Langchain Document Loaders Part 1: Unstructured Files

This video is the first of many I will be doing about Langchain. Please see the relevant links below:

Other links:

[paulomarcos]

Bro, this content helped me a lot. Thanks. Hugs, here from Florianópolis, Bazil!

[oscargalvez]

Nice tutorial, I am getting into the langchain world and the chunks explanation was very explanatory, thanks!!

[everybodyguitar]

Is image or table considered as unstructured document?

[endo]

looking for Langchain Document Loaders Part 2. unless there is none id suggest to take it off.

[himanshushrivastava]

Thanks for the tutorial Merk! By following and understandinng your tutorial, I have developed a chatbot using GPT and LangChain framework that can provide answers from a given document. However, this chatbot is limited to the document’s information only. I want to create a chatbot that can integrate its own data with the document’s data. How can I achieve this?

[komalsiddharth]

def load_pdf(data):
loader = DirectoryLoader(data,
glob="*.pdf",
loader_cls=PyPDFLoader)

documents = loader.load()

return documents

this is my function..but i m getting file not found error while loading my documnet, ,
can someone help plz

[tradingwithwill]

there are some pip installs required. docs are confusing as to which ones via notebook

[Vrilogs]

hello, once we try loading multiple documents, the speed at which it loads is super slow. Any help or suggestions to increase the speed would be helpful, thank you!

[RS-vuum]

Hi,
Have you uploaded the Part 2 of this video?

[ChuckWilliamsTechnology]

Can you share your notebook file...thanks a ton

[ronakdinesh]

can i load multiple pdfs and also get the references?