Codebestanden laden en splitsen

Retrieval Augmented Generation (RAG) met LangChain

Meri Nova

Machine Learning Engineer

Meer documentloaders...

Een reeks verschillende bestandsindelingen.

De ruwe markdown voor het README-bestand in de GitHub-repo van LangChain.

Weergegeven markdown uit het README.md-bestand op LangChains GitHub.

Markdown-bestanden (.md) laden

from langchain_community.document_loaders import UnstructuredMarkdownLoader


loader = UnstructuredMarkdownLoader("README.md")

markdown_content = loader.load()
print(markdown_content[0])

Document(page_content='# Discord Text Classification ![Python Version](https...'
         metadata={'source': 'README.md'})

Python-bestanden (.py) laden

from abc import ABC, abstractmethod

class LLM(ABC):
  @abstractmethod
  def complete_sentence(self, prompt):
    pass

...

Ingezet in RAG-apps voor code schrijven/fixen, docs maken, enz.
Imports, classes, functies, enz.

from langchain_community.document_loaders \
    import PythonLoader

loader = PythonLoader('chatbot.py')


python_data = loader.load()
print(python_data[0])

Document(page_content='from abc import ABC, ...

class LLM(ABC):
  @abstractmethod
...',
metadata={'source': 'chatbot.py'})

Codebestanden splitsen

python_splitter = RecursiveCharacterTextSplitter(
    chunk_size=150, chunk_overlap=10
)


chunks = python_splitter.split_documents(python_data)
for i, chunk in enumerate(chunks[:3]):
    print(f"Chunk {i+1}:\n{chunk.page_content}\n")

Chunk 1:
from abc import ABC, abstractmethod

class LLM(ABC):
  @abstractmethod
  def complete_sentence(self, prompt):
    pass

Chunk 2:
class OpenAI(LLM):
  def complete_sentence(self, prompt):
    return prompt + " ... OpenAI end of sentence."

class Anthropic(LLM):

Chunk 3:
def complete_sentence(self, prompt):
    return prompt + " ... Anthropic end of sentence."

Splitsen per taal

separators
- ["\n\n", "\n", " ", ""]
- ["\nclass ", "\ndef ", "\n\tdef ", "\n\n", " ", ""]

from langchain_text_splitters import RecursiveCharacterTextSplitter, Language

python_splitter = RecursiveCharacterTextSplitter.from_language(

    language=Language.PYTHON, chunk_size=150, chunk_overlap=10

)


chunks = python_splitter.split_documents(data)


for i, chunk in enumerate(chunks[:3]):
    print(f"Chunk {i+1}:\n{chunk.page_content}\n")

Chunk 1:
from abc import ABC, abstractmethod

Chunk 2:
class LLM(ABC):
  @abstractmethod
  def complete_sentence(self, prompt):
    pass

Chunk 3:
class OpenAI(LLM):
  def complete_sentence(self, prompt):

Laten we oefenen!

Retrieval Augmented Generation (RAG) met LangChain