/gemini-cli/blob/main/docs/get-started/authentication.md)
+
+`profile_name`: Replace default with relevant GCP project name in `.config/gcloud/configurations/your-project-configuration-file`

qtype/examples/rag/recipe_chatbot.qtype.yaml

@@ -0,0 +1,216 @@
+id: recipe_rag_chatbot
+description: |
+  RAG chatbot for the Chowdown recipe collection from GitHub.
+  
+  This application provides two flows:
+  
+  1. recipe_chat: Conversational chatbot that answers questions about recipes
+     - Uses RAG to find relevant recipes based on user questions
+     - Maintains conversation history with memory
+     - Provides cooking advice, recipe recommendations, and ingredient information
+  
+  2. recipe_ingestion: Ingests recipe markdown files into vector database
+     - Clones/fetches recipes from GitHub (clarklab/chowdown)
+     - Splits recipe documents into searchable chunks
+     - Generates embeddings using AWS Bedrock Titan
+     - Stores in Qdrant vector database for fast similarity search
+  
+  Prerequisites:
+  - AWS credentials configured (AWS_PROFILE environment variable)
+  - Qdrant running locally on port 6333 (or update args for Qdrant Cloud)
+  - Clone the recipe repo: git clone https://github.com/clarklab/chowdown.git
+  
+  To ingest recipes:
+    qtype run recipe_chatbot.qtype.yaml --flow recipe_ingestion
+  
+  To start chatbot:
+    qtype serve recipe_chatbot.qtype.yaml --flow recipe_chat
+
+# AWS Authentication for Bedrock
+auths:
+  - type: aws
+    id: aws_auth
+    profile_name: ${AWS_PROFILE}
+
+# Models
+models:
+  # Embedding model for vectorizing recipes and queries
+  - type: EmbeddingModel
+    id: titan_embed
+    provider: aws-bedrock
+    model_id: amazon.titan-embed-text-v2:0
+    dimensions: 1024
+    auth: aws_auth
+  
+  # Chat model for conversational responses
+  - type: Model
+    id: claude_sonnet
+    provider: aws-bedrock
+    model_id: us.anthropic.claude-3-5-sonnet-20241022-v2:0
+    inference_params:
+      temperature: 0.7
+      max_tokens: 4096
+    auth: aws_auth
+
+# Vector index for recipe embeddings
+indexes:
+  - type: VectorIndex
+    module: llama_index.vector_stores.qdrant.QdrantVectorStore
+    id: recipe_index
+    name: chowdown_recipes
+    embedding_model: titan_embed
+    args:
+      collection_name: chowdown_recipes
+      url: http://localhost:6333
+      api_key: ""  # Empty for local Qdrant
+
+# Memory for maintaining conversation context
+memories:
+  - id: recipe_chat_memory
+    token_limit: 10000
+    chat_history_token_ratio: 0.7
+
+# Flows
+flows:
+  # Conversational chatbot flow
+  - type: Flow
+    id: recipe_chat
+    description: Chat with the recipe collection using RAG
+    
+    interface:
+      type: Conversational
+    
+    variables:
+      - id: user_message
+        type: ChatMessage
+      - id: user_question
+        type: text
+      - id: search_results
+        type: list[RAGSearchResult]
+      - id: context_prompt
+        type: text
+      - id: assistant_response
+        type: ChatMessage
+    
+    inputs:
+      - user_message
+    
+    outputs:
+      - assistant_response
+    
+    steps:
+      # Extract text from user's chat message
+      - id: extract_question
+        type: FieldExtractor
+        json_path: "$.blocks[?(@.type == 'text')].content"
+        inputs:
+          - user_message
+        outputs:
+          - user_question
+      
+      # Search recipe vector index for relevant recipes
+      - id: search_recipes
+        type: VectorSearch
+        index: recipe_index
+        default_top_k: 5
+        inputs:
+          - user_question
+        outputs:
+          - search_results
+      
+      # Build prompt with recipe context
+      - id: build_context_prompt
+        type: PromptTemplate
+        template: |
+          You are a helpful cooking assistant with access to a collection of recipes from Chowdown.
+          
+          Here are the most relevant recipes based on the user's question:
+          
+          {search_results}
+          
+          User question: {user_question}
+          
+          Please provide a helpful answer based on the recipes above. If you're suggesting a recipe, 
+          include key ingredients and brief cooking instructions. If the recipes don't contain 
+          relevant information, politely say so and offer general cooking advice if appropriate.
+        inputs:
+          - search_results
+          - user_question
+        outputs:
+          - context_prompt
+      
+      # Generate conversational response using LLM with memory
+      - id: generate_response
+        type: LLMInference
+        model: claude_sonnet
+        memory: recipe_chat_memory
+        system_message: |
+          You are a friendly and knowledgeable cooking assistant. You help users find recipes, 
+          answer questions about ingredients, suggest substitutions, and provide cooking tips.
+          Base your answers on the provided recipe context, but feel free to add general 
+          cooking knowledge when helpful. Be conversational and enthusiastic about food!
+        inputs:
+          - context_prompt
+        outputs:
+          - assistant_response
+
+  # Recipe ingestion flow
+  - type: Flow
+    id: recipe_ingestion
+    description: Load recipes from local GitHub clone, chunk, embed, and index
+    
+    variables:
+      - id: recipe_document
+        type: RAGDocument
+      - id: recipe_chunk
+        type: RAGChunk
+      - id: embedded_chunk
+        type: RAGChunk
+    
+    outputs:
+      - embedded_chunk
+    
+    steps:
+      # Load recipe markdown files from local clone
+      - id: load_recipes
+        type: DocumentSource
+        reader_module: llama_index.core.SimpleDirectoryReader
+        args:
+          input_dir: "./chowdown/_recipes"
+          recursive: false
+          required_exts: [".md"]
+        outputs:
+          - recipe_document
+      
+      # Split recipes into chunks for better retrieval
+      - id: split_recipes
+        type: DocumentSplitter
+        splitter_name: "SentenceSplitter"
+        chunk_size: 512
+        chunk_overlap: 50
+        inputs:
+          - recipe_document
+        outputs:
+          - recipe_chunk
+      
+      # Generate embeddings for each chunk
+      - id: embed_chunks
+        type: DocumentEmbedder
+        model: titan_embed
+        concurrency_config:
+          num_workers: 5
+        inputs:
+          - recipe_chunk
+        outputs:
+          - embedded_chunk
+      
+      # Store embedded chunks in Qdrant
+      - id: index_recipes
+        type: IndexUpsert
+        index: recipe_index
+        batch_config:
+          batch_size: 25
+        inputs:
+          - embedded_chunk
+        outputs:
+          - embedded_chunk