### Quickstart: Basic memvid-sdk Usage Source: https://docs.memvid.com/installation/python A Python quickstart example demonstrating how to use the memvid-sdk to open a memory file, put a new memory, check statistics, verify the file integrity, and seal it. It covers basic import and usage patterns. ```python from memvid_sdk import LockedError, Memvid, use mv = use("basic", "notes.mv2") mv.put(text="hello world", kind="text/plain") print(mv.stats()) report = Memvid.verify("notes.mv2", deep=True) print(report["overall_status"]) mv.seal() ``` -------------------------------- ### Pinecone Setup and Initialization (Python) Source: https://docs.memvid.com/comparisons/vector-databases Guides through the setup process for Pinecone, a vector database. Involves signing up, creating a project, obtaining an API key, installing the client library, initializing the connection, creating an index, and waiting for it to become ready. Data must be embedded before insertion. ```python # 1. Sign up at pinecone.io # 2. Create a project # 3. Get API key # 4. Install SDK pip install pinecone-client # 5. Initialize import pinecone pinecone.init(api_key="your-api-key", environment="us-west1-gcp") # 6. Create index (wait for provisioning...) pinecone.create_index("my-index", dimension=1536, metric="cosine") # 7. Wait for index to be ready import time while not pinecone.describe_index("my-index").status["ready"]: time.sleep(1) # 8. Connect to index index = pinecone.Index("my-index") # 9. Now you need to embed your data before inserting... ``` -------------------------------- ### Quick Start Source: https://docs.memvid.com/python-sdk/overview A concise guide to get started with the Memvid Python SDK, demonstrating memory creation, data ingestion, searching, and querying. ```APIDOC ## Quick Start ```python from memvid_sdk import create # Create a new memory mem = create('knowledge.mv2') # Enable lexical search (BM25) mem.enable_lex() # Add documents mem.put( title='Meeting Notes', label='notes', metadata={'source': 'slack'}, text='Alice mentioned she works at Anthropic...' ) # Search results = mem.find('who works at AI companies?', k=5) print(results['hits']) # Ask questions answer = mem.ask('What does Alice do?') print(answer['text']) # Seal when done mem.seal() ``` **Note:** No embeddings required for BM25 lexical search. Embeddings can be added later for semantic search. ``` -------------------------------- ### Install Memvid Node.js SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Installs the Memvid SDK for Node.js applications. ```bash npm install @memvid/sdk ``` -------------------------------- ### Installation and Quick Start (Python) Source: https://docs.memvid.com/frameworks/langchain Install the necessary packages and get started with Memvid in Python for LangChain applications. ```APIDOC ## Installation (Python) ```bash pip install memvid-sdk langchain langchain-openai ``` ## Quick Start (Python) ```python from memvid_sdk import use # Open with LangChain adapter mem = use('langchain', 'knowledge.mv2') # Access LangChain tools tools = mem.tools # Returns LangChain StructuredTool objects ``` ``` -------------------------------- ### Install Memvid Python SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Installs the Memvid SDK for Python applications using pip. ```bash pip install memvid-sdk ``` -------------------------------- ### Memvid CLI Quick Start Commands Source: https://docs.memvid.com/installation/cli Demonstrates basic Memvid CLI operations including creating a memory, adding documents, performing immediate searches, and asking questions. These commands help you quickly start building AI memories. ```bash # Create your first memory memvid create my-memory.mv2 # Add some documents memvid put my-memory.mv2 --input ./documents/ # Search immediately (no embedding wait!) memvid find my-memory.mv2 --query "your search term" # Ask questions memvid ask my-memory.mv2 --question "What is this about?" ``` -------------------------------- ### Installation and Quick Start (Node.js) Source: https://docs.memvid.com/frameworks/langchain Install the necessary packages and get started with Memvid in Node.js for LangChain applications. ```APIDOC ## Installation (Node.js) ```bash npm install @memvid/sdk @langchain/core @langchain/openai @langchain/langgraph zod ``` ## Quick Start (Node.js) ```typescript import { use } from '@memvid/sdk'; // Open with LangChain adapter const mem = await use('langchain', 'knowledge.mv2'); // Access LangChain tools (compatible with createReactAgent) const tools = mem.tools; // Array of tool() objects ``` ``` -------------------------------- ### ChromaDB Setup and Initialization (Python) Source: https://docs.memvid.com/comparisons/vector-databases Details the setup for ChromaDB, an open-source vector database. Covers installation, client initialization, creating a collection, and adding documents. Note that ChromaDB embeds documents automatically, which can take significant time for large datasets. ```python # 1. Install pip install chromadb # 2. Initialize import chromadb client = chromadb.Client() # 3. Create collection collection = client.create_collection("my-collection") # 4. Add documents (ChromaDB embeds automatically, but still takes time) collection.add( documents=["doc1", "doc2", "doc3"], ids=["id1", "id2", "id3"] ) # This step embeds all documents - can take minutes for large datasets ``` -------------------------------- ### Memvid SDK: LangChain Integration Example Source: https://docs.memvid.com/introduction/welcome Demonstrates how to integrate Memvid with LangChain in Python. It shows how to open a memory file with the LangChain adapter, create a retriever, and set up a RetrievalQA chain for question answering. ```python from memvid_sdk import use from langchain_openai import ChatOpenAI from langchain.chains import RetrievalQA # Open with LangChain adapter mem = use('langchain', 'my-knowledge.mv2', read_only=True) retriever = mem.as_retriever(k=5) # Create QA chain qa = RetrievalQA.from_chain_type( llm=ChatOpenAI(model="gpt-4o"), retriever=retriever ) result = qa.run("What are the main concepts?") print(result) ``` -------------------------------- ### Memvid CLI Installation and Usage Source: https://docs.memvid.com/introduction/welcome Provides commands to install the Memvid CLI globally using npm and then create a new memory file, ingest documents with vector compression, and perform a basic search. ```bash npm install -g memvid-cli # Create a new memory file (1 GB capacity by default) memvid create my-knowledge.mv2 # Ingest documents with vector compression memvid put my-knowledge.mv2 --input ./documents/ --vector-compression # Search your knowledge memvid find my-knowledge.mv2 --query "your search query" ``` -------------------------------- ### Install Memvid CLI Source: https://docs.memvid.com/quickstart/five-minute-guide Installs the Memvid command-line interface globally. Requires Node.js version 14 or higher and works on macOS, Linux, and Windows. ```bash npm install -g memvid-cli ``` -------------------------------- ### Install @memvid/sdk using npm or pnpm Source: https://docs.memvid.com/installation/node This snippet shows how to install the Node.js SDK using package managers npm or pnpm. Ensure you have Node.js version 18 or later installed. Prebuilt binaries are available for common platforms; otherwise, you may need to build from source. ```bash npm install @memvid/sdk # or: pnpm add @memvid/sdk ``` -------------------------------- ### Install and Verify Memvid CLI Source: https://docs.memvid.com/installation/cli Installs the Memvid CLI globally using npm and then verifies the installation by checking the CLI version. Ensure Node.js and npm are installed and configured correctly. ```bash npm install -g memvid-cli memvid --version ``` -------------------------------- ### Install Memvid CLI Source: https://docs.memvid.com/quickstart/cli-to-dashboard Installs the Memvid command-line interface using package managers like Homebrew for macOS, a script for Linux, Winget for Windows, or Cargo for Rust projects. After installation, verify the CLI is operational by checking its version. ```bash brew install memvid/tap/memvid ``` ```bash curl -sSL https://get.memvid.com | sh ``` ```powershell winget install memvid ``` ```bash cargo install memvid-cli ``` ```bash memvid --version ``` -------------------------------- ### Node.js SDK Quick Start: Create, Open, and Use Memory Source: https://docs.memvid.com/installation/node Demonstrates the basic usage of the Node.js SDK to create a new memory file, add data, commit changes, open an existing memory file for read-only access, perform searches, and integrate with framework adapters like Langchain. This code requires Node.js 18+. ```typescript import { create, open, use } from "@memvid/sdk"; // Create new memory const mem = await create("notes.mv2"); await mem.put({ title: "Hello Memvid", label: "demo", text: "Hello from Node.js", enableEmbedding: true, }); await mem.seal(); // commits writes // Open existing memory (read-only) const ro = await open("notes.mv2", "basic", { readOnly: true }); const results = await ro.find("hello", { k: 5, mode: "auto" }); console.log(results.hits.map((h: any) => h.title)); // Framework adapters (tools/functions) const lc = await use("langchain", "notes.mv2", { readOnly: true }); console.log(Object.keys(lc.tools ?? {})); ``` -------------------------------- ### Memvid SDK: Python Example Source: https://docs.memvid.com/introduction/welcome Illustrates the usage of the Memvid SDK in Python for opening a memory file, conducting searches, and performing AI-powered question answering. Includes a reminder to close the memory instance when finished. ```python from memvid_sdk import use # Open your memory mem = use('basic', 'my-knowledge.mv2', read_only=True) # Search results = mem.find('machine learning', k=10) for hit in results.get('hits', []): print(f"{hit['score']:.2f}: {hit['title']}") # Ask questions with AI synthesis answer = mem.ask('What are the key concepts?') print(answer.get('answer')) # Always close when done mem.close() ``` -------------------------------- ### Install Memvid CLI and Create Memory Source: https://docs.memvid.com/introduction/the-memvid-approach Provides instructions for installing the Memvid command-line interface globally using npm and then creating a new Memvid memory file. This is the initial setup step for using Memvid locally. ```bash # Install npm install -g memvid-cli # Create memory memvid create my-memory.mv2 ``` -------------------------------- ### Initial Memvid Setup Steps Source: https://docs.memvid.com/cli/tickets-and-capacity Guides through the initial setup process for a new Memvid memory, including creating a memory file, syncing it with the dashboard, and verifying the binding. ```bash # 1. Create memory file memvid create project.mv2 # 2. Sync with dashboard (binds and applies ticket) MEMVID_API_KEY=mv_live_xxx memvid tickets sync project.mv2 --memory-id mem_abc123 # 3. Verify binding memvid binding project.mv2 ``` -------------------------------- ### Install memvid-sdk Python Package Source: https://docs.memvid.com/installation/python Install the memvid-sdk package using pip. Optional adapters for integrations with libraries like LangChain and OpenAI can be installed using package extras. ```bash pip install memvid-sdk # optional adapters pip install "memvid-sdk[langchain]" "memvid-sdk[openai]" ``` -------------------------------- ### Memvid Python SDK Quick Start Source: https://docs.memvid.com/python-sdk/overview A quick start guide to using the Memvid Python SDK. Demonstrates creating a memory, enabling lexical search, adding documents, performing searches, asking questions, and sealing the memory. ```python from memvid_sdk import create # Create a new memory mem = create('knowledge.mv2') # Enable lexical search (BM25) mem.enable_lex() # Add documents (no embeddings needed!) mem.put( title='Meeting Notes', label='notes', metadata={'source': 'slack'}, text='Alice mentioned she works at Anthropic...' ) # Search works immediately results = mem.find('who works at AI companies?', k=5) print(results['hits']) # Ask questions answer = mem.ask('What does Alice do?') print(answer['text']) # Seal when done mem.seal() ``` -------------------------------- ### Memvid SDK: Node.js Example Source: https://docs.memvid.com/introduction/welcome Shows how to use the Memvid SDK in Node.js to open a memory file, perform semantic search, and ask questions. It demonstrates opening a memory in read-only mode and iterating through search results. ```typescript import { use } from '@memvid/sdk'; // Open your memory const mem = await use('basic', 'my-knowledge.mv2', { readOnly: true }); // Search const results = await mem.find('machine learning', { k: 10 }); results.hits.forEach(hit => { console.log(`${hit.score.toFixed(2)}: ${hit.title}`); }); // Ask questions const answer = await mem.ask('What are the key concepts?'); console.log(answer.answer); ``` -------------------------------- ### MemVid Model Comparison Example Source: https://docs.memvid.com/concepts/time-travel-replay Shows how to use MemVid to compare different LLM models. The example involves starting a session, performing an 'ask' command with a specific model (e.g., GPT-4o), and ending the session. This allows for subsequent analysis or replaying with different models. ```bash # Ask with GPT-4o memvid session start knowledge.mv2 --name "Model Comparison" memvid ask knowledge.mv2 --question "Summarize the key findings" --use-model openai:gpt-4o memvid session end knowledge.mv2 ``` -------------------------------- ### Memvid Node.js SDK Quick Start Example Source: https://docs.memvid.com/sdks/node A basic example demonstrating how to create a new memory file, add documents, perform searches, ask questions using an AI model, and close the memory file. This requires Node.js 18+. ```typescript import { create, open } from '@memvid/sdk'; // Create a new memory file const mem = await create('knowledge.mv2'); // Add documents await mem.put({ title: 'Meeting Notes', text: 'Alice mentioned she works at Anthropic...', enableEmbedding: true }); // Search const results = await mem.find('who works at AI companies?'); console.log(results.hits); // Ask questions with AI const answer = await mem.ask('What does Alice do?', { model: 'gpt-4o-mini', modelApiKey: process.env.OPENAI_API_KEY }); console.log(answer.text); // Close when done await mem.close(); ``` -------------------------------- ### Python SDK: Interact with Memvid Memory Databases Source: https://docs.memvid.com/quickstart/cli-to-dashboard This Python code demonstrates how to use the memvid SDK to interact with memory databases. It shows how to install the SDK, open a database in read-only mode, perform searches using keywords, and ask natural language questions, specifying an OpenAI model for processing. ```bash pip install memvid-sdk ``` ```python from memvid_sdk import use # Open read-only (for queries) mem = use('basic', 'docs.mv2', read_only=True) # Search results = mem.find('authentication', k=5) for hit in results['hits']: print(f"{hit['score']:.2f}: {hit['title']}") # Ask questions answer = mem.ask('How do I configure OAuth?', model='openai:gpt-4o') print(answer['answer']) ``` -------------------------------- ### Run Memvid CLI without Global Installation Source: https://docs.memvid.com/installation/cli Executes Memvid CLI commands using npx, allowing you to run the tool without a global npm installation. This is useful for testing or when global installations are restricted. ```bash npx memvid-cli --help npx memvid-cli create test.mv2 ``` -------------------------------- ### Quick Start: Use Memvid with LangChain Adapter (Python) Source: https://docs.memvid.com/frameworks/langchain Provides a Python example for initializing Memvid with the 'langchain' adapter. It illustrates how to load Memvid data and access the tools it exposes for LangChain integration. ```python from memvid_sdk import use # Open with LangChain adapter mem = use('langchain', 'knowledge.mv2') # Access LangChain tools tools = mem.tools # Returns LangChain StructuredTool objects ``` -------------------------------- ### Node.js SDK: Interact with Memvid Memory Databases Source: https://docs.memvid.com/quickstart/cli-to-dashboard This Node.js code illustrates how to use the memvid SDK for interacting with memory databases. It covers installing the SDK via npm, opening a database in read-only mode, executing searches with a specified number of results (k), and posing natural language questions, including specifying different OpenAI models. ```bash npm install @memvid/sdk ``` ```typescript import { use } from '@memvid/sdk'; // Open read-only const mem = await use('basic', 'docs.mv2', { readOnly: true }); // Search const results = await mem.find('authentication', { k: 5 }); results.hits.forEach(hit => { console.log(`${hit.score.toFixed(2)}: ${hit.title}`); }); // Ask questions const answer = await mem.ask('How do I configure OAuth?', { model: 'openai:gpt-4o-mini' }); console.log(answer.answer); ``` -------------------------------- ### Troubleshoot 'Command Not Found' Source: https://docs.memvid.com/installation/cli Provides commands to check your npm global bin directory and add it to your PATH environment variable if the Memvid CLI commands are not recognized. This ensures your system can locate the installed CLI. ```bash # Check npm global bin location npm root -g # Add to PATH if needed export PATH="$PATH:$(npm root -g)/../bin" ``` -------------------------------- ### Agent Setup and Chat Initiation (Python) Source: https://docs.memvid.com/frameworks/autogen Initializes a UserProxyAgent, an AssistantAgent for research with tool access, and another AssistantAgent for writing. It then sets up a GroupChat and GroupChatManager to orchestrate a conversation between these agents, starting with a specific research and writing task. ```python from autogen import UserProxyAgent, AssistantAgent, GroupChat, GroupChatManager # Assume search_tool is defined elsewhere and imported # from your_module import search_tool # Mock search_tool for demonstration purposes class MockSearchTool: def __init__(self): self.schema = {"name": "search", "parameters": {"query": "string"}} self.name = "search" self.func = self.search_func def search_func(self, query: str): print(f"Searching for: {query}") return f"Mock results for {query}" search_tool = MockSearchTool() user_proxy = UserProxyAgent(name="user", human_input_mode="NEVER") researcher = AssistantAgent( name="researcher", llm_config={ "model": "gpt-4o", "functions": [search_tool.schema] }, system_message="You research topics using the knowledge base." ) researcher.register_function(function_map={search_tool.name: search_tool.func}) writer = AssistantAgent( name="writer", llm_config={"model": "gpt-4o"}, system_message="You write summaries based on research findings." ) group_chat = GroupChat( agents=[user_proxy, researcher, writer], messages=[], max_round=10 ) manager = GroupChatManager(groupchat=group_chat, llm_config={"model": "gpt-4o"}) user_proxy.initiate_chat( manager, message="Research deployment best practices and write a summary" ) ``` -------------------------------- ### OpenAI CLIP Provider Setup and Usage (Python) Source: https://docs.memvid.com/concepts/visual-embeddings Shows how to set up and use OpenAI's CLIP embedding models with the Memvid SDK. It includes setting the API key via an environment variable and provides examples of initializing the provider using a factory function with default or specific models, or direct instantiation. -------------------------------- ### Quick Start: Use Memvid with LangChain Adapter (Node.js) Source: https://docs.memvid.com/frameworks/langchain Demonstrates the basic setup for using Memvid within a LangChain application using the Node.js adapter. It shows how to initialize Memvid with the 'langchain' adapter and access its compatible tools. ```typescript import { use } from '@memvid/sdk'; // Open with LangChain adapter const mem = await use('langchain', 'knowledge.mv2'); // Access LangChain tools (compatible with createReactAgent) const tools = mem.tools; // Array of tool() objects ``` -------------------------------- ### Installation Source: https://docs.memvid.com/cli Instructions for installing the Memvid CLI using npm and verifying the installation. ```APIDOC ## Installation ```bash # npm (recommended) npm install -g memvid-cli # Verify installation memvid --version ``` See [Installation Guide](/installation/cli) for platform-specific instructions and troubleshooting. ``` -------------------------------- ### Quick Start with Haystack Adapter Source: https://docs.memvid.com/frameworks/haystack Initializes Memvid with the Haystack adapter and accesses its retriever component. This is a basic setup to get started with Memvid's search capabilities within Haystack. ```python from memvid_sdk import use # Open with Haystack adapter mem = use('haystack', 'knowledge.mv2') # Access Haystack components retriever = mem.as_retriever(top_k=5) ``` -------------------------------- ### Memvid Google ADK Integration Source: https://docs.memvid.com/frameworks/google-adk This section details the integration of Memvid with Google ADK, including installation, setup, and usage examples for building Gemini-powered agents. ```APIDOC ## Installation ```bash npm install @memvid/sdk @google/generative-ai ``` ## Quick Start ```typescript import { use } from '@memvid/sdk'; // Open with Google ADK adapter const mem = await use('google-adk', 'knowledge.mv2'); // Access ADK function declarations const tools = mem.tools; // FunctionDeclaration[] for Gemini API const executors = mem.functions; // Function executors by name ``` ## Available Functions The Google ADK adapter provides three function declarations: | Function | Description | | ------------- | ----------------------------------------------------- | | `memvid_put` | Store documents in memory with title, label, and text | | `memvid_find` | Search for relevant documents by query | | `memvid_ask` | Ask questions with RAG-style answer synthesis | ## Basic Usage with Gemini ```typescript import { use } from '@memvid/sdk'; import { GoogleGenerativeAI } from '@google/generative-ai'; // Initialize Memvid with Google ADK adapter const mem = await use('google-adk', 'knowledge.mv2'); // Get function declarations and executors const tools = mem.tools as any[]; const executors = mem.functions as Record Promise>; // Create Gemini client const geminiKey = process.env.GEMINI_API_KEY ?? process.env.GOOGLE_API_KEY; if (!geminiKey) throw new Error("Set GEMINI_API_KEY (or legacy GOOGLE_API_KEY)"); const genAI = new GoogleGenerativeAI(geminiKey); // Create model with Memvid tools const model = genAI.getGenerativeModel({ model: 'gemini-2.0-flash', tools: [{ functionDeclarations: tools }], }); // Start a chat const chat = model.startChat(); const result = await chat.sendMessage('Search for authentication information'); // Handle function calls const response = result.response; const parts = response.candidates?.[0]?.content?.parts || []; for (const part of parts) { if (part.functionCall) { const { name, args } = part.functionCall; console.log(`Function call: ${name}`); // Execute the function if (executors[name]) { const funcResult = await executors[name](args as Record); console.log(`Result: ${funcResult}`); // Send result back to model const followUp = await chat.sendMessage([{ functionResponse: { name, response: { result: funcResult } } }]); console.log(`Model response: ${followUp.response.text()}`); } } else if (part.text) { console.log(`Response: ${part.text}`); } } ``` ## Direct Tool Execution Use the function executors directly without Gemini: ```typescript import { use } from '@memvid/sdk'; const mem = await use('google-adk', 'knowledge.mv2', { mode: 'create' }); const executors = mem.functions as Record Promise>; // Store documents const putResult = await executors.memvid_put({ title: 'API Documentation', label: 'docs', text: 'Authentication uses JWT tokens with refresh capability.', }); console.log(putResult); // Output: Document stored with frame_id: 2 // Search documents const findResult = await executors.memvid_find({ query: 'authentication', top_k: 5, }); console.log(findResult); // Output: Found 1 results: // 1. [API Documentation] (score: 2.34): Authentication uses JWT tokens... // Ask questions const askResult = await executors.memvid_ask({ question: 'How does authentication work?', mode: 'auto', }); console.log(askResult); // Output: Answer: Authentication uses JWT tokens with refresh capability. // Sources: API Documentation ``` ## Complete Agentic Example ```typescript import { use } from '@memvid/sdk'; import { GoogleGenerativeAI } from '@google/generative-ai'; async function runGeminiAgent() { // Initialize const mem = await use('google-adk', 'knowledge.mv2'); const tools = mem.tools as any[]; const executors = mem.functions as Record Promise>; // Store some knowledge first await executors.memvid_put({ title: 'Gemini Overview', label: 'google-ai', text: 'Gemini is Google\'s most capable AI model family.', }); // ... rest of the agent logic } ``` ``` -------------------------------- ### Create and Ingest Data with Memvid CLI Source: https://docs.memvid.com/quickstart/five-minute-guide Demonstrates creating a new memory file and adding documents to it using the Memvid CLI. Data can be ingested directly from standard input and is immediately searchable. ```bash # Create a new memory memvid create knowledge.mv2 # Add documents (no embeddings needed!) echo "Alice works at Anthropic as a Senior Engineer in San Francisco." | \ memvid put knowledge.mv2 --title "Team Info" echo "Bob joined OpenAI last month as a Research Scientist." | \ memvid put knowledge.mv2 --title "New Hires" echo "Project Alpha has a budget of $500k and is led by Alice." | \ memvid put knowledge.mv2 --title "Projects" ``` -------------------------------- ### Session Management: Start, Checkpoint, End, List, Replay, Delete Source: https://docs.memvid.com/python-sdk/overview Provides a comprehensive guide to managing user sessions, including starting a session with a name, performing operations, adding checkpoints, ending the session to get a summary, listing all existing sessions, replaying a session with modified parameters, and deleting a session. ```python # Start recording session_id = mem.session_start('qa-test') # Perform operations mem.find('test query') mem.ask('What happened?') # Add checkpoint mem.session_checkpoint() # End session summary = mem.session_end() # List sessions sessions = mem.session_list() # Replay session with different params replay = mem.session_replay(session_id, top_k=10, adaptive=True) print(replay['match_rate']) # Delete session mem.session_delete(session_id) ``` -------------------------------- ### Memvid CLI: Create, Ingest, and Search Memory Databases Source: https://docs.memvid.com/quickstart/cli-to-dashboard This snippet demonstrates the core command-line interface (CLI) operations for the memvid tool. It covers creating a new memory file, ingesting data with vector compression, checking database statistics, performing keyword searches, asking natural language questions, and verifying data integrity. The `--vector-compression` flag is used for efficient data storage. ```bash memvid create docs.mv2 memvid put docs.mv2 \ --input ./docs/ \ --vector-compression \ --track "documentation" memvid put docs.mv2 \ --input ./api-reference/ \ --vector-compression \ --track "api" memvid stats docs.mv2 memvid find docs.mv2 --query "authentication setup" --mode auto export OPENAI_API_KEY=your-key memvid ask docs.mv2 \ --question "How do I configure OAuth?" \ --use-model openai memvid verify docs.mv2 --deep ``` -------------------------------- ### Create and Ingest Data with Memvid Python SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Demonstrates creating a new memory and ingesting documents using the Memvid Python SDK. Documents require a title, label, metadata, and text. ```python from memvid_sdk import create mem = create('knowledge.mv2') mem.enable_lex() # Add documents (no embeddings needed!) mem.put( title='Team Info', label='team', metadata={}, text='Alice works at Anthropic as a Senior Engineer in San Francisco.' ) mem.put( title='New Hires', label='team', metadata={}, text='Bob joined OpenAI last month as a Research Scientist.' ) mem.put( title='Projects', label='project', metadata={}, text='Project Alpha has a budget of $500k and is led by Alice.' ) ``` -------------------------------- ### Ask Questions with Memvid CLI Source: https://docs.memvid.com/quickstart/five-minute-guide Demonstrates using LLM-powered Q&A with Memvid CLI. Requires an OpenAI API key to be set as an environment variable. ```bash # Ask with LLM synthesis (requires OPENAI_API_KEY) export OPENAI_API_KEY=sk-... memvid ask knowledge.mv2 --question "What is Alice's role?" --use-model openai ``` -------------------------------- ### Verify memvid Installation Source: https://docs.memvid.com/sdks/cli Checks if the memvid CLI has been installed correctly by displaying its current version. This command should be run after installation to confirm successful setup. ```bash memvid --version ``` -------------------------------- ### Ask Questions with Memvid Source: https://docs.memvid.com/quickstart/cli-to-dashboard Utilize AI models to ask questions and receive synthesized answers based on the content of your Memvid memory. Supports local models like 'tinyllama' and external services like OpenAI and Anthropic by providing API keys. ```bash # Using local model (tinyllama) memvid ask my-knowledge.mv2 --question "What is Memvid and how does it work?" ``` ```bash # Using OpenAI (requires API key) export OPENAI_API_KEY=your-key memvid ask my-knowledge.mv2 --question "What is Memvid?" --use-model openai ``` ```bash # Using Anthropic export ANTHROPIC_API_KEY=your-key memvid ask my-knowledge.mv2 --question "What is Memvid?" --use-model claude ``` -------------------------------- ### Ask Questions with Memvid Python SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Illustrates using LLM-powered Q&A with the Memvid Python SDK. Requires an OpenAI API key to be set in the environment variables. ```python # Ask with LLM synthesis answer = mem.ask( "What is Alice's role?", model='gpt-4o-mini', api_key=os.environ['OPENAI_API_KEY'] ) print(answer['text']) # "Alice is a Senior Engineer at Anthropic in San Francisco." ``` -------------------------------- ### Install Memvid Framework Dependencies Source: https://docs.memvid.com/errors/troubleshooting These bash commands show how to install necessary dependencies for different frameworks (LangChain, LlamaIndex, CrewAI) to ensure proper integration with Memvid. Make sure to install the correct package for your chosen framework. ```bash # For LangChain pip install langchain langchain-openai # For LlamaIndex pip install llama-index # For CrewAI pip install crewai ``` -------------------------------- ### Create and Manage Memvid Memory Source: https://docs.memvid.com/quickstart/cli-to-dashboard Create a new Memvid memory file (`.mv2`) and add various types of content, including text, files, and directories, with options for metadata like tracks and tags. Vector compression can be enabled during document addition for optimized storage. ```bash memvid create my-knowledge.mv2 memvid stats my-knowledge.mv2 ``` ```bash echo "Memvid is a portable AI memory system. It stores embeddings, indices, and data in a single .mv2 file." | memvid put my-knowledge.mv2 --input - --title "What is Memvid" ``` ```bash # Add a single file with vector compression memvid put my-knowledge.mv2 --input document.pdf --vector-compression # Add all files in a directory memvid put my-knowledge.mv2 --input ./documents/ --vector-compression ``` ```bash memvid put my-knowledge.mv2 \ --input notes.md \ --track "notes" \ --tag "category=meeting" \ --vector-compression ``` -------------------------------- ### Update Memvid CLI Source: https://docs.memvid.com/installation/cli Updates the globally installed Memvid CLI to the latest version using npm. Regular updates ensure you have the latest features and bug fixes. ```bash npm update -g memvid-cli ``` -------------------------------- ### Get CLI Version Source: https://docs.memvid.com/cli/maintenance-and-tickets Displays the current version of the Memvid CLI. This is a basic command for verifying the installed version. ```bash memvid version ``` -------------------------------- ### Manage Documents and Query via CLI Source: https://docs.memvid.com/examples/document-qa This example provides command-line interface commands for managing a document Q&A system. It covers creating a new document store, ingesting all documents from a directory, and asking questions against the store. ```bash # Create and ingest memvid create documents.mv2 memvid put documents.mv2 --input ./docs/ # Ask questions memvid ask documents.mv2 --question "What is the refund policy?" ``` -------------------------------- ### Diagnose Python Import Errors with Bash Source: https://docs.memvid.com/errors/troubleshooting This snippet provides bash commands to diagnose Python import errors related to the memvid SDK. It includes checking the installation, Python version, and installed packages. ```bash pip show memvid-sdk python --version pip list | grep memvid ``` -------------------------------- ### Install and Use NER Models for Logic-Mesh Source: https://docs.memvid.com/installation/models Guides on installing NER models and enabling Logic-Mesh during data ingestion with `memvid put`. Also demonstrates how to use `memvid follow` with extracted entities. ```bash # Install NER model memvid models install --ner distilbert-ner # Enable Logic-Mesh during ingestion and traversal memvid put graph.mv2 --input docs/ --logic-mesh memvid follow graph.mv2 traverse --start "Microsoft" --hops 2 ``` -------------------------------- ### Memvid CLI: Create, Put, and Find Knowledge Source: https://docs.memvid.com/comparisons/vector-databases This snippet shows basic Memvid CLI commands for creating a knowledge base file, adding content to it, and searching for specific information. It requires the memvid-cli to be installed globally. ```bash npm install -g memvid-cli memvid create knowledge.mv2 echo "Your document content" | memvid put knowledge.mv2 memvid find knowledge.mv2 --query "document" ``` -------------------------------- ### Get Memory Statistics and List Entities Source: https://docs.memvid.com/python-sdk/overview Provides examples for retrieving statistics about memories, such as the count of entities and cards, and for listing all available entities within the system. ```python stats = mem.memories_stats() print(stats['entityCount'], stats['cardCount']) entities = mem.memory_entities() ``` -------------------------------- ### Ask Command Examples with memvid CLI Source: https://docs.memvid.com/cli/search-and-ask Demonstrates various ways to use the 'memvid ask' command to query memory files. This includes specifying models, adjusting retrieval parameters like top-k, filtering by date ranges, and obtaining context-only responses. It highlights options for masking PII and using different LLM providers. ```bash # Ask with local Ollama model (recommended) memvid ask knowledge.mv2 \ --question "How do I configure authentication?" \ --use-model "ollama:qwen2.5:1.5b" # Ask with more context memvid ask knowledge.mv2 \ --question "Explain the architecture in detail" \ --top-k 15 \ --use-model "ollama:qwen2.5:3b" # Get just the context without LLM synthesis memvid ask knowledge.mv2 \ --question "What is the architecture?" \ --context-only # Mask sensitive data before sending to cloud LLM memvid ask knowledge.mv2 \ --question "What are the contact details?" \ --use-model openai \ --mask-pii # Filter to specific date range memvid ask knowledge.mv2 \ --question "What happened in Q4?" \ --start "2024-10-01" \ --end "2024-12-31" \ --use-model "ollama:qwen2.5:1.5b" # JSON output with Gemini memvid ask knowledge.mv2 \ --question "Summarize the API" \ --use-model "gemini-2.0-flash" \ --json ``` -------------------------------- ### Get Help and Version Information Source: https://docs.memvid.com/troubleshooting/cli Retrieves help information for memvid commands and displays version details. This includes general help, command-specific help, and the memvid version. ```bash # General help memvid --help # Command-specific help memvid create --help memvid put --help memvid find --help memvid doctor --help # Version info memvid version ``` -------------------------------- ### Create and Ingest Data with Memvid Node.js SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Shows how to create a new memory and ingest documents using the Memvid Node.js SDK. Documents are added with titles and labels. ```typescript import { create } from '@memvid/sdk'; const mem = await create('knowledge.mv2'); // Add documents (no embeddings needed!) await mem.put({ title: 'Team Info', label: 'team', text: 'Alice works at Anthropic as a Senior Engineer in San Francisco.' }); await mem.put({ title: 'New Hires', label: 'team', text: 'Bob joined OpenAI last month as a Research Scientist.' }); await mem.put({ title: 'Projects', label: 'project', text: 'Project Alpha has a budget of $500k and is led by Alice.' }); ``` -------------------------------- ### Configure Indexes in Memvid Source: https://docs.memvid.com/concepts/performance-tuning Control index creation during Memvid setup to optimize storage and search performance. Disable vector or lexical indexes as needed based on the intended use case. ```bash # No vector index (lexical only) memvid create code.mv2 --no-vec # No lexical index (semantic only) memvid create semantic.mv2 --no-lex ``` -------------------------------- ### Ask Questions with Memvid Node.js SDK Source: https://docs.memvid.com/quickstart/five-minute-guide Illustrates how to use LLM-powered Q&A with the Memvid Node.js SDK. Requires an OpenAI API key passed to the SDK. ```typescript // Ask with LLM synthesis const answer = await mem.ask("What is Alice's role?", { model: 'gpt-4o-mini', modelApiKey: process.env.OPENAI_API_KEY }); console.log(answer.text); // "Alice is a Senior Engineer at Anthropic in San Francisco." ``` -------------------------------- ### Use Case Examples Source: https://docs.memvid.com/concepts/time-travel-replay Practical examples demonstrating how to use Memvid for various scenarios. ```APIDOC ## Use Case Examples Memvid can be applied to several practical scenarios, including debugging, compliance audits, and model comparisons. ### 1. Debug Missing Results This example shows how to record a failing scenario and replay it with adaptive retrieval to identify issues. ```bash # Record the failing scenario memvid session start knowledge.mv2 --name "Missing Results Debug" memvid ask knowledge.mv2 --question "What did Databricks purchase?" --use-model openai memvid session end knowledge.mv2 # Replay with adaptive retrieval memvid session replay knowledge.mv2 --session --adaptive --verbose # Reveals: Document existed at rank 12, adaptive found it ``` ### 2. Compliance Audit Trail Use Memvid to create an immutable record of decisions for compliance purposes. ```bash # Record all decisions for audit memvid session start knowledge.mv2 --name "Compliance Review 2024-12" memvid ask knowledge.mv2 --question "Is this transaction fraudulent?" --use-model openai memvid session end knowledge.mv2 # Later: Replay with frozen context to verify decision memvid session replay knowledge.mv2 --session --audit # Shows exact frames and answer - reproducible for auditors ``` ### 3. Model Comparison Compare the performance and output of different LLM models. ```bash # Ask with GPT-4o memvid session start knowledge.mv2 --name "Model Comparison" memvid ask knowledge.mv2 --question "Summarize the key findings" --use-model openai:gpt-4o memvid session end knowledge.mv2 ``` ``` -------------------------------- ### Memvid CLI Hybrid Search Modes Source: https://docs.memvid.com/introduction/welcome Demonstrates how to perform hybrid, lexical, and semantic searches using the Memvid CLI. The 'auto' mode is recommended for combining lexical and semantic search capabilities. ```bash # Hybrid search (recommended) memvid find knowledge.mv2 --query "user authentication" --mode auto # Lexical search - exact keyword matching memvid find knowledge.mv2 --query "authentication" --mode lex # Semantic search - conceptual understanding memvid find knowledge.mv2 --query "how do users log in" --mode sem ``` -------------------------------- ### Search Data with Memvid CLI Source: https://docs.memvid.com/quickstart/five-minute-guide Shows how to perform a lexical search on a Memvid memory using the CLI. This search is available immediately after data ingestion. ```bash # Search works immediately (BM25 lexical search) memvid find knowledge.mv2 --query "who works at AI companies" ``` -------------------------------- ### Check Framework Version Compatibility for Memvid Source: https://docs.memvid.com/errors/troubleshooting This bash command helps you check the installed version of a framework, such as LangChain, to ensure it's compatible with Memvid. Compatibility issues can arise from outdated or unsupported framework versions. ```bash pip show langchain # Check version ``` -------------------------------- ### Installing and Using Memvid CLI Source: https://docs.memvid.com/comparisons/vector-databases Provides bash commands to install the Memvid command-line interface (CLI) using npm, create a new Memvid file, add content to it, and perform a search query. This demonstrates the immediate usability of Memvid without API keys or embedding delays. ```bash # Install (10 seconds) npm install -g memvid-cli # Create and search (10 more seconds) memvid create test.mv2 echo "The quick brown fox jumps over the lazy dog" | memvid put test.mv2 memvid find test.mv2 --query "quick fox" # That's it. No API keys. No embedding wait. Just search. ``` -------------------------------- ### Select Synthesis Model for RAG with Memvid Source: https://docs.memvid.com/concepts/performance-tuning Choose the appropriate synthesis model for RAG tasks based on speed, quality, and cost requirements. Examples show how to specify models for both local and API-based synthesis. ```bash # Fast local synthesis memvid ask memory.mv2 --question "..." --use-model tinyllama # Fast API synthesis memvid ask memory.mv2 --question "..." --use-model groq ``` -------------------------------- ### Memvid Smart Frames Search Examples (Python) Source: https://docs.memvid.com/comparisons/vector-databases Demonstrates various search functionalities within Memvid using Python. Includes exact lexical search, temporal queries based on timelines, entity state retrieval using a knowledge graph, and semantic/hybrid search modes. Requires the 'mem' object to be initialized. ```python # Exact lexical search (instant, no embeddings needed) results = mem.find("handleAuthentication", k=5) # Temporal queries (unique to Memvid) results = mem.timeline("2024-01-01", "2024-01-31") # Entity state (knowledge graph) alice = mem.state("Alice") # {employer: "Anthropic", role: "Engineer"} # Semantic search (when you need it) results = mem.find("cost reduction strategies", mode="vec") # Hybrid search (best of both) results = mem.find("budget optimization", mode="auto") ``` -------------------------------- ### Open or Create Memvid Instance (Node.js, Python) Source: https://docs.memvid.com/quickstart/sdk-recipes Initializes a Memvid instance using the 'basic' provider and a specified file. It supports optional modes like 'auto' and features like enabling lexical search. Dependencies include the '@memvid/sdk' for Node.js and 'memvid_sdk' for Python. ```typescript import { use } from "@memvid/sdk"; const mem = await use("basic", "notes.mv2", { mode: "auto", enableLex: true }); ``` ```python from memvid_sdk import use mem = use("basic", "notes.mv2", mode="auto", enable_lex=True, enable_vec=False) ```