init add to majority vote

cookbook/pocketflow-majority-vote/README.md

@@ -0,0 +1,77 @@
+# Extended Thinking
+
+This project demonstrates an extended thinking mode implementation that enables LLMs to solve complex reasoning problems by thinking step-by-step. It's designed to improve problem-solving accuracy through deliberate reasoning.
+
+## Features
+
+- Improves model reasoning on complex problems
+- Works with models like Claude 3.7 Sonnet that support extended thinking
+- Solves problems that direct prompting often fails on
+- Provides detailed reasoning traces for verification
+
+## Getting Started
+
+1. Install the required packages:
+```bash
+pip install -r requirements.txt
+```
+
+2. Set up your API key:
+```bash
+export ANTHROPIC_API_KEY="your-api-key-here"
+```
+
+3. Run a test problem to see thinking mode in action:
+```bash
+python main.py
+```
+
+4. Try your own reasoning problem:
+```bash
+python main.py --"Your complex reasoning problem here"
+```
+
+## How It Works
+
+The implementation uses a self-looping Chain of Thought node that allows an LLM to think through complex problems step by step:
+
+```mermaid
+flowchart LR
+    cot[ChainOfThoughtNode] -->|"continue"| cot
+```
+
+Each time the node loops, it:
+1. Reads the problem and previous thoughts
+2. Generates the next thought or final solution
+3. Decides whether more thinking is needed
+
+This approach helps LLMs solve problems that would be difficult with a single-pass approach.
+
+
+## Example Thinking Process
+
+Example Problem from [Quant Interview](https://www.youtube.com/watch?v=SCP7JptxPU0):
+
+```
+You work at a shoe factory. In front of you, there are three pairs of shoes (six individual shoes) with the following sizes: two size 4s, two size 5s, and two size 6s. The factory defines an "acceptable pair" as two shoes that differ in size by a maximum of one size (e.g., a size 5 and a size 6 would be an acceptable pair). If you close your eyes and randomly pick three pairs of shoes without replacement, what is the probability that you end up drawing three acceptable pairs?
+```
+
+Below is an example of how Claude 3.7 Sonnet  to solve this complex problem, and get the correct result:
+
+```
+========================
+All structured answers: ['0.333', '0.333', '0.333', '0.6', '0.333']
+Majority vote => 0.333
+Frequency => 4
+========================
+
+=== Final Answer ===
+0.333
+====================
+```
+
+## Files
+
+- [`main.py`](./main.py): Implementation of the ...
+- [`utils.py`](./utils.py): Simple wrapper for calling the Anthropic model
+ 

cookbook/pocketflow-majority-vote/main.py

@@ -0,0 +1,67 @@
+# main.py
+from pocketflow import BatchNode, Flow
+import collections
+from utils import call_llm
+import yaml
+class MajorityVoteNode(BatchNode):
+    def prep(self, shared):
+        question = shared.get("question", "(No question provided)")
+        attempts_count = shared.get("num_tries", 3)
+        return [question for _ in range(attempts_count)]
+
+    def exec(self, single_question: str):
+        prompt = f"""
+You are a helpful assistant. Please answer the user's question below.
+Question: {single_question}
+
+Return strictly using the following YAML structure:
+```yaml
+thinking: |
+    (Your thinking process here)
+answer: 0.123 # Final answer as a decimal with 3 decimal places
+```"""
+        raw_response = call_llm(prompt)
+        yaml_part = raw_response.split("```yaml")[1].split("```")[0].strip()
+        parsed = yaml.safe_load(yaml_part)
+
+        # Validate we have at least 'answer' field
+        if not isinstance(parsed, dict) or 'answer' not in parsed:
+            raise RuntimeError(f"Missing 'answer' in YAML: {parsed}")
+
+        # Return only the 'answer' field for the majority vote.
+        return str(parsed['answer'])
+    
+    def exec_fallback(self, prep_res, exc):
+        return None
+
+    def post(self, shared, prep_res, exec_res_list):
+        # Count frequency for non-None answers
+        exec_res_list = [res for res in exec_res_list if res is not None]
+        counter = collections.Counter(exec_res_list)
+        best_answer, freq = counter.most_common(1)[0]
+
+        # Store final
+        shared["majority_answer"] = best_answer
+
+        print("========================")
+        print("All structured answers:", exec_res_list)
+        print("Majority vote =>", best_answer)
+        print("Frequency =>", freq)
+        print("========================")
+
+        # End the flow
+        return "end"
+
+if __name__ == "__main__":
+    shared = {
+        "question": """You work at a shoe factory. In front of you, there are three pairs of shoes (six individual shoes) with the following sizes: two size 4s, two size 5s, and two size 6s. The factory defines an "acceptable pair" as two shoes that differ in size by a maximum of one size (e.g., a size 5 and a size 6 would be an acceptable pair). If you close your eyes and randomly pick three pairs of shoes without replacement, what is the probability that you end up drawing three acceptable pairs?""",
+        "num_tries": 5
+    }
+
+    majority_node = MajorityVoteNode()
+    flow = Flow(start=majority_node)
+    flow.run(shared)
+
+    print("\n=== Final Answer ===")
+    print(shared["majority_answer"])
+    print("====================")

cookbook/pocketflow-majority-vote/requirements.txt

@@ -0,0 +1,2 @@
+pocketflow>=0.0.1
+anthropic>=0.15.0   # For Claude API access 

cookbook/pocketflow-majority-vote/utils.py

@@ -0,0 +1,20 @@
+from anthropic import Anthropic
+import os
+
+def call_llm(prompt):
+    client = Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY", "your-api-key"))
+    response = client.messages.create(
+        model="claude-3-7-sonnet-20250219",
+        max_tokens=10000,
+        messages=[
+            {"role": "user", "content": prompt}
+        ]
+    )
+    return response.content[0].text
+
+if __name__ == "__main__":
+    print("## Testing call_llm")
+    prompt = "In a few words, what is the meaning of life?"
+    print(f"## Prompt: {prompt}")
+    response = call_llm(prompt)
+    print(f"## Response: {response}")