┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│   Ingest    │────▶│   Retrieve  │────▶│   Generate  │
│  Documents  │     │   Context   │     │   Response  │
└─────────────┘     └─────────────┘     └─────────────┘
      │                   │                   │
      ▼                   ▼                   ▼
 ┌─────────┐       ┌───────────┐       ┌───────────┐
 │ Chunking│       │  Vector   │       │    LLM    │
 │Embedding│       │  Search   │       │  + Context│
 └─────────┘       └───────────┘       └───────────┘

undefined

# Semantic chunking (preserves meaning)
SEMANTIC = "semantic"      # Split on paragraphs/sections

# Recursive splitting (tries multiple separators)
RECURSIVE = "recursive"    # ["\n\n", "\n", " ", ""]

# Document-aware (respects structure)
DOCUMENT_AWARE = "document_aware"  # Headers, lists, etc.

undefined

undefined

undefined

undefined

# Reciprocal Rank Fusion
return rrf_merge(semantic_results, keyword_results, alpha)

undefined

RAG_PROMPT_TEMPLATE = """
Answer the user's question based ONLY on the following context.
If the context doesn't contain enough information, say "I don't have enough information to answer that."

Context:
{context}

Question: {question}

Answer:"""

def generate_with_rag(question: str):
    # Retrieve
    context_docs = hybrid_search(question, top_k=5)
    context = "\n\n".join([doc.content for doc in context_docs])

    # Generate
    prompt = RAG_PROMPT_TEMPLATE.format(
        context=context,
        question=question
    )

    response = llm.generate(prompt)

    # Return with citations
    return {
        "answer": response,
        "sources": [doc.metadata for doc in context_docs]
    }

Thought: I need to search for information about X
Action: search("X")
Observation: [search results]
Thought: Based on the results, I should...
Action: calculate(...)
Observation: [calculation result]
Thought: I now have enough information
Action: final_answer("The answer is...")

REACT_PROMPT = """
You are an AI assistant that can use tools to answer questions.

Available tools:
{tools_description}

Use this format:
Thought: [your reasoning about what to do next]
Action: [tool_name(arguments)]
Observation: [tool result - this will be filled in]
... (repeat Thought/Action/Observation as needed)
Thought: I have enough information to answer
Final Answer: [your final response]

Question: {question}
"""

class ReActAgent:
    def __init__(self, tools: list, llm):
        self.tools = {t.name: t for t in tools}
        self.llm = llm
        self.max_iterations = 10

    def run(self, question: str) -> str:
        prompt = REACT_PROMPT.format(
            tools_description=self._format_tools(),
            question=question
        )

        for _ in range(self.max_iterations):
            response = self.llm.generate(prompt)

            if "Final Answer:" in response:
                return self._extract_final_answer(response)

            action = self._parse_action(response)
            observation = self._execute_tool(action)
            prompt += f"\nObservation: {observation}\n"

        return "Max iterations reached"

undefined

    while True:
        response = self.llm.chat(
            messages=messages,
            tools=TOOLS,
            tool_choice="auto"
        )

        if response.tool_calls:
            for tool_call in response.tool_calls:
                result = self._execute_tool(
                    tool_call.name,
                    tool_call.arguments
                )
                messages.append({
                    "role": "tool",
                    "tool_call_id": tool_call.id,
                    "content": str(result)
                })
        else:
            return response.content

undefined

class PlanAndExecuteAgent:
    """
    1. Create a plan (list of steps)
    2. Execute each step
    3. Replan if needed
    """

    def run(self, task: str) -> str:
        # Planning phase
        plan = self.planner.create_plan(task)
        # Returns: ["Step 1: ...", "Step 2: ...", ...]

        results = []
        for step in plan:
            # Execute each step
            result = self.executor.execute(step, context=results)
            results.append(result)

            # Check if replan needed
            if self._needs_replan(task, results):
                new_plan = self.planner.replan(
                    task,
                    completed=results,
                    remaining=plan[len(results):]
                )
                plan = new_plan

        # Synthesize final answer
        return self.synthesizer.summarize(task, results)

class AgentTeam:
    """
    Specialized agents collaborating on complex tasks
    """

    def __init__(self):
        self.agents = {
            "researcher": ResearchAgent(),
            "analyst": AnalystAgent(),
            "writer": WriterAgent(),
            "critic": CriticAgent()
        }
        self.coordinator = CoordinatorAgent()

    def solve(self, task: str) -> str:
        # Coordinator assigns subtasks
        assignments = self.coordinator.decompose(task)

        results = {}
        for assignment in assignments:
            agent = self.agents[assignment.agent]
            result = agent.execute(
                assignment.subtask,
                context=results
            )
            results[assignment.id] = result

        # Critic reviews
        critique = self.agents["critic"].review(results)

        if critique.needs_revision:
            # Iterate with feedback
            return self.solve_with_feedback(task, results, critique)

        return self.coordinator.synthesize(results)

class PromptTemplate:
    def __init__(self, template: str, variables: list[str]):
        self.template = template
        self.variables = variables

    def format(self, **kwargs) -> str:
        # Validate all variables provided
        missing = set(self.variables) - set(kwargs.keys())
        if missing:
            raise ValueError(f"Missing variables: {missing}")

        return self.template.format(**kwargs)

    def with_examples(self, examples: list[dict]) -> str:
        """Add few-shot examples"""
        example_text = "\n\n".join([
            f"Input: {ex['input']}\nOutput: {ex['output']}"
            for ex in examples
        ])
        return f"{example_text}\n\n{self.template}"

undefined

class PromptRegistry:
    def __init__(self, db):
        self.db = db

    def register(self, name: str, template: str, version: str):
        """Store prompt with version"""
        self.db.save({
            "name": name,
            "template": template,
            "version": version,
            "created_at": datetime.now(),
            "metrics": {}
        })

    def get(self, name: str, version: str = "latest") -> str:
        """Retrieve specific version"""
        return self.db.get(name, version)

    def ab_test(self, name: str, user_id: str) -> str:
        """Return variant based on user bucket"""
        variants = self.db.get_all_versions(name)
        bucket = hash(user_id) % len(variants)
        return variants[bucket]

    def record_outcome(self, prompt_id: str, outcome: dict):
        """Track prompt performance"""
        self.db.update_metrics(prompt_id, outcome)

class PromptChain:
    """
    Chain prompts together, passing output as input to next
    """

    def __init__(self, steps: list[dict]):
        self.steps = steps

    def run(self, initial_input: str) -> dict:
        context = {"input": initial_input}
        results = []

        for step in self.steps:
            prompt = step["prompt"].format(**context)
            output = llm.generate(prompt)

            # Parse output if needed
            if step.get("parser"):
                output = step["parser"](output)

            context[step["output_key"]] = output
            results.append({
                "step": step["name"],
                "output": output
            })

        return {
            "final_output": context[self.steps[-1]["output_key"]],
            "intermediate_results": results
        }

---

LLM_METRICS = {
    # Performance
    "latency_p50": "50th percentile response time",
    "latency_p99": "99th percentile response time",
    "tokens_per_second": "Generation speed",

    # Quality
    "user_satisfaction": "Thumbs up/down ratio",
    "task_completion": "% tasks completed successfully",
    "hallucination_rate": "% responses with factual errors",

    # Cost
    "cost_per_request": "Average $ per API call",
    "tokens_per_request": "Average tokens used",
    "cache_hit_rate": "% requests served from cache",

    # Reliability
    "error_rate": "% failed requests",
    "timeout_rate": "% requests that timed out",
    "retry_rate": "% requests needing retry"
}

import logging
from opentelemetry import trace

tracer = trace.get_tracer(__name__)

class LLMLogger:
    def log_request(self, request_id: str, data: dict):
        """Log LLM request for debugging and analysis"""
        log_entry = {
            "request_id": request_id,
            "timestamp": datetime.now().isoformat(),
            "model": data["model"],
            "prompt": data["prompt"][:500],  # Truncate for storage
            "prompt_tokens": data["prompt_tokens"],
            "temperature": data.get("temperature", 1.0),
            "user_id": data.get("user_id"),
        }
        logging.info(f"LLM_REQUEST: {json.dumps(log_entry)}")

    def log_response(self, request_id: str, data: dict):
        """Log LLM response"""
        log_entry = {
            "request_id": request_id,
            "completion_tokens": data["completion_tokens"],
            "total_tokens": data["total_tokens"],
            "latency_ms": data["latency_ms"],
            "finish_reason": data["finish_reason"],
            "cost_usd": self._calculate_cost(data),
        }
        logging.info(f"LLM_RESPONSE: {json.dumps(log_entry)}")

response = llm.generate(prompt)

span.set_attribute("response.length", len(response))
span.set_attribute("tokens.total", response.usage.total_tokens)

return response.content

undefined

class LLMEvaluator:
    """
    Evaluate LLM outputs for quality
    """

    def evaluate_response(self,
                          question: str,
                          response: str,
                          ground_truth: str = None) -> dict:
        scores = {}

        # Relevance: Does it answer the question?
        scores["relevance"] = self._score_relevance(question, response)

        # Coherence: Is it well-structured?
        scores["coherence"] = self._score_coherence(response)

        # Groundedness: Is it based on provided context?
        scores["groundedness"] = self._score_groundedness(response)

        # Accuracy: Does it match ground truth?
        if ground_truth:
            scores["accuracy"] = self._score_accuracy(response, ground_truth)

        # Harmfulness: Is it safe?
        scores["safety"] = self._score_safety(response)

        return scores

    def run_benchmark(self, test_cases: list[dict]) -> dict:
        """Run evaluation on test set"""
        results = []
        for case in test_cases:
            response = llm.generate(case["prompt"])
            scores = self.evaluate_response(
                question=case["prompt"],
                response=response,
                ground_truth=case.get("expected")
            )
            results.append(scores)

        return self._aggregate_scores(results)

import hashlib
from functools import lru_cache

class LLMCache:
    def __init__(self, redis_client, ttl_seconds=3600):
        self.redis = redis_client
        self.ttl = ttl_seconds

    def _cache_key(self, prompt: str, model: str, **kwargs) -> str:
        """Generate deterministic cache key"""
        content = f"{model}:{prompt}:{json.dumps(kwargs, sort_keys=True)}"
        return hashlib.sha256(content.encode()).hexdigest()

    def get_or_generate(self, prompt: str, model: str, **kwargs) -> str:
        key = self._cache_key(prompt, model, **kwargs)

        # Check cache
        cached = self.redis.get(key)
        if cached:
            return cached.decode()

        # Generate
        response = llm.generate(prompt, model=model, **kwargs)

        # Cache (only cache deterministic outputs)
        if kwargs.get("temperature", 1.0) == 0:
            self.redis.setex(key, self.ttl, response)

        return response

import time
from tenacity import retry, wait_exponential, stop_after_attempt

class RateLimiter:
    def __init__(self, requests_per_minute: int):
        self.rpm = requests_per_minute
        self.timestamps = []

    def acquire(self):
        """Wait if rate limit would be exceeded"""
        now = time.time()

        # Remove old timestamps
        self.timestamps = [t for t in self.timestamps if now - t < 60]

        if len(self.timestamps) >= self.rpm:
            sleep_time = 60 - (now - self.timestamps[0])
            time.sleep(sleep_time)

        self.timestamps.append(time.time())

undefined

class LLMWithFallback:
    def __init__(self, primary: str, fallbacks: list[str]):
        self.primary = primary
        self.fallbacks = fallbacks

    def generate(self, prompt: str, **kwargs) -> str:
        models = [self.primary] + self.fallbacks

        for model in models:
            try:
                return llm.generate(prompt, model=model, **kwargs)
            except (RateLimitError, APIError) as e:
                logging.warning(f"Model {model} failed: {e}")
                continue

        raise AllModelsFailedError("All models exhausted")

---