from langchain.memory import ConversationSummaryBufferMemory
from langchain_anthropic import ChatAnthropic
from anthropic import Anthropic

undefined

from anthropic import Anthropic

client = Anthropic(api_key="your-api-key")

class ProgressiveCompressor:
    def __init__(self, thresholds=[0.70, 0.85, 0.95]):
        self.thresholds = thresholds
        self.messages = []
        self.max_tokens = 200000  # Claude context window

    def add_message(self, role: str, content: str):
        self.messages.append({"role": role, "content": content})

        # Check if compression needed
        current_usage = self._estimate_tokens()
        usage_ratio = current_usage / self.max_tokens

        if usage_ratio >= self.thresholds[0]:
            self._compress(level=self._get_compression_level(usage_ratio))

    def _estimate_tokens(self):
        return sum(len(m["content"]) // 4 for m in self.messages)

    def _get_compression_level(self, ratio):
        for i, threshold in enumerate(self.thresholds):
            if ratio < threshold:
                return i
        return len(self.thresholds)

    def _compress(self, level: int):
        """Apply compression based on severity level."""
        if level == 1:  # 70% threshold: Light compression
            self._remove_redundant_messages()
        elif level == 2:  # 85% threshold: Medium compression
            self._summarize_old_messages(keep_recent=10)
        else:  # 95% threshold: Aggressive compression
            self._summarize_old_messages(keep_recent=5)

    def _remove_redundant_messages(self):
        """Remove duplicate or low-value messages."""
        # Implementation: Use semantic deduplication
        pass

    def _summarize_old_messages(self, keep_recent: int):
        """Summarize older messages, keep recent ones verbatim."""
        if len(self.messages) <= keep_recent:
            return

        # Messages to summarize
        to_summarize = self.messages[:-keep_recent]
        recent = self.messages[-keep_recent:]

        # Generate summary
        conversation_text = "\n\n".join([
            f"{m['role'].upper()}: {m['content']}"
            for m in to_summarize
        ])

        response = client.messages.create(
            model="claude-3-5-haiku-20241022",
            max_tokens=500,
            messages=[{
                "role": "user",
                "content": f"Summarize this conversation:\n\n{conversation_text}"
            }]
        )

        # Replace old messages with summary
        summary = {
            "role": "system",
            "content": f"[Summary]\n{response.content[0].text}"
        }
        self.messages = [summary] + recent

undefined

from anthropic import Anthropic

client = Anthropic(api_key="your-api-key")

---

Context Usage    Action                     Technique
─────────────────────────────────────────────────────────
0-70%           No compression             Store verbatim
70-85%          Light compression          Remove redundancy
85-95%          Medium compression         Summarize old messages
95-100%         Aggressive compression     Hierarchical + RAG

from sklearn.feature_extraction.text import TfidfVectorizer
import numpy as np

def extractive_compress(messages: list, compression_ratio: float = 0.3):
    """Extract most important messages using TF-IDF scoring."""
    texts = [msg['content'] for msg in messages]

    # Calculate TF-IDF scores
    vectorizer = TfidfVectorizer()
    tfidf_matrix = vectorizer.fit_transform(texts)
    scores = np.array(tfidf_matrix.sum(axis=1)).flatten()

    # Select top messages
    n_keep = max(1, int(len(messages) * compression_ratio))
    top_indices = sorted(np.argsort(scores)[-n_keep:])

    return [messages[i] for i in top_indices]

from anthropic import Anthropic

def abstractive_compress(messages: list, client: Anthropic):
    """Generate semantic summary using Claude."""
    conversation_text = "\n\n".join([
        f"{msg['role'].upper()}: {msg['content']}"
        for msg in messages
    ])

    response = client.messages.create(
        model="claude-3-5-sonnet-20241022",
        max_tokens=500,
        messages=[{
            "role": "user",
            "content": f"""Summarize this conversation, preserving:
1. Key decisions made
2. Important context and facts
3. Unresolved questions
4. Action items

Conversation:
{conversation_text}

Summary (aim for 1/5 the original length):"""
        }]
    )

    return {
        "role": "assistant",
        "content": f"[Summary]\n{response.content[0].text}"
    }

Level 0 (Raw):    [Msg1][Msg2][Msg3][Msg4][Msg5][Msg6][Msg7][Msg8]
Level 1 (Chunk):  [Summary1-2]  [Summary3-4]  [Summary5-6]  [Summary7-8]
Level 2 (Group):  [Summary1-4]              [Summary5-8]
Level 3 (Session): [Overall Session Summary]

from anthropic import Anthropic
from typing import List, Dict

class HierarchicalMemory:
    def __init__(self, client: Anthropic, chunk_size: int = 10):
        self.client = client
        self.chunk_size = chunk_size
        self.levels: List[List[Dict]] = [[]]  # Level 0 = raw messages

    def add_message(self, message: Dict):
        """Add message and trigger summarization if needed."""
        self.levels[0].append(message)

        if len(self.levels[0]) >= self.chunk_size * 2:
            self._summarize_level(0)

    def _summarize_level(self, level: int):
        """Summarize a level into the next higher level."""
        messages = self.levels[level]

        # Ensure next level exists
        while len(self.levels) <= level + 1:
            self.levels.append([])

        # Summarize first chunk
        chunk = messages[:self.chunk_size]
        summary = self._generate_summary(chunk, level)

        # Move to next level
        self.levels[level + 1].append(summary)
        self.levels[level] = messages[self.chunk_size:]

        # Recursively check if next level needs summarization
        if len(self.levels[level + 1]) >= self.chunk_size * 2:
            self._summarize_level(level + 1)

    def _generate_summary(self, messages: List[Dict], level: int) -> Dict:
        """Generate summary for a chunk."""
        conversation_text = "\n\n".join([
            f"{msg['role'].upper()}: {msg['content']}"
            for msg in messages
        ])

        response = self.client.messages.create(
            model="claude-3-5-haiku-20241022",
            max_tokens=300,
            messages=[{
                "role": "user",
                "content": f"Summarize this Level {level} conversation chunk:\n\n{conversation_text}"
            }]
        )

        return {
            "role": "system",
            "content": f"[L{level+1} Summary] {response.content[0].text}",
            "level": level + 1
        }

    def get_context(self, max_tokens: int = 4000) -> List[Dict]:
        """Retrieve context within token budget."""
        context = []
        token_count = 0

        # Prioritize recent raw messages
        for msg in reversed(self.levels[0]):
            msg_tokens = len(msg['content']) // 4
            if token_count + msg_tokens > max_tokens * 0.6:
                break
            context.insert(0, msg)
            token_count += msg_tokens

        # Add summaries from higher levels
        for level in range(1, len(self.levels)):
            for summary in self.levels[level]:
                summary_tokens = len(summary['content']) // 4
                if token_count + summary_tokens > max_tokens:
                    break
                context.insert(0, summary)
                token_count += summary_tokens

        return context

from anthropic import Anthropic

class RollingMemory:
    def __init__(self, client: Anthropic, window_size: int = 10, compress_threshold: int = 15):
        self.client = client
        self.window_size = window_size
        self.compress_threshold = compress_threshold
        self.rolling_summary = None
        self.recent_messages = []

    def add_message(self, message: dict):
        self.recent_messages.append(message)

        if len(self.recent_messages) >= self.compress_threshold:
            self._compress()

    def _compress(self):
        """Compress older messages into rolling summary."""
        messages_to_compress = self.recent_messages[:-self.window_size]

        parts = []
        if self.rolling_summary:
            parts.append(f"Existing summary:\n{self.rolling_summary}")

        parts.append("\nNew messages:\n" + "\n\n".join([
            f"{msg['role']}: {msg['content']}"
            for msg in messages_to_compress
        ]))

        response = self.client.messages.create(
            model="claude-3-5-haiku-20241022",
            max_tokens=400,
            messages=[{
                "role": "user",
                "content": "\n".join(parts) + "\n\nUpdate the summary:"
            }]
        )

        self.rolling_summary = response.content[0].text
        self.recent_messages = self.recent_messages[-self.window_size:]

    def get_context(self):
        context = []
        if self.rolling_summary:
            context.append({
                "role": "system",
                "content": f"[Summary]\n{self.rolling_summary}"
            })
        context.extend(self.recent_messages)
        return context

from anthropic import Anthropic
from openai import OpenAI
import chromadb

class RAGMemory:
    def __init__(self, anthropic_client: Anthropic, openai_client: OpenAI):
        self.anthropic = anthropic_client
        self.openai = openai_client

        # Initialize vector store
        self.chroma = chromadb.Client()
        self.collection = self.chroma.create_collection(
            name="conversation",
            metadata={"hnsw:space": "cosine"}
        )

        self.recent_messages = []
        self.recent_window = 5
        self.message_counter = 0

    def add_message(self, message: dict):
        """Add to recent memory and vector store."""
        self.recent_messages.append(message)

        if len(self.recent_messages) > self.recent_window:
            old_msg = self.recent_messages.pop(0)
            self._store_in_vectordb(old_msg)

    def _store_in_vectordb(self, message: dict):
        """Archive to vector database."""
        # Generate embedding
        response = self.openai.embeddings.create(
            model="text-embedding-3-small",
            input=message['content']
        )

        self.collection.add(
            embeddings=[response.data[0].embedding],
            documents=[message['content']],
            metadatas=[{"role": message['role']}],
            ids=[f"msg_{self.message_counter}"]
        )
        self.message_counter += 1

    def retrieve_context(self, query: str, max_tokens: int = 4000):
        """Retrieve relevant context using RAG."""
        context = []
        token_count = 0

        # 1. Recent messages (short-term memory)
        for msg in self.recent_messages:
            context.append(msg)
            token_count += len(msg['content']) // 4

        # 2. Retrieve relevant historical context
        if token_count < max_tokens:
            query_embedding = self.openai.embeddings.create(
                model="text-embedding-3-small",
                input=query
            )

            n_results = min(10, (max_tokens - token_count) // 100)
            results = self.collection.query(
                query_embeddings=[query_embedding.data[0].embedding],
                n_results=n_results
            )

            for i, doc in enumerate(results['documents'][0]):
                if token_count + len(doc) // 4 > max_tokens:
                    break

                metadata = results['metadatas'][0][i]
                context.insert(0, {
                    "role": metadata['role'],
                    "content": f"[Retrieved] {doc}"
                })
                token_count += len(doc) // 4

        return context

from sklearn.cluster import KMeans
from openai import OpenAI
import numpy as np

class ClusteredMemory:
    def __init__(self, openai_client: OpenAI, n_clusters: int = 5):
        self.client = openai_client
        self.n_clusters = n_clusters
        self.messages = []
        self.embeddings = []

    def add_messages(self, messages: list):
        for msg in messages:
            self.messages.append(msg)

            response = self.client.embeddings.create(
                model="text-embedding-3-small",
                input=msg['content']
            )
            self.embeddings.append(response.data[0].embedding)

    def compress_by_clustering(self):
        """Cluster messages and return representatives."""
        if len(self.messages) < self.n_clusters:
            return self.messages

        embeddings_array = np.array(self.embeddings)
        kmeans = KMeans(n_clusters=self.n_clusters, random_state=42)
        labels = kmeans.fit_predict(embeddings_array)

        # Select message closest to each centroid
        compressed = []
        for cluster_id in range(self.n_clusters):
            cluster_indices = np.where(labels == cluster_id)[0]
            centroid = kmeans.cluster_centers_[cluster_id]
            cluster_embeddings = embeddings_array[cluster_indices]
            distances = np.linalg.norm(cluster_embeddings - centroid, axis=1)
            closest_idx = cluster_indices[np.argmin(distances)]

            compressed.append({
                **self.messages[closest_idx],
                "cluster_id": int(cluster_id),
                "cluster_size": len(cluster_indices)
            })

        return compressed

from openai import OpenAI
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity

class SemanticDeduplicator:
    def __init__(self, openai_client: OpenAI, similarity_threshold: float = 0.85):
        self.client = openai_client
        self.threshold = similarity_threshold

    def deduplicate(self, messages: list):
        """Remove semantically similar messages."""
        if len(messages) <= 1:
            return messages

        # Generate embeddings
        embeddings = []
        for msg in messages:
            response = self.client.embeddings.create(
                model="text-embedding-3-small",
                input=msg['content']
            )
            embeddings.append(response.data[0].embedding)

        embeddings_array = np.array(embeddings)
        similarity_matrix = cosine_similarity(embeddings_array)

        # Mark unique messages
        keep_indices = []
        for i in range(len(messages)):
            is_unique = True
            for j in keep_indices:
                if similarity_matrix[i][j] > self.threshold:
                    is_unique = False
                    break

            if is_unique:
                keep_indices.append(i)

        return [messages[i] for i in keep_indices]

import re

class MessagePrioritizer:
    def score_message(self, msg: dict, index: int, total: int) -> float:
        """Calculate composite importance score."""
        scores = []

        # Length score (longer = more info)
        scores.append(min(len(msg['content']) / 500, 1.0))

        # Question score
        if msg['role'] == 'user':
            scores.append(min(msg['content'].count('?') * 0.5, 1.0))

        # Entity score (capitalized words)
        entities = len(re.findall(r'\b[A-Z][a-z]+', msg['content']))
        scores.append(min(entities / 10, 1.0))

        # Recency score (linear decay)
        scores.append(index / max(total - 1, 1))

        # Role score
        scores.append(0.6 if msg['role'] == 'user' else 0.4)

        return sum(scores) / len(scores)

    def prioritize(self, messages: list, target_count: int):
        """Select top N messages by priority."""
        scored = [
            (msg, self.score_message(msg, i, len(messages)), i)
            for i, msg in enumerate(messages)
        ]

        scored.sort(key=lambda x: x[1], reverse=True)
        top_messages = scored[:target_count]
        top_messages.sort(key=lambda x: x[2])  # Restore chronological order

        return [msg for msg, score, idx in top_messages]