Cargar y dividir archivos de código

Retrieval Augmented Generation (RAG) con LangChain

Meri Nova

Machine Learning Engineer

Más cargadores de documentos...

Una selección de distintos formatos de archivo.

El markdown en bruto usado para crear el archivo README del repositorio de GitHub de LangChain.

Markdown renderizado del README.md de GitHub de LangChain.

Cargar archivos Markdown (.md)

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'})

Cargar archivos Python (.py)

from abc import ABC, abstractmethod

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

...

Integrado en apps RAG para escribir o corregir código, crear docs, etc.
Imports, clases, funciones, etc.

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'})

Dividir archivos de código

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."

Dividir por lenguaje

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):

¡Vamos a practicar!

Retrieval Augmented Generation (RAG) con LangChain