Anyone having trouble with the code, llama index updated the name "of "GPTSimpleVectorIndex" to "GPTVectorStoreIndex". Just replace them and it should work if that is the error you are getting
Sorry, I am a novice in the area of AI, but I have a typical management question: What would it need to being able to use my own knowledge bot WITHOUT feeding the critical information to meta, Google or openai? Or: how can I ensure that my data is safe? By the way: great content- much appreciated
I am looking for an asnwer for this too. I think the answer is you need to run the chatbot locally/on a server you control. There are many different ways to do this, including using Portainer + Docker (this is what I was told by a exeriences coder)
Hi, I have a problem with the OpenAI API rate limit when using large set of data. This is when loading the GPTSimpleVectorIndex. For small data sets it's okay. Can u advise?
I keep getting this error despite creating a brand new OpenAI account. I'm trying to create a chatbot that can read from a pdf file. How do I fix this error: "You exceeded your current quota, please check your plan and billing details" There's no way I can exceed if I literally just created my account...
I can't use the custom code for some reason. it says OpenAI is not defined here: llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002")). I tried from openai import OpenAI but it is not working. Any suggestions anyone?
I am still getting this error. NameError Traceback (most recent call last) Cell In[37], line 6 2 from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper 5 # define LLM ----> 6 llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002")) 7 from langchain import OpenAI 8 from openai import OpenAI NameError: name 'OpenAI' is not defined
@@LiamOttley understandable, you have been one of the best teachers when it comes to AI and how to leverage it! If your able to do a video on it in the future it would definitely help a lot. Until then I’ll be waiting for your next video!
I edited this because I want to emphasize the importance of search (and how poor RUclips search is). I had a vein in the center of my forehead trying to do this on my own about three weeks ago....and I'm only seeing Liams video now. Get your search alerts and notifications down during this revolution, and you just may be lucky enough to find the Liams of this world giving you a play-by-play breakdown of exactly what you want in your AI build.
Hey Liam! Awesome thanks...can you do a follow-up on an addon to index a website like a blog? And have the output to include a link to the article used for the answer so users can click through to read more?
Looks like it doesn't work, after some research it looks like they renamed GPTSimpleVectorIntex to GPTVectorStoreIndex. What version of Llama_index are you using?
isn't this limited by tokens from the openai api? like if i want to load 500 doucments it wouldn't work right? if so is there any way to run these models locally
bro, do you know if any of them will let me create a chatgpt clone that users can input stories but they contain profanity, and the chatgpt able to reply with profanity, im using it for story scripts
Great video!. I have some questions: 1) When we create an index, I understand that what's going on is that somehow based on the question we know which part of the files inside the index should be used to reply to it, and this is context information given to GPT as part of the prompt. Is that the case? 2) Is there a limit in how bit this index can be?
Hey Liam, sorry not sure what Jupiter is, is that what your running the code in? Assuming we can run this locally? Also how would you integrate this into something you built, by referencing this new model or what within Open AI? Would like some more details on the code your using and integration???
This is all Python code running in Jupyter notebook. Super easy install with the anaconda launcher. Deploying apps is a bit trickier so you’d probably want to play around with things on your own as I am then hire a developer once you’re happy with it to create a product out of it
Hello, How can I increase response message length (maybe token limit I guess) . After I train data and ask question answer is not complete and token shows always not more than 2500 600 etc
I'm so confused, did you skip a step when we got to the llama index section. Is there a video I need to watch before this, this doesn't make any sense to me.
Hey Liam! Great video mate 🙌 Can I ask if this can generate responses in a particular json format if needed after indexing any document? Thanks again for the video!
Is this the best approach to export thousands of ChatGPT conversations and then be able to search that data (I'm a prolific writer)? Does it import and structure (or show you how) automatically? OR is there a better tool for doing that? Thanks in advance for any helpful answers. I'm NOT a programmer so that is an important consideration.
Hey man I know this was months ago but the new llama index has different names for some of the stuff in your code, creating problems when running the code. Is it possible for an update on this?
My question is will doing this bypass the content filter of ChatGPT? Could I host GPT and use llama-index or something to do that? No, it's not for sexy time. It won't talk about a lot of things like stock trading or cybersecurity because it flags it as bad content and gives an excuse instead of responding.
I've spent hours on this to no avail due to an error "TypeError: __init__() got an unexpected keyword argument 'llm_predictor'". While i've been able to bypass the error, it seems like there is still an issue because as I change the temperature and OpenAI model, the output is identical every-time, which shouldn't be the case. ***Note, the first index iteration is commented out intentionally for debugging.*** Any idea on how to fix this? The solution 'seemed to be' specifying variables: "# Create a new GPTSimpleVectorIndex with custom LLM predictor and prompt helper custom_LLM_index = GPTSimpleVectorIndex.from_documents(documents) custom_LLM_index.llm_predictor = llm_predictor custom_LLM_index.prompt_helper = prompt_helper" ### code being used: import os os.environ['OPENAI_API_KEY'] = "API KEY" from llama_index import SimpleDirectoryReader from langchain import OpenAI from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper # Load your data into 'documents' a custom type by Llamaindex documents = SimpleDirectoryReader('./Documents/Jupytr Docs/llama_doc_index/data').load_data() # Create an index from your documents ##index = GPTSimpleVectorIndex.from_documents(documents) # Query your index ##response = index.query("what is the article about") ##print(response) # Define another LLM explicitly llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002")) # Define prompt configuration max_input_size = 4096 num_output = 256 max_chunk_overlap = 20 prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap) # Create a new GPTSimpleVectorIndex with custom LLM predictor and prompt helper custom_LLM_index = GPTSimpleVectorIndex.from_documents(documents) custom_LLM_index.llm_predictor = llm_predictor custom_LLM_index.prompt_helper = prompt_helper # Query your custom index response = custom_LLM_index.query("what is the article about") print(response)
Do I get this right, that also with gpts API, if you build an App on your website; each time a new user is accessing the chat, you have to pass all the data again to the gpts API? so it costs everytime some tokens to "prepare" the chat bot for my new user, right?
Dear Liam, great stuff. Already subscribed and looking forward to learn from you. A question: how to increase the length of the output ? I am using it to document some code and it stops before completing the task entirely. many thanks
Any way I can save the index for later reloading it? Can one add several type of things to the same index? Like Wikipedia pages and also pdf documents and maybe calender? All would go to the same index? Or how would it work? For the calendar, I assume it would need to be refresh on a regular basis, how does one refresh part of the index (the calendar part)?
Hi Liam! I'm interested to build a chatbot for an internal website, however, I worry that this might caused information leakage. What's your opinion on this?
Very good. How do we train the bot to be context oriented? If I only want the bot to have knowledge of radio controlled cars for example. At the moment I can ask this bot about what's in its index, but I can also ask it about washing machines and it will answer.
Leave your questions below! 😎
📚 My Free Skool Community: bit.ly/3uRIRB3
🤝 Work With Me: www.morningside.ai/
📈 My AI Agency Accelerator: bit.ly/3wxLubP
Could you please show us how to deploy this to a web app, so it can be used in a web app?
Is whole thing free?
God bless the algorithm for showing this channel to me!
🙏🏼 🙏🏼 🙏🏼
Same!
Amen😂
Maybe the algorithm is God 😮
The AI beast dropping knowledge bombs again! Awesome video Liam, punchy, engaging and dripping with actionable content 👏🏼 Cutting edge stuff.
Anyone having trouble with the code, llama index updated the name "of "GPTSimpleVectorIndex" to "GPTVectorStoreIndex". Just replace them and it should work if that is the error you are getting
omg thank you! You've helped me not have to categorise my grocery shopping list into fruit, meat etc. manually.
Nice one Liam, always enjoying your contents.
Much appreciated mate, glad I could help!
Yes an update to this with GPT 3.5 turbo (current model) would be incredible.
really cool stuff! Musch more efficient than traditional methods of custom training the model or making custom responses. Thanks a lot!
Cracking video ! Short, sharp and focused ! Information is spot on and really helpful. Thanks! Looking forward to seeing more good content.
The code isn't working anymore, got stuck with an error on GPTVectorStoreIndex. The libraries you have used have been modified.
Replace with GPTSimpleVectorIndex
Sorry, I am a novice in the area of AI, but I have a typical management question:
What would it need to being able to use my own knowledge bot WITHOUT feeding the critical information to meta, Google or openai? Or: how can I ensure that my data is safe?
By the way: great content- much appreciated
I am looking for an asnwer for this too. I think the answer is you need to run the chatbot locally/on a server you control. There are many different ways to do this, including using Portainer + Docker (this is what I was told by a exeriences coder)
Yeah I would like a video specifically on this
Did you find any solutions?
@@workinprogress2077 Did you find any solutions?
@@bl8596 Did you find any solutions?
you deserve tones of subscribers
Thank you, I've been looking for something like this for weeks
Thanks for making this!
Liam never disappoints :)
Thanks mate 💪🏼
Hi, I have a problem with the OpenAI API rate limit when using large set of data. This is when loading the GPTSimpleVectorIndex. For small data sets it's okay. Can u advise?
Great vid as always!
Appreciate it g
Liam, thanks for sharing this information. This is quality stuff.
Glad you enjoyed it 🙏🏼
@@LiamOttley wish i knew 5% of how to get any idea started, ugh, thanks you are golden
Put speed for the video at 0.75 - Liam speaks really fast!
Thank you, i can already see how to use it in education.
I really like your content, thank you!
Thanks for watching 🤝
Great video as always. Keep up the good work. Wish you very best of luck for your channel. I hope it will rock in the near future.
Super interesting ! Thank you, Liam ! I was wondering how can we see the model used, and if we can control the temperature ?
Code doesn;t work anymore because from llama_index import GPTSimpleVectorIndex throwing an error now.
At:
# Setup your LLM
from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper
# define LLM
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002"))
# define prompt helper
# set maximum input size
max_input_size = 4096
# set number of output tokens
num_output = 256
# set maximum chunk overlap
max_chunk_overlap = 20
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)
custom_LLM_index = GPTSimpleVectorIndex(
documents, llm_predictor=llm_predictor, prompt_helper=prompt_helper
)
I'm getting:
NameError Traceback (most recent call last)
Cell In[16], line 7
3 from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper
6 # define LLM
----> 7 llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002"))
9 # define prompt helper
10 # set maximum input size
11 max_input_size = 4096
NameError: name 'OpenAI' is not defined
I am having the same error message. 😢
I have been trying to find solution to this without success...😭
@Mr_LiamOttley........... yes sir?
thank you for the video. What is the difference between using LlamaIndex vs Langchain? thank you
I keep getting this error despite creating a brand new OpenAI account. I'm trying to create a chatbot that can read from a pdf file. How do I fix this error: "You exceeded your current quota, please check your plan and billing details"
There's no way I can exceed if I literally just created my account...
Awesome video! Going to mess around with all this as my first steps into AI programming... well sorta first steps anyway!
Thank you. It is a vit above my head
I can't use the custom code for some reason. it says OpenAI is not defined here: llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002")).
I tried from openai import OpenAI but it is not working.
Any suggestions anyone?
You need to add : from langchain import OpenAI
@@JebliMohamed good man
Thanks Jebli
I am still getting this error.
NameError Traceback (most recent call last)
Cell In[37], line 6
2 from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper
5 # define LLM
----> 6 llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002"))
7 from langchain import OpenAI
8 from openai import OpenAI
NameError: name 'OpenAI' is not defined
@@millerco2000 from langchain import OpenAI this fixed it for me
Amazing tutorial! subscribed
Great pacing and demo, thank you for the tutorial.
Hi, do I have to pay for open_ai key?
Great video
Respect for sharing your files 🙏
It seems anyone will be able to do this soon. The value will be in the data. Can you use AI to gather the data to train in on?
very informative video! Could we get a video on langchain soon? 👀
Quite a big beast to tackle, hard to not make it too technical for most of my viewers :/
@@LiamOttley understandable, you have been one of the best teachers when it comes to AI and how to leverage it! If your able to do a video on it in the future it would definitely help a lot. Until then I’ll be waiting for your next video!
Getting the error "chunk_overlap_ratio must be a float between 0. and 1.", any solution for this guys?
Thanks. for sharing the skills
Fantastic! Thank you.
FYI, "GPTSimpleVectorIndex" changed to "GPTVectorStoreIndex"
oh..... now imagine throwing in all the D&D PDF's into one simple bot :D
I edited this because I want to emphasize the importance of search (and how poor RUclips search is). I had a vein in the center of my forehead trying to do this on my own about three weeks ago....and I'm only seeing Liams video now. Get your search alerts and notifications down during this revolution, and you just may be lucky enough to find the Liams of this world giving you a play-by-play breakdown of exactly what you want in your AI build.
Very kind words mate glad I could help ❤️🙏🏼
Wow impressive video, thsnk you so much!
Thankyou, great video
Great Video. Thanks for sharing. 🎉
Extremely cool! Looking forward to more awesome content.
I would like to see a Javascript version of this
Not sure if there are javascript equivalents for libraries like Llamaindex
Hey Liam! Awesome thanks...can you do a follow-up on an addon to index a website like a blog? And have the output to include a link to the article used for the answer so users can click through to read more?
Amazing Liam bro..
🤝
Looks like it doesn't work, after some research it looks like they renamed GPTSimpleVectorIntex to GPTVectorStoreIndex. What version of Llama_index are you using?
Superb Video, I loved it. ❤❤❤
Awesome video...thanks bro
My pleasure mate
isn't this limited by tokens from the openai api? like if i want to load 500 doucments it wouldn't work right?
if so is there any way to run these models locally
Great info!
Question: the information that we index, is this shared with an external server loosing its confidentiality, or it just remain in the users computer?
I've the exact same question
Fucking brilliant man. Keep up the mad hustle.
bro, do you know if any of them will let me create a chatgpt clone that users can input stories but they contain profanity, and the chatgpt able to reply with profanity, im using it for story scripts
Well done Liam
Great video!. I have some questions:
1) When we create an index, I understand that what's going on is that somehow based on the question we know which part of the files inside the index should be used to reply to it, and this is context information given to GPT as part of the prompt. Is that the case?
2) Is there a limit in how bit this index can be?
Hey Liam, sorry not sure what Jupiter is, is that what your running the code in? Assuming we can run this locally? Also how would you integrate this into something you built, by referencing this new model or what within Open AI? Would like some more details on the code your using and integration???
This is all Python code running in Jupyter notebook. Super easy install with the anaconda launcher. Deploying apps is a bit trickier so you’d probably want to play around with things on your own as I am then hire a developer once you’re happy with it to create a product out of it
Hello, How can I increase response message length (maybe token limit I guess) . After I train data and ask question answer is not complete and token shows always not more than 2500 600 etc
Good guy Liam!
Thanks g x
Wow! Can we use any open source llm model instead of using openai api key?
If I have a PDF of 300 Pages, will it still work as I saw another video using Lanchain and Pinecore (to store vector data for 300 pages)
Good question, I haven't seen anything on limits for these kinds of indexes so worth testing. Ask different questions about info on sample pages?
Thanks, but I can't see any code that 'prompt' variable is used for openai's api.
Can u explain how can the chatbot remember previous chat?
I figured out it.
Need to modyify as query(prompt) intead of query(user_input)
🙏🏼
can we teach it to iteratively improve its own code?
Does this training of the knowledge base, cut into the token limit?
Does the ChatGPT api key required for this to work? And if so does it cost money to use llma?
keep making great videos
🤝
I'm so confused, did you skip a step when we got to the llama index section. Is there a video I need to watch before this, this doesn't make any sense to me.
Can something like this be used with sensitive business data? Is OpenAI consuming and storing all of this data as its being indexed?
Very good. Need a nice front end and link to a vector db like Pinecone
Is there a file size limit for a txt file? And if you upload a large file, does it take a long time to respond to the query?
Not sure if I got it wrong, but it means we have to pay for an openAI key, it's not free, is it?
does this method prevent chatGPT from using/learning from the indexed data?
can any one help me why am i getting Ratelimit error while using GPTVectorStoreIndex(documents) with my openai key? and suggest me how tackle this
Same issue, here, did you solve it?
Great video! I was just wondering if it is possible to make it less expensive, because when I use big data bases it uses a lot of tokens.
GPT 3.5 Turbo is extremely cheap, hopefully they add support for it soon instead of davinci-003
Hey Liam! Great video mate 🙌
Can I ask if this can generate responses in a particular json format if needed after indexing any document?
Thanks again for the video!
Is this the best approach to export thousands of ChatGPT conversations and then be able to search that data (I'm a prolific writer)? Does it import and structure (or show you how) automatically? OR is there a better tool for doing that? Thanks in advance for any helpful answers. I'm NOT a programmer so that is an important consideration.
Do you know if there is a way to use multiple sources for the documents? For instance can you use text docs AND discord?
Thankyou so much..!!
wow!!!! than you so much !!!
Hey man I know this was months ago but the new llama index has different names for some of the stuff in your code, creating problems when running the code. Is it possible for an update on this?
My question is will doing this bypass the content filter of ChatGPT? Could I host GPT and use llama-index or something to do that? No, it's not for sexy time. It won't talk about a lot of things like stock trading or cybersecurity because it flags it as bad content and gives an excuse instead of responding.
Good question, I'd assume because it's just using your API key and davinci-text-003 or whatever you set it as then it would still hit the filter
I've spent hours on this to no avail due to an error "TypeError: __init__() got an unexpected keyword argument 'llm_predictor'". While i've been able to bypass the error, it seems like there is still an issue because as I change the temperature and OpenAI model, the output is identical every-time, which shouldn't be the case. ***Note, the first index iteration is commented out intentionally for debugging.*** Any idea on how to fix this?
The solution 'seemed to be' specifying variables:
"# Create a new GPTSimpleVectorIndex with custom LLM predictor and prompt helper
custom_LLM_index = GPTSimpleVectorIndex.from_documents(documents)
custom_LLM_index.llm_predictor = llm_predictor
custom_LLM_index.prompt_helper = prompt_helper"
### code being used:
import os
os.environ['OPENAI_API_KEY'] = "API KEY"
from llama_index import SimpleDirectoryReader
from langchain import OpenAI
from llama_index import LLMPredictor, GPTSimpleVectorIndex, PromptHelper
# Load your data into 'documents' a custom type by Llamaindex
documents = SimpleDirectoryReader('./Documents/Jupytr Docs/llama_doc_index/data').load_data()
# Create an index from your documents
##index = GPTSimpleVectorIndex.from_documents(documents)
# Query your index
##response = index.query("what is the article about")
##print(response)
# Define another LLM explicitly
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.1, model_name="text-davinci-002"))
# Define prompt configuration
max_input_size = 4096
num_output = 256
max_chunk_overlap = 20
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)
# Create a new GPTSimpleVectorIndex with custom LLM predictor and prompt helper
custom_LLM_index = GPTSimpleVectorIndex.from_documents(documents)
custom_LLM_index.llm_predictor = llm_predictor
custom_LLM_index.prompt_helper = prompt_helper
# Query your custom index
response = custom_LLM_index.query("what is the article about")
print(response)
Very Interesting
How do I break the word limit for an answer,Sometimes the answer feels half, not quite ,How can I modify it thank you
great stuff, looking to tie this out as a slack bot to answer questions from employees for various business facing items contained in our KB
Hello, if I use the Google docs loader, will the file be updated every time I update the Google doc?
GPTSimpleVectorIndex is not a import that llama_index has?
Do I get this right, that also with gpts API, if you build an App on your website; each time a new user is accessing the chat, you have to pass all the data again to the gpts API? so it costs everytime some tokens to "prepare" the chat bot for my new user, right?
Exactly
Dear Liam, great stuff. Already subscribed and looking forward to learn from you. A question: how to increase the length of the output ? I am using it to document some code and it stops before completing the task entirely. many thanks
often the token limit is too low
Great content! How would you get around the response character limit using this example?
Any way I can save the index for later reloading it? Can one add several type of things to the same index? Like Wikipedia pages and also pdf documents and maybe calender? All would go to the same index? Or how would it work? For the calendar, I assume it would need to be refresh on a regular basis, how does one refresh part of the index (the calendar part)?
What do you recommend to build a construction engineering contractor estimating cooperation
Thanks
Hi Liam! I'm interested to build a chatbot for an internal website, however, I worry that this might caused information leakage. What's your opinion on this?
I’d say OpenAI is taking privacy pretty seriously. I wouldn’t be worried personally, people have built huge apps using their APIs already.
Very good. How do we train the bot to be context oriented? If I only want the bot to have knowledge of radio controlled cars for example. At the moment I can ask this bot about what's in its index, but I can also ask it about washing machines and it will answer.
I guess this information are still go through OpenAI's Server, right?
Isn't that an issues according to data privacy of the costumer?
How is this different from using langchain?
Really cool video
Very nice! Does this thing run locally? Especially if there is no internet connection available.