Basic RAG with LangChain and LangGraph - Ollama

Learn how to run ulama, manage models via the CLI, and explore available llama and gemma models, their downloads, updates, and quantization options.

Explore the 1 billion parameter llama model, detailing eight-bit quantization, instruction-tuned architecture, 32 attention networks across 16 decoder blocks, and template-driven tool and function calling in LangChain and LangGraph.

Discover the range of Ollama models, from general purpose to code-specific options like code generation and Code Gemma, and learn how multimodal Lava handles image and text tasks with LangChain.

Learn to run llama 3.2 with ollama, start the llama server on localhost:434, and use show to inspect models, compare 1B and 3B parameters, quantization, and tool calling details.

Learn to manage models with ollama pull, run, list, and rm, pull embedding models, inspect details such as context length and quantization, and remove unused models.

copy and rename a model with Ollama cp, run it from a copy, chat with it in chat mode, check ps, and stop with Ollama stop, noting the five-minute offload.

Create and run an Ollama model from a predefined model file using the create command with model file.txt, loading from llama 3.2 and setting temperature, context, and a system message.

Learn to use the llama model command to load llama 3.21 billion model and compare with the Seldon model, view inside commands, and manage parameters, system messages, and templates.

Learn to use Ollama's set, save, and load commands to configure system messages, enable or disable history, store and load models, and observe verbose diagnostics.

Discover how to interact with the Ulama raw API, using generate and chat endpoints, and learn to configure model, prompt, system messages, and context for effective outputs.

Learn to load uncensored models from Hugging Face into llama, download an older uncensored model, and run educational prompts to explore capabilities while noting legal and ethical restrictions.

Explore how LangChain acts as a middleman between you and Ollama, enabling text generation, chat completion, and RAG workflows with Python, prompts, and multiple integrations.

Set up Lang Smith observability for LangChain by creating an API key, storing it in a .env file, and enabling lang chain tracing v2 with the endpoint.

Discover how to call your first LangChain Ollama API by wiring the base URL to a local llama model, selecting a chat model, and invoking input to obtain output.

Explore generating uncensored content in LangChain by switching between Seldon, Sherlock, and uncensored models, and learn to stream token-by-token outputs for educational purposes.

Track and analyze LLM inputs and outputs in Lang Smith, viewing runs, latency, token usage, and model metadata; use Lang Fusion or Opic for private data.

Explore how the line graph is inspired by flow networks and network X, and how LangGraph extends LangChain to model nodes, edges, and directed flows.

Explore the line graph in the Lang graph library by reviewing GitHub repository, its APIs, and memory design using type hinting that stores agent state with nodes and tool nodes.

Explore LangGraph at a high level: create a state graph with nodes and edges, show how a message state, agent and tool nodes, and conditional edges drive workflow.

Explore the LangGraph line graph module, and learn how to import graph components from the line graph package and its memory checkpoints, while understanding why the GitHub repository context matters.

Set up LangGraph with Ollama by wiring start and end nodes, loading environment variables, and connecting a local Chatto Llama model to a line graph for interactive coding.

Build and visualize a LangGraph with Ollama by adding nodes and edges, compiling, invoking with messages, looping user input, and exploring type hints and class relationships.

Explore OpenAI and the Llama Vision model to describe images in PDFs for RAG workflows. Compare local Llama Vision with OpenAI API for faster image descriptions and setup.

Explore how the OpenAI vision guide enables multi-modal input by combining text and image data, and compare hosting an LLM versus using the Llama Vision API for RAG workflows.

Learn to generate image descriptions using LangChain, Ollama, and LLAMA Vision by converting images to base64 and querying a local model, with notes on OpenAI for image description.

Learn to create an OpenAI API key, set up billing and environment variables, and monitor usage for secure, cost-aware OpenAI API access.

Load the OpenAI API key from a dot env file and compare private LM with the llama local LM and OpenAI chat GPT-4 for generating image descriptions.

Explore converting a pdf to markdown with doc link to improve LLM understanding, compare doc link and markdown options, and integrate with LangChain doc link loader.

Learn to convert online documents to markdown with LangChain doc link loader and document loader, configure export types, and manage local paths for seamless markdown output.

Load a pdf with Lang chain doc link and doc link loader, export as markdown, and convert document pages into a markdown file for easy editing.

Develop a Python function using the doc link loader to convert a source file to markdown in a target directory, extracting the file name with pathlib and appending .md.

Learn how to use os.walk to enumerate all files in a directory, build a relative output path, and convert documents into markdown stored in a markdown folder.

Use os.walk to traverse directories, filter for PDF, Microsoft documents, PPT, and Excel files, and convert them into structured markdown outputs stored in a target directory.

Discover how to extract images from pdf or docx documents, describe them with vision models, and convert image data into text or tabular form for extraction.

Learn to extract images from a pdf, convert figures to markdown with embedded or referenced images, and generate text descriptions using a language model.

Split markdown data page by page with LangChain's markdown header splitter to isolate each page's content, then pass content and images to an LLM for per-page image descriptions.

Extract images from page content with regex, collect image urls and clean text, then generate image descriptions with a language model to enrich markdown.

Compare enriched markdown with bare markdown by showing image enrichment, extracted image descriptions, and producing a perfect markdown file for lm-driven rag data workflows.

Learn the simplest rag architecture: ingest markdown files into a vector database, chunk by headings, encode with llama embedding, and use a basic agent to retrieve and answer.

Load markdown files, split content by headings with LangChain’s markdown header splitter, configure header retention, attach company metadata, and prepare chunks for vector store ingestion in a RAG workflow.

Generate text embeddings using the gnomic embedded text model from llama via ollama. Store vectors in an in memory doc store and index them for ingestion into a vector database.

Learn how to retrieve documents from a FAISS vector store using embeddings, cosine similarity, and MMR to fetch top relevant chunks, and apply filters to target specific companies.

Learn to store and load a FAISS vector store by saving and loading a vector DB to local paths, then create a retriever with a search type and k three.

Build an agentic rag that ingests and retrieves documents in a vector store, then uses an LLM and a retriever to generate answers, rewriting queries when needed.

Learn to build a custom retriever that filters at runtime, connecting a vector store and LLM to deliver precise answers from top 3 MMR results.

Build a document grading node to determine document relevance to a user query, using a binary yes/no score to decide generate or rewrite actions within an agent workflow.

Implement an agent node that uses the graph state to decide retrieval via the retriever tool or end, then generate or rewrite the answer with the analyst tool.

Connect and configure the final agent graph by wiring agent, retriever tool, rewrite, and generate nodes with conditional edges; compile the graph and run the agent in autonomous mode.

Watch how an agent retrieves documents, checks relevance, and decides to rewrite or generate a final answer, streaming output in three-sentence bursts and comparing across queries like Facebook and Google.