from praisonaiagents import Agent

agent = Agent(
    name="compress-agent",
    instructions="Compress conversation history to save context space.",
    compress_context=True,
)
agent.start("Summarise older messages to free context window space.")

compressor = ContextCompressor(
    deduplicate=True,
    similarity_threshold=0.9,
)

result = compressor.compress(chunks)

compressor = ContextCompressor(
    max_tokens=2000,
    extraction_method="query_focused",
)

result = compressor.compress(
    chunks,
    query="How do I authenticate with the API?",
)

compressor = ContextCompressor(
    max_tokens=1000,
    truncation_strategy="end",  # or "start", "middle"
)

result = compressor.compress(chunks)

compressor = ContextCompressor(
    max_tokens=500,
    use_llm_summarization=True,
    summarization_model="gpt-4o-mini",
)

result = compressor.compress(chunks, query=query)

from dataclasses import dataclass
from typing import List

@dataclass
class CompressionResult:
    chunks: List[str]
    original_tokens: int
    compressed_tokens: int
    method_used: str
    metadata: dict = None

result = compressor.compress(chunks, query=query)

print(f"Method used: {result.method_used}")
print(f"Original: {result.original_tokens} tokens")
print(f"Compressed: {result.compressed_tokens} tokens")
print(f"Ratio: {result.compressed_tokens / result.original_tokens:.2%}")

# Use compressed chunks
for chunk in result.chunks:
    print(chunk[:200] + "...")

# Search with compression
praisonai knowledge search "query" --compress

# Specify compression ratio
praisonai knowledge search "query" --compress --compression-ratio 0.3

# Specify max tokens
praisonai knowledge search "query" --compress --max-context-tokens 2000

# Verbose output
praisonai knowledge search "query" --compress --verbose

from praisonaiagents import Agent

agent = Agent(
    name="CompressedRetriever",
    instructions="Answer questions using the knowledge base.",
    knowledge={
        "sources": ["./docs"],
        "retrieval_k": 10,
    }
)

response = agent.chat("Summarize the authentication methods")

class ContextCompressor:
    def __init__(
        self,
        max_tokens: int = 4000,
        target_ratio: float = 0.5,
        deduplicate: bool = True,
        similarity_threshold: float = 0.9,
        use_llm_summarization: bool = False,
        summarization_model: str = "gpt-4o-mini",
    ):
        """Initialize context compressor."""
    
    def compress(
        self,
        chunks: List[str],
        query: str = None,
    ) -> CompressionResult:
        """Compress chunks to fit token budget."""
    
    def estimate_tokens(self, text: str) -> int:
        """Estimate token count for text."""

@dataclass
class CompressionResult:
    chunks: List[str]
    original_tokens: int
    compressed_tokens: int
    method_used: str
    metadata: dict = None