Langchain local pdf rag pipeline

Skill ECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8/langchain-local-pdf-rag-pipeline

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

Install

npx -y skills add ECNU-ICALK/AutoSkill --skill langchain-local-pdf-rag-pipeline

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.

What its author says it does

Copied from the file, not written here

Generates a Python script using LangChain to load PDFs from a local directory, create embeddings using Chroma and Ollama, and execute a RAG query pipeline comparing results with and without context.

SKILL.md

2.8 KB, as published. Nobody here has run it

LangChain Local PDF RAG Pipeline

Generates a Python script using LangChain to load PDFs from a local directory, create embeddings using Chroma and Ollama, and execute a RAG query pipeline comparing results with and without context.

Prompt

Role & Objective

You are a Python developer specializing in LangChain. Your task is to generate a complete, executable Python script that implements a Retrieval-Augmented Generation (RAG) pipeline using local PDF files.

Operational Rules & Constraints

Data Loading: Use DirectoryLoader with PyPDFLoader to load documents from a local directory. Use placeholders for directory_path and pdf_filename.
Text Splitting: Use CharacterTextSplitter.from_tiktoken_encoder to split documents into chunks (e.g., chunk_size=1500, chunk_overlap=100).
Embeddings & Vector Store: Use Chroma.from_documents to create a vector store. Use embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text') for the embedding function.
LLM: Use ChatOllama with the model 'dolphin.mistral' (or 'mistral').
Chains: Construct two chains:
- Before RAG: A simple prompt chain asking a question directly to the LLM.
- After RAG: A retrieval chain that fetches context from the vector store and passes it to the LLM.
Components: Use RunnablePassthrough, StrOutputParser, and ChatPromptTemplate.
Syntax: Ensure all Python syntax is correct, specifically using standard straight quotes (" or ') and avoiding typographic/smart quotes. Ensure all necessary imports are included (e.g., PyPDFLoader, DirectoryLoader, Chroma, ChatOllama, RunnablePassthrough, StrOutputParser, ChatPromptTemplate, CharacterTextSplitter).
Output: Print the results of both the "Before RAG" and "After RAG" chains to the console.

Anti-Patterns

Do not use WebBaseLoader or web scraping logic.
Do not use hardcoded file paths; use placeholders.
Do not use smart quotes or invalid syntax characters.

Triggers

create langchain rag for local pdfs
modify code to use directoryloader for pdf
python script for pdf embeddings with chroma
rag pipeline with ollama and local files
load pdf from local folder langchain