@bluefly/openstandardagents 0.3.3 → 0.3.5

package/examples/migrations/langchain/01-python-react-agent-after.ossa.yaml

@@ -0,0 +1,38 @@
+apiVersion: ossa/v0.3.5
+kind: Agent
+metadata:
+  name: python-react-agent
+  version: 0.1.0
+  description: Migrated from LangChain react agent
+  labels:
+    ossa-version: v0.3.5
+    migration-source: langchain
+  annotations:
+    ossa.io/migration: langchain-to-ossa
+    ossa.io/migrated-date: "2026-01-15"
+    ossa.io/source-file: 01-python-react-agent-before.py
+spec:
+  role: Reasoning and Action (ReAct) Agent - uses chain-of-thought reasoning to decide which tools to use
+  llm:
+    provider: openai
+    model: gpt-4
+    temperature: 0.7
+    maxTokens: 2000
+  tools:
+    - type: function
+      name: search_web
+      description: Search the web for information. Use this when you need to find current information or facts.
+    - type: function
+      name: calculate
+      description: Calculate mathematical expressions. Use this for any math operations.
+    - type: function
+      name: get_weather
+      description: Get current weather for a location. Use this when asked about weather.
+  autonomy:
+    level: autonomous
+  extensions:
+    langchain:
+      memory_type: ConversationBufferMemory
+      memory_config:
+        memory_key: chat_history
+        return_messages: true

package/examples/migrations/langchain/01-python-react-agent-before.py

@@ -0,0 +1,62 @@
+"""
+LangChain ReAct Agent with Tools
+This agent uses reasoning and action to solve problems with access to search and calculator tools.
+"""
+
+from langchain.agents import initialize_agent, AgentType, Tool
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
+from langchain.tools import tool
+
+# Initialize LLM
+llm = ChatOpenAI(
+    model_name="gpt-4",
+    temperature=0.7,
+    max_tokens=2000
+)
+
+# Define tools
+@tool
+def search_web(query: str) -> str:
+    """Search the web for information. Use this when you need to find current information or facts."""
+    # Implementation would go here
+    return f"Search results for: {query}"
+
+@tool
+def calculate(expression: str) -> str:
+    """Calculate mathematical expressions. Use this for any math operations."""
+    try:
+        result = eval(expression)
+        return f"Result: {result}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+@tool
+def get_weather(location: str) -> str:
+    """Get current weather for a location. Use this when asked about weather."""
+    # Implementation would go here
+    return f"Weather in {location}: Sunny, 72°F"
+
+tools = [search_web, calculate, get_weather]
+
+# Initialize memory
+memory = ConversationBufferMemory(
+    memory_key="chat_history",
+    return_messages=True
+)
+
+# Create ReAct agent
+agent = initialize_agent(
+    tools=tools,
+    llm=llm,
+    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,
+    memory=memory,
+    verbose=True,
+    handle_parsing_errors=True,
+    max_iterations=5
+)
+
+# Example usage
+if __name__ == "__main__":
+    response = agent.run("What's the weather in San Francisco and what's 25 * 4?")
+    print(response)

package/examples/migrations/langchain/02-typescript-conversational-after.ossa.yaml

@@ -0,0 +1,40 @@
+apiVersion: ossa/v0.3.5
+kind: Agent
+metadata:
+  name: typescript-conversational
+  version: 0.1.0
+  description: Migrated from LangChain openai-functions agent
+  labels:
+    ossa-version: v0.3.5
+    migration-source: langchain
+  annotations:
+    ossa.io/migration: langchain-to-ossa
+    ossa.io/migrated-date: "2026-01-15"
+    ossa.io/source-file: 02-typescript-conversational-before.ts
+spec:
+  role: OpenAI Functions Agent - uses OpenAI function calling to select and use tools
+  llm:
+    provider: openai
+    model: gpt-4
+    temperature: 0.5
+    maxTokens: 1500
+  tools:
+    - type: function
+      name: send_email
+      description: Send an email to a recipient. Use this when asked to send emails.
+    - type: function
+      name: check_calendar
+      description: Check calendar for available time slots. Use this when scheduling meetings.
+    - type: function
+      name: search_knowledge_base
+      description: Search internal knowledge base for information. Use this for company policies, procedures, or documentation.
+  autonomy:
+    level: assisted
+  extensions:
+    langchain:
+      memory_type: BufferMemory
+      memory_config:
+        returnMessages: true
+        memoryKey: chat_history
+        inputKey: input
+        outputKey: output

package/examples/migrations/langchain/02-typescript-conversational-before.ts

@@ -0,0 +1,79 @@
+/**
+ * LangChain Conversational Agent with Memory
+ * This agent maintains conversation context and can use multiple tools
+ */
+
+import { ChatOpenAI } from "langchain/chat_models/openai";
+import { initializeAgentExecutorWithOptions } from "langchain/agents";
+import { DynamicStructuredTool } from "langchain/tools";
+import { BufferMemory } from "langchain/memory";
+import { z } from "zod";
+
+// Initialize LLM
+const llm = new ChatOpenAI({
+  modelName: "gpt-4",
+  temperature: 0.5,
+  maxTokens: 1500,
+});
+
+// Define tools
+const emailTool = new DynamicStructuredTool({
+  name: "send_email",
+  description: "Send an email to a recipient. Use this when asked to send emails.",
+  schema: z.object({
+    to: z.string().describe("Email recipient"),
+    subject: z.string().describe("Email subject"),
+    body: z.string().describe("Email body"),
+  }),
+  func: async ({ to, subject, body }) => {
+    console.log(`Sending email to ${to}: ${subject}`);
+    return `Email sent successfully to ${to}`;
+  },
+});
+
+const calendarTool = new DynamicStructuredTool({
+  name: "check_calendar",
+  description: "Check calendar for available time slots. Use this when scheduling meetings.",
+  schema: z.object({
+    date: z.string().describe("Date to check (YYYY-MM-DD)"),
+  }),
+  func: async ({ date }) => {
+    return `Available slots on ${date}: 9:00 AM, 2:00 PM, 4:00 PM`;
+  },
+});
+
+const knowledgeBaseTool = new DynamicStructuredTool({
+  name: "search_knowledge_base",
+  description: "Search internal knowledge base for information. Use this for company policies, procedures, or documentation.",
+  schema: z.object({
+    query: z.string().describe("Search query"),
+  }),
+  func: async ({ query }) => {
+    return `Knowledge base results for "${query}": Found 5 relevant documents...`;
+  },
+});
+
+const tools = [emailTool, calendarTool, knowledgeBaseTool];
+
+// Initialize memory
+const memory = new BufferMemory({
+  returnMessages: true,
+  memoryKey: "chat_history",
+  inputKey: "input",
+  outputKey: "output",
+});
+
+// Create conversational agent
+const executor = await initializeAgentExecutorWithOptions(tools, llm, {
+  agentType: "openai-functions",
+  memory,
+  verbose: true,
+  maxIterations: 5,
+});
+
+// Example usage
+const result = await executor.call({
+  input: "Can you check my calendar for tomorrow and schedule a meeting at 2 PM?",
+});
+
+console.log(result.output);

package/examples/migrations/langchain/03-sequential-chain-after.ossa.yaml

@@ -0,0 +1,95 @@
+apiVersion: ossa/v0.3.5
+kind: Workflow
+metadata:
+  name: sequential-chain
+  version: 0.1.0
+  description: Migrated from LangChain sequential chain
+  labels:
+    ossa-version: v0.3.5
+    migration-source: langchain
+  annotations:
+    ossa.io/migration: langchain-to-ossa
+    ossa.io/migrated-date: "2026-01-15"
+    ossa.io/source-file: 03-sequential-chain-before.py
+spec:
+  role: Sequential chain processor - executes steps in order
+  llm:
+    provider: anthropic
+    model: claude-3-sonnet-20240229
+    temperature: 0.3
+    maxTokens: 4000
+  steps:
+    - id: extract
+      name: extract
+      description: Extract key information from document
+      task:
+        prompt: |
+          Extract the key information from the following document:
+
+          Document: {{ inputs.document }}
+
+          Extract:
+          - Main topic
+          - Key points (bullet list)
+          - Entities mentioned (people, organizations, dates)
+      outputs:
+        - extracted_info
+
+    - id: analyze
+      name: analyze
+      description: Analyze sentiment and tone
+      task:
+        prompt: |
+          Analyze the sentiment and tone of the following extracted information:
+
+          {{ steps.extract.outputs.extracted_info }}
+
+          Provide:
+          - Overall sentiment (positive/negative/neutral)
+          - Tone (formal/informal/technical)
+          - Confidence level
+      outputs:
+        - analysis
+
+    - id: summarize
+      name: summarize
+      description: Generate comprehensive summary
+      task:
+        prompt: |
+          Create a comprehensive summary based on the extracted information and analysis:
+
+          Extracted Information:
+          {{ steps.extract.outputs.extracted_info }}
+
+          Analysis:
+          {{ steps.analyze.outputs.analysis }}
+
+          Generate a 2-3 paragraph executive summary that captures the essence of the document,
+          its key points, and the overall tone.
+      outputs:
+        - summary
+
+  inputs:
+    type: object
+    properties:
+      document:
+        type: string
+        description: Document text to process
+    required:
+      - document
+
+  outputs:
+    type: object
+    properties:
+      extracted_info:
+        type: string
+        description: Extracted information from document
+      analysis:
+        type: string
+        description: Sentiment and tone analysis
+      summary:
+        type: string
+        description: Executive summary
+
+  autonomy:
+    level: autonomous

package/examples/migrations/langchain/03-sequential-chain-before.py

@@ -0,0 +1,100 @@
+"""
+LangChain Sequential Chain for Document Processing
+This chain processes documents through multiple stages: extraction, analysis, and summarization
+"""
+
+from langchain.chains import LLMChain, SequentialChain
+from langchain.chat_models import ChatAnthropic
+from langchain.prompts import PromptTemplate
+
+# Initialize LLM
+llm = ChatAnthropic(
+    model="claude-3-sonnet-20240229",
+    temperature=0.3,
+    max_tokens=4000
+)
+
+# Chain 1: Extract key information
+extract_prompt = PromptTemplate(
+    input_variables=["document"],
+    template="""Extract the key information from the following document:
+
+Document: {document}
+
+Extract:
+- Main topic
+- Key points (bullet list)
+- Entities mentioned (people, organizations, dates)
+
+Extracted Information:"""
+)
+
+extract_chain = LLMChain(
+    llm=llm,
+    prompt=extract_prompt,
+    output_key="extracted_info"
+)
+
+# Chain 2: Analyze sentiment and tone
+analyze_prompt = PromptTemplate(
+    input_variables=["extracted_info"],
+    template="""Analyze the sentiment and tone of the following extracted information:
+
+{extracted_info}
+
+Provide:
+- Overall sentiment (positive/negative/neutral)
+- Tone (formal/informal/technical)
+- Confidence level
+
+Analysis:"""
+)
+
+analyze_chain = LLMChain(
+    llm=llm,
+    prompt=analyze_prompt,
+    output_key="analysis"
+)
+
+# Chain 3: Generate summary
+summarize_prompt = PromptTemplate(
+    input_variables=["extracted_info", "analysis"],
+    template="""Create a comprehensive summary based on the extracted information and analysis:
+
+Extracted Information:
+{extracted_info}
+
+Analysis:
+{analysis}
+
+Generate a 2-3 paragraph executive summary that captures the essence of the document,
+its key points, and the overall tone.
+
+Summary:"""
+)
+
+summarize_chain = LLMChain(
+    llm=llm,
+    prompt=summarize_prompt,
+    output_key="summary"
+)
+
+# Create sequential chain
+overall_chain = SequentialChain(
+    chains=[extract_chain, analyze_chain, summarize_chain],
+    input_variables=["document"],
+    output_variables=["extracted_info", "analysis", "summary"],
+    verbose=True
+)
+
+# Example usage
+if __name__ == "__main__":
+    sample_document = """
+    The Q4 2023 earnings report shows strong growth across all divisions.
+    Revenue increased 25% year-over-year to $150M. The cloud services division
+    led growth with 40% increase. CEO Jane Smith expressed optimism about 2024
+    prospects, citing new product launches and market expansion plans.
+    """
+
+    result = overall_chain({"document": sample_document})
+    print("Summary:", result["summary"])

package/examples/migrations/langchain/04-config-based-after.ossa.yaml

@@ -0,0 +1,54 @@
+apiVersion: ossa/v0.3.5
+kind: Agent
+metadata:
+  name: customer-support-agent
+  version: 0.1.0
+  description: Migrated from LangChain zero-shot agent
+  labels:
+    ossa-version: v0.3.5
+    migration-source: langchain
+  annotations:
+    ossa.io/migration: langchain-to-ossa
+    ossa.io/migrated-date: "2026-01-15"
+    ossa.io/source-file: 04-config-based-before.yaml
+spec:
+  role: |
+    You are a helpful customer support agent. Your role is to:
+    - Help customers with order inquiries
+    - Answer questions using the FAQ knowledge base
+    - Escalate complex issues by creating support tickets
+
+    Always be polite, professional, and empathetic.
+
+  llm:
+    provider: openai
+    model: gpt-4-turbo
+    temperature: 0.4
+    maxTokens: 2000
+
+  tools:
+    - type: function
+      name: get_order_status
+      description: Retrieve the status of a customer order by order ID
+
+    - type: function
+      name: cancel_order
+      description: Cancel an order if it hasn't shipped yet
+
+    - type: function
+      name: search_faq
+      description: Search the FAQ knowledge base for answers to common questions
+
+    - type: function
+      name: create_ticket
+      description: Create a support ticket for issues that require human intervention
+
+  autonomy:
+    level: assisted
+
+  extensions:
+    langchain:
+      memory_type: ConversationBufferMemory
+      memory_config:
+        memory_key: chat_history
+        return_messages: true

package/examples/migrations/langchain/04-config-based-before.yaml

@@ -0,0 +1,52 @@
+# LangChain Configuration-based Agent
+# This is a YAML configuration that defines an agent without code
+
+agent:
+  name: customer-support-agent
+  type: conversational-react
+  description: Customer support agent with access to order management and knowledge base
+
+llm:
+  provider: openai
+  model: gpt-4-turbo
+  temperature: 0.4
+  max_tokens: 2000
+
+tools:
+  - name: get_order_status
+    type: function
+    description: Retrieve the status of a customer order by order ID
+
+  - name: cancel_order
+    type: function
+    description: Cancel an order if it hasn't shipped yet
+
+  - name: search_faq
+    type: function
+    description: Search the FAQ knowledge base for answers to common questions
+
+  - name: create_ticket
+    type: function
+    description: Create a support ticket for issues that require human intervention
+
+memory:
+  type: ConversationBufferMemory
+  config:
+    memory_key: chat_history
+    return_messages: true
+
+prompts:
+  system: |
+    You are a helpful customer support agent. Your role is to:
+    - Help customers with order inquiries
+    - Answer questions using the FAQ knowledge base
+    - Escalate complex issues by creating support tickets
+
+    Always be polite, professional, and empathetic.
+
+  human: "{input}"
+
+settings:
+  max_iterations: 5
+  handle_parsing_errors: true
+  verbose: false