Here's how to use ChatGPT on your own personal files and custom data. Source code: https://github.com/techleadhd/chatgpt-retrieval
Ace your coding interviews with ex-Google/ex-Facebook training. https://techinterviewpro.com/
Make passive income with crypto in DeFi Pro. http://defipro.dev/
???? Get access to 100+ programming interview problems explained: https://coderpro.com/
???? Learn to build a successful business on YouTube from scratch: http://youtubebackstage.com/
???? I'll send you FREE daily coding interview questions to practice your skills: http://dailyinterviewpro.com/
???? My computer and camera gear: https://www.amazon.com/shop/techlead/list/UVRWWQKBFRR
?? My favorite keyboards: http://iqunix.store/techlead
Follow me on social media for more tips & fun:
https://instagram.com/techleadhd/
https://twitter.com/techleadhd/
Disclaimer: This description may contain affiliate links. Cryptocurrencies are not investments and are subject to market volatility.
Source code: https://github.com/techleadhd/chatgpt-retrieval
Ace your coding interviews with ex-Google/ex-Facebook training. https://techinterviewpro.com/
@saamtech Says:
he is such a hater!! haha 😆
@alfadat Says:
Several errors with "Importing chat models from langchain is deprecated", please update the code
@DigsWigs2022 Says:
Suddenly smarter
@gaphonso Says:
Very good video! I was wondering the whole time about the privacy and security of my personal data, but you conveyed this point very well. (11:00) Very good approach and explanation
@itslike123 Says:
Cant you just copy all your data to a new thread then ask questions instead of using phyton
@hacenecherouali5997 Says:
Thanks for the video, I learnt a lot. I tried the script but got errors that took me some times to find a solution. The revision of used modules are important. I succeed with the following configuration (for python 3.9 and 3.11.5):
pip install langchain==0.0.230 openai==0.27.8 chromadb==0.3.25 tiktoken==0.4.0 unstructured==0.8.1 cryptography==41.0.2
@miguelgutierrez716 Says:
Is free trial usage still working? I cant get any credit :'(
@navneetnsit09 Says:
@TechLead:
That mouse looks futuristic. Which model is that?
@noahbennett8074 Says:
holy crap... Dam your good... you should teach!
@MichaelDomer Says:
Question for ChatGPT: "Is there something wrong with that TechLead guy on Youtube?"
ChatGPT: "No comment"
@ghand6158 Says:
Let Python weed the weak ones out TechLead. You'll only be seeing the motivated folks willing to learn and grow!
@webnomad1453 Says:
Hi, it looks like this is not working anymore? Would you have time to update the project on github? There is an error that sends me down a rabbit hole - LangChainDeprecationWarning: Importing vector stores from langchain is deprecated. Importing from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead
@pazesantos Says:
It looks like this code doesn't work anymore. Langchain has changed or something.
@VelkanRF Says:
this code dosent works...if you will share something, makes sure that is usefull
@YoLo-ek6deghhsvjrt Says:
so for the personal custom data, does somebody know is it going to upload the data to openAI server when i use this langchain tool ?
i would like to use this tool , but i dont want my personal data send to openAI
@sivanosh Says:
Is there a limit to the amount of my data that I can upload to my custom Gipiti?
@mikebledig7208 Says:
This thing doesn't work!
I cloned the github. pip installed lanchain, blah blah blah, tried to run the examples, and it just gives a whole lot of errors:
index = VectorstoreIndexCreator().from_loaders([loader])
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain\indexes\vectorstore.py", line 112, in from_loaders
docs.extend(loader.load())
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\directory.py", line 117, in load
return list(self.lazy_load())
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\directory.py", line 180, in lazy_load
yield from self._lazy_load_file(i, p, pbar)
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\directory.py", line 218, in _lazy_load_file
raise e
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\directory.py", line 208, in _lazy_load_file
for subdoc in loader.lazy_load():
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 88, in lazy_load
elements = self._get_elements()
File "C:\Users\Mike\Environments\myenv\lib\site-packages\langchain_community\document_loaders\unstructured.py", line 168, in _get_elements
from unstructured.partition.auto import partition
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\partition\auto.py", line 16, in
from unstructured.partition.email import partition_email
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\partition\email.py", line 59, in
from unstructured.partition.html import partition_html
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\partition\html.py", line 7, in
from unstructured.documents.html import HTMLDocument
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\documents\html.py", line 33, in
from unstructured.partition.text_type import (
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\partition\text_type.py", line 15, in
from unstructured.nlp.english_words import ENGLISH_WORDS
File "C:\Users\Mike\Environments\myenv\lib\site-packages\unstructured\nlp\english_words.py", line 12, in
with open(ENGLISH_WORDS_FILE) as f:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\Mike\\Environments\\myenv\\Lib\\site-packages\\unstructured\\nlp\\english-words.txt'
@saadshajy3849 Says:
We created a number of GPT powered personal AI assistants for businesess like law, media industry and pretty much for corporate companies where they can integrate internal corporate resources and data securely to retrieve useful information and save 70% cost
@alvingultiano519 Says:
I call you boss now .
@dealeras2143 Says:
Thank you sooo much!!!
@jeffersonqiu7071 Says:
Did anyone tried to run this script recently? I kept getting many error messages to install dependecies from langchain-community and even after following all the errors, the script still couldn't run.
@Neellssoonn1 Says:
That part you say about discovering something first and therefore you are smart, it makes a resume of every single civilization in the universe.
@LittleLightCZ Says:
If you use an API key, then it means your personal data are still being uploaded on the servers, or not?
@apricotcomputers3943 Says:
sooo... you talk to your computer 😂
@shantanunarwade Says:
What about the privacy of the training data?
@genemodified Says:
Fascinating … and as a non-coder I enjoy learning the vocabulary used in describing the tech and lots of useful tips. Thanks.
@Benwick921 Says:
Can I replace the dependecy form ChatGPT using their API keys with something offline? If yes can you please make a tutorial? thanks!
@davidtindell950 Says:
Helpful. Thank You!
@aliceiqw Says:
I get this error:
PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH?
@HenryUkwu Says:
can i create an AI mentor for students based on my personal data?
@BogdanCondrat Says:
this is very new technology, the video is already deprecated, doesn't work with the current libraries.
@omarsohail7942 Says:
I have a question what if I only wanted the model to work on my data and not from the other orginal chatgpt data how will it be possible and is it possible to not use any value costing api
@MinisterHenry-jc3vk Says:
Can you get it to watch like 100 videos and then summarize them?
@collinspo Says:
How do I make ChatGPT include the reference (citation) from my custom documents? Thanks
@adamantea Says:
Warning to anyone thinking about starting this - lots of this is deprecated and you'll have to update the scripts before using them, see PR #57
@amrhesham6383 Says:
thank you
@VerdonTrigance Says:
Dude. you said "make this LOCALLY" and then just uploaded it to the openAI. Shame.
@duckyy8655 Says:
How would I go about doing this with locally downloaded ai
@user-pl2pg7yn3f Says:
Instead of data.txt, can we use data.csv? My data is saved in excel.
@eskoonlysflow8004 Says:
how big can the .txt file be? Is it limited or can i put in analysis 1gb .txt file? Thanks
@hichamalaoui34 Says:
May be 8 months late and Langchain has been updated since, but this is one of the best videos I watched. Thank you.
@Meviler Says:
Thank you sensei!
@muhammadowais8609 Says:
Really enjoyed the video, that 16min video was big pool of answers for me to solve a problem which i wanted too. Amazing video
@Ovrlordz Says:
With the API is this running completely local? If not what does the API pass?
@kaniki_the_problem Says:
After a sabbatical , I have come back to the mighty Tech LEAD !!!
@IdowuOlayiwola Says:
The whole code seems to be deprecated
@gerryscat Says:
How much data? What format, just a few text files?
@user-sh9el7pq8e Says:
It looks like code and methods used in his video has been deprecated and no longer working.
@ArtisticGurus Says:
Great tutorial! In this model (your image workflow), does the "LLM" after finding an answer send data back to the ChatGPT cloud? So for instance, is this data now available (learned by) all ChatGPT? Does your data stay your data or is it potentially leaked. Thanks for your help!
LATEST COMMENTS