mem-llm 1.0.2__py3-none-any.whl → 2.1.0__py3-none-any.whl

mem_llm-2.1.0.dist-info/RECORD

@@ -0,0 +1,40 @@
+mem_llm/__init__.py,sha256=uG8swMB5oVhnI-vPhfn5aWWL4BIcWNZv5tolA3CDkAk,3133
+mem_llm/api_server.py,sha256=n2Lu9lj_RSMRO-p81AnFB4fS0gbnshFKqfWtL3kYReM,20874
+mem_llm/base_llm_client.py,sha256=RbX9QVdHGT0TRoCTGB_qyMzjosg7Q54L1eLdzzj7pEE,6292
+mem_llm/builtin_tools.py,sha256=HC0pu3JoBv_yqI2fIJTIsmGNtzGQthUbjlraKoyFyu8,8567
+mem_llm/builtin_tools_async.py,sha256=kPHVgvshfn6mwasYmUDgIfdrfvXLeUr5POs7IexAfg4,4686
+mem_llm/cli.py,sha256=CV1BprDNPIPZrMLahW0WPrZ03NwoxW46QpJO2FnPqBQ,8658
+mem_llm/config.yaml.example,sha256=Bo2hfPC9ltqnCyUdvM-XpN5gigTlxoN-5yr6X2w1saM,913
+mem_llm/config_from_docs.py,sha256=uB1GEQqhzTWLKumgz4jHG65QDlExUHOgsdj7rS7W0lg,4970
+mem_llm/config_manager.py,sha256=xANKAinOO8w_HGeeS7MqMzTh18H9sa078sRrFfHbOG8,7251
+mem_llm/conversation_summarizer.py,sha256=yCG2pKrAJf7xjaG6DPXL0i9eesMZnnzjKTpuyLHMTPQ,12509
+mem_llm/data_export_import.py,sha256=gQIdD0hBY23qcRvx139yE15RWHXPinL_EoRNY7iabj0,22592
+mem_llm/dynamic_prompt.py,sha256=8H99QVDRJSVtGb_o4sdEPnG1cJWuer3KiD-nuL1srTA,10244
+mem_llm/knowledge_loader.py,sha256=oSNhfYYcx7DlZLVogxnbSwaIydq_Q3__RDJFeZR2XVw,2699
+mem_llm/llm_client.py,sha256=GvOwzlTJ2ogpe4y6BmFPpXxJNN1G7B6cgeGUc_0Ngy0,8705
+mem_llm/llm_client_factory.py,sha256=ncwxr3T3aqZVCiGw3GpMRq8kIaqf73BIxN9gvRTo2MA,8728
+mem_llm/logger.py,sha256=dZUmhGgFXtDsDBU_D4kZlJeMp6k-VNPaBcyTt7rZYKE,4507
+mem_llm/mem_agent.py,sha256=rXVdSY3XaZ7sV4-elXWN4J7rUSFYu4Jd5jWQeOCDFcc,68074
+mem_llm/memory_db.py,sha256=yY_afim1Rpk3mOz-qI5WvDDAwWoVd-NucBMBLVUNpwg,21711
+mem_llm/memory_manager.py,sha256=BtzI1o-NYZXMkZHtc36xEZizgNn9fAu6cBkGzNXa-uI,10373
+mem_llm/memory_tools.py,sha256=ARANFqu_bmL56SlV1RzTjfQsJj-Qe2QvqY0pF92hDxU,8678
+mem_llm/prompt_security.py,sha256=ehAi6aLiXj0gFFhpyjwEr8LentSTJwOQDLbINV7SaVM,9960
+mem_llm/response_metrics.py,sha256=nMegWV7brNOmptjxGJfYEqRKvAj_302MIw8Ky1PzEy8,7912
+mem_llm/retry_handler.py,sha256=z5ZcSQKbvVeNK7plagTLorvOeoYgRpQcsX3PpNqUjKM,6389
+mem_llm/thread_safe_db.py,sha256=Fq-wSn4ua1qiR6M4ZTIy7UT1IlFj5xODNExgub1blbU,10328
+mem_llm/tool_system.py,sha256=o8IGWUP1xygkq5jtZKeB9whdyq-vO3YSl_blVmlw-D4,20371
+mem_llm/vector_store.py,sha256=dDK2dyiu0WmfyE5vrAJywhEyCGf7nokEu9DxAE7MRp0,10863
+mem_llm/web_launcher.py,sha256=mEE1Wh-2u-xqgtkRW2i-zG0tizDIyJCo9BX942kA73M,3722
+mem_llm/clients/__init__.py,sha256=mDrflLaozDeRvmgq7eR30eOTIm3Au_gmmGdHLroeiAI,381
+mem_llm/clients/lmstudio_client.py,sha256=e1WZUtVYxQHvks-cun2bcEtbhb6XyX2_6p3a1gVQEcE,14777
+mem_llm/clients/ollama_client.py,sha256=ZPxNcVndOhF-Ftn2cal_c5YyI-hFoXNt53oSV9tniSA,13170
+mem_llm/web_ui/README.md,sha256=NrL8ZoRuQ_VC7srjy95RFkUDEi9gq3SCVoOp68rDZe8,852
+mem_llm/web_ui/__init__.py,sha256=n9FLiBMOguoQ7k9ZAIK4-uL-VeEwl99UMEpFMU6zOzM,105
+mem_llm/web_ui/index.html,sha256=sRwlSpiOXU4BrBDHE2eMSO6tGa2c_JS7mAdefZusAcU,20243
+mem_llm/web_ui/memory.html,sha256=9-j88P8wO5VaoeFx9l8VeOZIn-oC_HwygFQ_7-Exohk,17969
+mem_llm/web_ui/metrics.html,sha256=1uwyBKsbqkBrEJAHCH1tHDfISd3DbhJu1eOxDqqUviw,4334
+mem_llm-2.1.0.dist-info/METADATA,sha256=OEZ2n0YaFrHumYTQ35urEDTEobqq7vHDpHT3gcjKFN8,24867
+mem_llm-2.1.0.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
+mem_llm-2.1.0.dist-info/entry_points.txt,sha256=Ywhb5wtj-a_RtuZPzWW5XMSorRI-qQQ-ISTabYIldwA,85
+mem_llm-2.1.0.dist-info/top_level.txt,sha256=_fU1ML-0JwkaxWdhqpwtmTNaJEOvDMQeJdA8d5WqDn8,8
+mem_llm-2.1.0.dist-info/RECORD,,

{mem_llm-1.0.2.dist-info → mem_llm-2.1.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (76.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

mem_llm-2.1.0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+mem-llm = mem_llm.cli:main
+mem-llm-web = mem_llm.web_launcher:main

mem_llm/prompt_templates.py

@@ -1,244 +0,0 @@
-"""
-System Prompt Templates and Management
-Customizable prompt templates for different scenarios
-"""
-
-from typing import Dict, List, Optional
-from datetime import datetime
-
-
-class PromptTemplate:
-    """System prompt template"""
-    
-    def __init__(self, name: str, base_prompt: str, 
-                 variables: Optional[Dict[str, str]] = None):
-        """
-        Args:
-            name: Template name
-            base_prompt: Base prompt text (can contain variables in {variable} format)
-            variables: Default variable values
-        """
-        self.name = name
-        self.base_prompt = base_prompt
-        self.variables = variables or {}
-    
-    def render(self, **kwargs) -> str:
-        """
-        Fill template with variables
-        
-        Args:
-            **kwargs: Variable values
-            
-        Returns:
-            Generated prompt
-        """
-        merged_vars = {**self.variables, **kwargs}
-        return self.base_prompt.format(**merged_vars)
-
-
-class PromptManager:
-    """Manages prompt templates"""
-    
-    def __init__(self):
-        self.templates: Dict[str, PromptTemplate] = {}
-        self._load_default_templates()
-    
-    def _load_default_templates(self) -> None:
-        """Load default templates"""
-        
-        # 1. Customer Service
-        self.add_template(
-            name="customer_service",
-            base_prompt="""You are a professional customer service assistant for {company_name} company.
-
-Your task:
-- Approach customers kindly and helpfully
-- Remember past interactions and create context
-- Solve problems quickly and effectively
-- Redirect to human representative when necessary
-
-Communication Style:
-- Use {tone} tone
-- Give short and clear answers
-- Show empathy
-- Be professional
-
-Important Rules:
-- Never lie
-- Don't speculate on topics you don't know
-- Keep customer satisfaction in the foreground
-- Ask if there's any other help at the end of each response
-
-You are currently working on {current_date}.
-""",
-            variables={
-                "company_name": "Our Company",
-                "tone": "friendly and professional",
-                "current_date": datetime.now().strftime("%Y-%m-%d")
-            }
-        )
-        
-        # 2. Technical Support
-        self.add_template(
-            name="tech_support",
-            base_prompt="""You are a technical support expert for {product_name}.
-
-Your Expertise Areas:
-- Problem diagnosis and resolution
-- Step-by-step guidance
-- Technical documentation
-- Debugging
-
-Approach:
-- First understand the problem completely
-- Start with simple solutions
-- Explain step by step
-- Explain technical terms when necessary
-
-User Level: {user_level}
-
-Response Format:
-1. Summarize the problem
-2. List possible causes
-3. Provide solution steps
-4. Check results
-
-Log level: {log_level}
-""",
-            variables={
-                "product_name": "Our Product",
-                "user_level": "intermediate level",
-                "log_level": "detailed"
-            }
-        )
-        
-        # 3. Personal Assistant
-        self.add_template(
-            name="personal_assistant",
-            base_prompt="""Sen {user_name} için kişisel dijital asistansın.
-
-Görevlerin:
-- Günlük planlamasına yardım
-- Hatırlatmalar
-- Bilgi toplama ve özetleme
-- Öneri ve tavsiyeler
-
-Kişiselleştirme:
-- Kullanıcının tercihlerini öğren
-- Alışkanlıklarını hatırla
-- Proaktif önerilerde bulun
-- Önceliklere göre sırala
-
-Çalışma Saatleri: {work_hours}
-Zaman Dilimi: {timezone}
-Tercih Edilen Dil: {language}
-
-Yaklaşım:
-- Verimlilik odaklı
-- Minimal ve net
-- Proaktif
-- Esnek
-
-Veri Gizliliği: {privacy_level}
-""",
-            variables={
-                "user_name": "Kullanıcı",
-                "work_hours": "09:00-18:00",
-                "timezone": "Europe/Istanbul",
-                "language": "Türkçe",
-                "privacy_level": "yüksek"
-            }
-        )
-        
-        # 4. Business Customer Service
-        self.add_template(
-            name="business_customer_service",
-            base_prompt="""Sen {company_name} şirketinin kurumsal müşteri hizmetleri asistanısın.
-
-Kurumsal Müşteri Yaklaşımı:
-- Profesyonel ve çözüm odaklı
-- SLA'lara uygun hızlı yanıt
-- Teknik sorunlara derin destek
-- Çoklu kanal entegrasyonu
-
-Şirket Bilgileri:
-- Kuruluş Yılı: {founded_year}
-- Çalışan Sayısı: {employee_count}
-- Sektör: {industry}
-
-Öncelik Seviyesi: {priority_level}
-SLA Süresi: {sla_hours} saat
-""",
-            variables={
-                "company_name": "Kurumsal Şirket",
-                "founded_year": "2010",
-                "employee_count": "500+",
-                "industry": "Teknoloji",
-                "priority_level": "yüksek",
-                "sla_hours": "4"
-            }
-        )
-    
-    def add_template(self, name: str, base_prompt: str, 
-                    variables: Optional[Dict[str, str]] = None) -> None:
-        """
-        Add new template
-        
-        Args:
-            name: Template name
-            base_prompt: Prompt text
-            variables: Default variables
-        """
-        self.templates[name] = PromptTemplate(name, base_prompt, variables)
-    
-    def get_template(self, name: str) -> Optional[PromptTemplate]:
-        """
-        Get template
-        
-        Args:
-            name: Template name
-            
-        Returns:
-            PromptTemplate or None
-        """
-        return self.templates.get(name)
-    
-    def render_prompt(self, template_name: str, **kwargs) -> str:
-        """
-        Render template
-        
-        Args:
-            template_name: Template name
-            **kwargs: Variable values
-            
-        Returns:
-            Generated prompt
-        """
-        template = self.get_template(template_name)
-        if template:
-            return template.render(**kwargs)
-        raise ValueError(f"Template '{template_name}' not found")
-    
-    def list_templates(self) -> List[str]:
-        """List available templates"""
-        return list(self.templates.keys())
-    
-    def get_template_variables(self, template_name: str) -> Dict[str, str]:
-        """
-        Return template variables
-        
-        Args:
-            template_name: Template name
-            
-        Returns:
-            Variables dictionary
-        """
-        template = self.get_template(template_name)
-        if template:
-            return template.variables.copy()
-        return {}
-
-
-# Global instance for ready use
-prompt_manager = PromptManager()
-

mem_llm-1.0.2.dist-info/METADATA

@@ -1,382 +0,0 @@
-Metadata-Version: 2.4
-Name: mem-llm
-Version: 1.0.2
-Summary: Memory-enabled AI assistant with local LLM support
-Home-page: https://github.com/emredeveloper/Mem-LLM
-Author: C. Emre Karataş
-Author-email: karatasqemre@gmail.com
-Project-URL: Bug Reports, https://github.com/emredeveloper/Mem-LLM/issues
-Project-URL: Source, https://github.com/emredeveloper/Mem-LLM
-Keywords: llm ai memory agent chatbot ollama local
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: requests>=2.31.0
-Requires-Dist: pyyaml>=6.0.1
-Provides-Extra: dev
-Requires-Dist: pytest>=7.4.0; extra == "dev"
-Requires-Dist: black>=23.7.0; extra == "dev"
-Requires-Dist: flake8>=6.1.0; extra == "dev"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: keywords
-Dynamic: project-url
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
-# 🧠 Mem-Agent: Memory-Enabled Mini Assistant
-
-<div align="center">
-
-[![Python](https://img.shields.io/badge/Python-3.8%2B-blue.svg)](https://www.python.org/downloads/)
-[![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-[![Ollama](https://img.shields.io/badge/Ollama-Compatible-orange.svg)](https://ollama.ai/)
-
-**A local AI assistant that remembers user interactions and responds with context awareness using a lightweight 4-billion parameter LLM.**
-
-[Quick Start](#-quick-start) • [Features](#-features) • [Documentation](#-documentation) • [Examples](#-usage-examples)
-
-</div>
-
----
-
-## 🎯 Why Mem-Agent?
-
-Most Large Language Models (LLMs) treat every conversation as "new" and don't remember past interactions. **Mem-Agent** uses a small locally-running model to:
-
-- ✅ **Remember user history** - Separate memory for each customer/user
-- ✅ **Context awareness** - Responds based on previous conversations
-- ✅ **Fully local** - No internet connection required
-- ✅ **Lightweight & fast** - Only 2.5 GB model size
-- ✅ **Easy integration** - Get started with 3 lines of code
-
-## 🚀 Quick Start
-
-### 1. Install Ollama
-
-```bash
-# Windows/Mac/Linux: https://ollama.ai/download
-curl https://ollama.ai/install.sh | sh
-
-# Start the service
-ollama serve
-```
-
-### 2. Download Model
-
-```bash
-ollama pull granite4:tiny-h
-```
-
-### 3. Use Mem-Agent
-
-```python
-from mem_llm import MemAgent
-
-# Create agent
-agent = MemAgent(model="granite4:tiny-h")
-
-# System check
-status = agent.check_setup()
-if status['status'] == 'ready':
-    print("✅ System ready!")
-else:
-    print("❌ Error:", status)
-
-# Set user
-agent.set_user("user123")
-
-# First conversation
-response = agent.chat("Hello, my name is Ali")
-print(response)
-
-# Second conversation - It remembers me!
-response = agent.chat("Do you remember my name?")
-print(response)
-```
-
-## 📚 Example Scripts
-
-### 1. Simple Test
-
-```bash
-python examples/example_simple.py
-```
-
-### 2. Customer Service Simulation
-
-```bash
-python examples/example_customer_service.py
-```
-
-## 🏗️ Project Structure
-
-```
-Memory LLM/
-├── memory_llm/              # Main package
-│   ├── __init__.py          # Package initialization
-│   ├── mem_agent.py         # Main assistant class
-│   ├── memory_manager.py    # Memory management
-│   ├── memory_db.py         # SQL database support
-│   ├── llm_client.py        # Ollama integration
-│   ├── memory_tools.py      # User tools
-│   ├── knowledge_loader.py  # Knowledge base loader
-│   ├── prompt_templates.py  # Prompt templates
-│   └── config_manager.py    # Configuration manager
-├── examples/                # Example scripts
-├── tests/                   # Test files
-├── setup.py                 # Installation script
-├── requirements.txt         # Dependencies
-└── README.md               # This file
-```
-
-## 🔧 API Usage
-
-### MemAgent Class
-
-```python
-from mem_llm import MemAgent
-
-agent = MemAgent(
-    model="granite4:tiny-h",           # Ollama model name
-    memory_dir="memories",             # Memory directory
-    ollama_url="http://localhost:11434" # Ollama API URL
-)
-```
-
-#### Basic Methods
-
-```python
-# Set user
-agent.set_user("user_id")
-
-# Chat
-response = agent.chat(
-    message="Hello",
-    user_id="optional_user_id",  # If set_user not used
-    metadata={"key": "value"}     # Additional information
-)
-
-# Get memory summary
-summary = agent.memory_manager.get_summary("user_id")
-
-# Search in history
-results = agent.search_user_history("keyword", "user_id")
-
-# Update profile
-agent.update_user_info({
-    "name": "Ali",
-    "preferences": {"language": "en"}
-})
-
-# Get statistics
-stats = agent.get_statistics()
-
-# Export memory
-json_data = agent.export_memory("user_id")
-
-# Clear memory (WARNING!)
-agent.clear_user_memory("user_id", confirm=True)
-```
-
-### MemoryManager Class
-
-```python
-from mem_llm import MemoryManager
-
-memory = MemoryManager(memory_dir="memories")
-
-# Load memory
-data = memory.load_memory("user_id")
-
-# Add interaction
-memory.add_interaction(
-    user_id="user_id",
-    user_message="Hello",
-    bot_response="Hello! How can I help you?",
-    metadata={"timestamp": "2025-01-13"}
-)
-
-# Get recent conversations
-recent = memory.get_recent_conversations("user_id", limit=5)
-
-# Search
-results = memory.search_memory("user_id", "order")
-```
-
-### OllamaClient Class
-
-```python
-from mem_llm import OllamaClient
-
-client = OllamaClient(model="granite4:tiny-h")
-
-# Simple generation
-response = client.generate("Hello world!")
-
-# Chat format
-response = client.chat([
-    {"role": "system", "content": "You are a helpful assistant"},
-    {"role": "user", "content": "Hello"}
-])
-
-# Connection check
-is_ready = client.check_connection()
-
-# Model list
-models = client.list_models()
-```
-
-## 💡 Usage Scenarios
-
-### 1. Customer Service Bot
-- Remembers customer history
-- Knows previous issues
-- Makes personalized recommendations
-
-### 2. Personal Assistant
-- Tracks daily activities
-- Learns preferences
-- Makes reminders
-
-### 3. Education Assistant
-- Tracks student progress
-- Adjusts difficulty level
-- Remembers past mistakes
-
-### 4. Support Ticket System
-- Stores ticket history
-- Finds related old tickets
-- Provides solution suggestions
-
-## 📊 Memory Format
-
-Memories are stored in JSON format:
-
-```json
-{
-  "conversations": [
-    {
-      "timestamp": "2025-01-13T10:30:00",
-      "user_message": "Hello",
-      "bot_response": "Hello! How can I help you?",
-      "metadata": {
-        "topic": "greeting"
-      }
-    }
-  ],
-  "profile": {
-    "user_id": "user123",
-    "first_seen": "2025-01-13T10:30:00",
-    "preferences": {},
-    "summary": {}
-  },
-  "last_updated": "2025-01-13T10:35:00"
-}
-```
-
-## 🔒 Privacy and Security
-
-- ✅ Works completely locally (no internet connection required)
-- ✅ Data stored on your computer
-- ✅ No data sent to third-party services
-- ✅ Memories in JSON format, easily deletable
-
-## 🛠️ Development
-
-### Test Mode
-
-```python
-# Simple chat without memory (for testing)
-response = agent.simple_chat("Test message")
-```
-
-### Using Your Own Model
-
-```python
-# Different Ollama model
-agent = MemAgent(model="llama2:7b")
-
-# Or another LLM API
-# Customize llm_client.py file
-```
-
-## 🐛 Troubleshooting
-
-### Ollama Connection Error
-
-```bash
-# Start Ollama service
-ollama serve
-
-# Port check
-netstat -an | findstr "11434"
-```
-
-### Model Not Found
-
-```bash
-# Check model list
-ollama list
-
-# Download model
-ollama pull granite4:tiny-h
-```
-
-### Memory Issues
-
-```python
-# Check memory directory
-import os
-os.path.exists("memories")
-
-# List memory files
-os.listdir("memories")
-```
-
-## 📈 Performance
-
-- **Model Size**: ~2.5 GB
-- **Response Time**: ~1-3 seconds (depends on CPU)
-- **Memory Usage**: ~4-6 GB RAM
-- **Disk Usage**: ~10-50 KB per user
-
-## 🤝 Contributing
-
-1. Fork the repository
-2. Create feature branch (`git checkout -b feature/amazing-feature`)
-3. Commit changes (`git commit -m 'feat: Add amazing feature'`)
-4. Push to branch (`git push origin feature/amazing-feature`)
-5. Open Pull Request
-
-## 📝 License
-
-MIT License - See LICENSE file for details.
-
-## 🙏 Acknowledgments
-
-- [Ollama](https://ollama.ai/) - Local LLM server
-- [Granite](https://www.ibm.com/granite) - IBM Granite models
-
-## 📞 Contact
-
-You can open an issue for your questions.
-
----
-
-**Note**: This project is for educational and research purposes. Please perform comprehensive testing before using in production environment.

mem_llm-1.0.2.dist-info/RECORD

@@ -1,15 +0,0 @@
-mem_llm/__init__.py,sha256=l9ynmAWNyC_CPZcb5q-pkJ_oVdJZpFN4hwVHRNqCkg8,920
-mem_llm/config.yaml.example,sha256=lgmfaU5pxnIm4zYxwgCcgLSohNx1Jw6oh3Qk0Xoe2DE,917
-mem_llm/config_from_docs.py,sha256=YFhq1SWyK63C-TNMS73ncNHg8sJ-XGOf2idWVCjxFco,4974
-mem_llm/config_manager.py,sha256=8PIHs21jZWlI-eG9DgekjOvNxU3-U4xH7SbT8Gr-Z6M,7075
-mem_llm/knowledge_loader.py,sha256=oSNhfYYcx7DlZLVogxnbSwaIydq_Q3__RDJFeZR2XVw,2699
-mem_llm/llm_client.py,sha256=tLNulVEV_tWdktvcQUokdhd0gTkIISUHipglRt17IWk,5255
-mem_llm/mem_agent.py,sha256=BIEMHpbss4QPstS-aEoZwmKBBc_fg87tf8Jj7MTIV8g,20357
-mem_llm/memory_db.py,sha256=KyNIcChYihSavd2ot5KMBlVB9lq8rexoBQ0lA5bCJNI,12611
-mem_llm/memory_manager.py,sha256=iXnf5YEJXmQ75jgJ2LEx9zCHxIpZTcLtHlp2eWgFjRg,8335
-mem_llm/memory_tools.py,sha256=ARANFqu_bmL56SlV1RzTjfQsJj-Qe2QvqY0pF92hDxU,8678
-mem_llm/prompt_templates.py,sha256=tCiQJw3QQKIaH8NsxEKOIaIVxw4XT43PwdmyfCINzzM,6536
-mem_llm-1.0.2.dist-info/METADATA,sha256=yJxAbApli62T27XkKE0SIHxgD50PPbhXldmBXfdyfhE,9347
-mem_llm-1.0.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mem_llm-1.0.2.dist-info/top_level.txt,sha256=_fU1ML-0JwkaxWdhqpwtmTNaJEOvDMQeJdA8d5WqDn8,8
-mem_llm-1.0.2.dist-info/RECORD,,