OMG someone took the time to talk about usage costs. No one has yet herded up usage case scenarios in relation to cost from major AI vendors. Thanks for your consideration in this area.
At this point it doesn't get any easier than that! I was able to drop in a technical document that makes my eyes bleed when I read it and just start asking questions of it instead. Great job! If someone would bundle this up into a nice little application and let me aim it at directories full of documents I think they could make a boatload of money.
@@blockchainbrudda3051 aka "folders" Like D:/Technical Documents/ I can't wait for the day when SharePoint has AI assistance built in so a company can ask natural language questions of their business content and get back Chat-GPT style answers with links to the source material. It'll be a revolution for content management and productivity.
no dude its still giving me an error. please can you have another look? Notebook loading error There was an error loading this notebook. Ensure that the file is accessible and try again. Request had invalid authentication credentials. Expected OAuth 2 access token, login cookie or other valid authentication credential. See developers.google.com/identity/sign-in/web/devconsole-project.
A very clear explanation. Before this video, I was confused about the purpose of embeddings and how the actual answers are produced and the video explained it very well.
ChatPDF is also good. I have used it.. and its free for 120 pages, 3 PDFs/day, and 50 questions/day... one can pay $5 per month to get very good upgrades
what is the approx cost of API, if I use a University Subject's textbook with 1000 pages? I mean cost of embedding the pdf data to model and also the search cost for questions. Can you tell the cost in the form of API pricing or tokens?
Wow, I stared at that opening graph for like 10 minutes being in awe, realizing the implications and uses, marveling at the elegance. This is insanely similar to an approach I thought of to extract new information during conversation, but this is more elegant. I should start making graphs of my approaches, since they do tend to get pretty complex and sometimes I lose track of what I'm doing or trying to do.
Thanks for a very instructive video and learned quite a bit from your step by step guide. Much appreciate the effort you put in & you have inspired me to keep expanding my knowledge in this area. Thank you.
The Best tool for this is ruclips.net/video/bcK7LldB3dk/видео.html I like some of the transitions, but sometimes they're a bit too much and are seemingly random. Since we use these persistent elements that transition across pages to indicate some kind of relationship between the previous and the next states, some of your transitions confuse me because I can't immediately see what the relationship is. For example 1:23 of the selectable tiles (which weren't selected) transition into being two switches... does that mean anything? are they related in some way? I see this as random and a bad use of the design language. However, at 3:14 I like the transition from switches to the ticks on a paper, that makes sense to me. Epic presentation tho
Fantastic video. I'm sure someone has made a follow-up somewhere, but can you help me understand how to wrap everything into my own UI where I can pass a parameter through to the search query so it can effectively act as a chatbot?
@@dongnguyenanh7282 This is the default that u should use /content/gdrive/My Drive/data/2023_GPT4All_Technical_Report.pdf. i would suggest to make a folder named 'data' and place your pdf file in it. It worked for me
@@dongnguyenanh7282 Hi, I uploaded my own file to my Google Drive. You must allow access to the drive while signed in to your Google account. For me it looks like this: reader = PdfReader('/content/gdrive/My Drive/my.pdf')
Alright, let's be real here. I have no idea who you are, what IDE you're using, or how AI works (I still think it stands for "Artificial Iguanas"). but I can confidently say that your video is fantastic! 🔥Great job! 🔥
Thanks, can we also use it with non pay-for-each-token models like ChatGPT3.5 or ChatGPT4? (Might be a stupid question; but i did not find an answer to this so far)
Hello, thanks for this amazing content ! I tried it with multiple PDF and CHATGPT get confused when I ask him generic questions that are similar on multiple documents (for example : "what are the skills of Jhon DOE ? " when I uploaded multiple PDF resume, it send me back the skills of everyone in the vector database) How do you manage multiple PDF ?
I have another video on dealing with multiplle PDF files. Have a look at that. You can set it to give you the top k responses. Will be making a video on it soon.
@@engineerprompt Your explanation is very didactic. Your code is very clear. I look forward to your new video on chatting with multiple PDFs. Congratulations.
I have a question.. So what If I want to have like a knowledge of chatGPT model which I specify, plus the added information from the PDF file? How is this achievable?
@@dongnguyenanh7282 "/content/gdrive/My Drive/" is the root dir of your gdrive, you can append you file path in gdrive after this root dir. you can treat it as a real folder and use 'ls' to find out where your file is.
I have some JSON files which I want to use for chatbot data source. How to store the JSON information in Croma DB using embedding and then retrieve it based on the user query. I googled a lot but did not find any answers.
Nice, I don't have the basic coding skills and I feel that's a must. I will like to challenge you though to create an App that can compare two or more than two documents and to discover if there are issues of copy and paste or plagiarism between the documents without running a search across the whole internet. Is this doable?
You can build GUI application on top of it. Check this out: ruclips.net/video/RIWbalZ7sTo/видео.html I haven't used it for any other language but I think it can be done.
the 3 questions you are asking are very simple. running this on a company's annual report 10-K. There are many questions e.g. what is the capital expenditure for 2022. The answers exist in the PDF yet it says 'i don't know'.
Thanks for this video it's really helpful. Could you make a video on how to do embedding with gpt4all and langchain on colab , it would be cool to be able to run your own models and have your own extra data sets
Thanks! This was super helpful and I was able to query my own PDF's but I can't figure out where and how to specify the LLM I want to use GPT-4. Can you please let me know?
Hello, how do you think i can handle the same process with lot of files of my own company database, i have few Gigabytes of files that i would need to scan & chunks to create my own database, then connect with GPT4all to interact with question regarding my company, give some tasks etc... thx for the head up
Amazing tutorial, but is there a way to have multiple pdf all stored in the same place once for all and then go there for the query as we are doing in this tutorial? From a practical point it would have much more sense...
There is more interest that I anticipated :-) I am going to be making more videos on the topic with practical use cases (multiple files, different file formats etc.). Keep an eye out for those!
Hello in the case that i had a diagram, graph, chart, or any kind of graphic organizer in the pdf, is it possible for that too to be inputed? Thank you so much btw for the excellent video.
Well explained. Thank you for sharing your knowledge with us. I want to ask if it is possible to get response of a query from the vector database and ad well as the outside the vector database
So when does this use the API the most? During the embedding or during the query? If its during the embedding, can I pickle the results so I can query the same stuff faster and more cheaply in the future?
I have been looking for something like this for almost 2 months, and watched at least a dozen youtube videos. This is the first video/code that acutally works! Question... suggestions on how to connect this to streamlit or another webbased query platform?
Hi, thank you for the video. I need your help. I want to use this solution. However, i would to base gpt answers on one hundreds pdf files. Each pdf file is a book about 200 pages. I do not see in this video how we can rely on several pdf.
great simplified video explanation. In the part where you choose the text-ada model. Can you replace that with the model id of an openai fine-tuned model we created? This way we can use the fine-tuned model to speak with the pdf?
@@engineerprompt so basically if i wanted, i can say have a fine tuned model that speaks like Thor read my pdf knowledge base and answer in the way of Thor. is this correct?
Nice video! I assume that DeepL uses a similar approach to translate PDFs. I used it but encountered some problems. For example, if a sentence does not end on one page, it can cause problems and return nonsense. This may have been the reason for our "Overlap"? So, I rewrote some 250-page-long documents to eliminate any overlapping sentences from page to page. (From now on, I will compare translating a text to making queries, since both require a comparable amount of "work" for GPT.) This helped a lot, but not always. In my opinion, the reason for the occasional issues is that it is difficult to predict the number of tokens required for each page. If the text, like in my case, is complex scientific or technical content, GPT will need more tokens for the same number of characters than it would for a fairy tale, for example. Therefore, with a technical or scientific document, you may run out of tokens very quickly if the content is complex. Whether it's translating or making queries, I believe this problem will arise. Perhaps we need to wait for GPT to upgrade the maximum number of tokens by 2-3 times from now until it can handle any kind of text. Currently, you could reduce the format of your pages to ensure that each page has less (con)text.
How can I combine the RetrievalQAWithSourcesChain from your other tutorial into these codes. Basically, I want to provide the references which will return the page number or numbers, within the PDF document, that the answer is found. Please help.
When I try to query it gives me an error "This model's maximum context length is 4097 tokens, however you requested 4372 tokens (4116 in your prompt; 256 for the completion). Please reduce your prompt; or completion length." This may be because I can't seem to get a gpt model that supports large proms. Honestly, it won't let me specify any model at all. Although I put it in the right place according to the timecode (8:59). When trying to specify the model, it gives the error "File "", line 1 chain = load_qa_chain(OpenAI(gpt-4-32k-0314), chain_type="stuff") ^ SyntaxError: invalid decimal literal"
If you have access to the 32k tokens model then change it like this. chain = load_qa_chain(OpenAI(model_name='gpt-4-32k-0314'), chain_type="stuff") This will work. However, if you are using the default model, then as the error message is showing you are providing more tokens than what the model supports. In this case you want to reduce the number of documents that are being return by the similarity search results. Pass a value of k (by defult its set to 4). I will recommend starting with 3 and if it still doesn't resolve the issue, go even lower. docsearch.similarity_search(query, k=4) Hope this helps.
The cost question was incorrect tho. It says they got GPU's for 800$ and failed trainings for about 500$ using the OpenAI API, then they say the full training could be done with 100$ renting a gpu. :/
I have this use-case where there are different types of documents. I can parse documents using document loaders using langchain. But, there are images also in these documents. I want to store them as metadata and if answer generated from a context chunk it show the image also. Please help.
Is exact openai model configured implicitly? I'm wondering how to know which model we use based on the pricing section listed on openai page. You use embeddings. Shoud it be that one then - Embeddings - Ada? Would be nice to see video about calculating prices based on various factors (so that we can plan costs acording to the requirements).
that's a good point, will add those details in another video for sure. You can pass the model to OpenAI function (there is a model parameter). Thanks for the suggestion.
I am passing the entire document and able to retrieve all the details I need in a single prompt. But response time goes higher. Vice versa if I go with multiple prompts response time is less but since I need to pass the input document everytime usage of token goes high. I am building an application in drf and I don't need any user interface for this. Just need to hit the openAI once to get relevant results from the document and send as json response. Any solutions?
Thanks so much, this was very helpful! You mentioned doing a version that can take in multiple files within a folder, what are the changes required? Will the embeddings retain a correlation to the rest of their respective file (e.g. if i ask who are the authors of a particular quote somewhere in the middle of a paper, how will it know that it relates to the names right at the beginning if there are multiple different papers embedded?)
I used a research paper as input pdf and i want it to create a 1500 word summary but it cuts off at 200 something words, also where you specified i cant input any models. ( 8:59 )
Thanks for the very well detailed tutorial. I'm working with a large pdf (10mb, 580 pages) and I have this error message when running docsearch = FAISS.from_texts(texts, embeddings): RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details.
thank you! Is there a way to adjust the token size of the output? i would like to add more context to the output. also on minute 9 you mention changing ai model. how exactly do i do that?
Hi Prompt Engineering, can we implement the same logic with our custom model, ( without taking any help from OpenAI)? waiting to here from your side....
![Eminem - Temporary (feat. Skylar Grey) [Official Music Video]](http://i.ytimg.com/vi/ZaK9Wi5ho0o/mqdefault.jpg)
Want to connect?
💼Consulting: calendly.com/engineerprompt/consulting-call
🦾 Discord: discord.com/invite/t4eYQRUcXB
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Join Patreon: Patreon.com/PromptEngineering
▶ Subscribe: www.youtube.com/@engineerprompt?sub_confirmation=1
OMG someone took the time to talk about usage costs. No one has yet herded up usage case scenarios in relation to cost from major AI vendors. Thanks for your consideration in this area.
Well, done. You filled in several important holes in my understanding of how to code something like this for my domain.
Glad it helped!
Very clear, thorough, well paced and learner-centered. What an amazing educator!
Excellent video. In three minutes, I learned more about how AI works in general than 100s of other videos. Well done, sir.
Let me see your watch history 🤣🤣
At this point it doesn't get any easier than that! I was able to drop in a technical document that makes my eyes bleed when I read it and just start asking questions of it instead. Great job! If someone would bundle this up into a nice little application and let me aim it at directories full of documents I think they could make a boatload of money.
What do you mean 'aim it at directories' ?
@@blockchainbrudda3051 aka "folders"
Like D:/Technical Documents/
I can't wait for the day when SharePoint has AI assistance built in so a company can ask natural language questions of their business content and get back Chat-GPT style answers with links to the source material. It'll be a revolution for content management and productivity.
Chatpdf
Working on It
I created an updated video to work with multiple PDF files: Checkout here: ruclips.net/video/s5LhRdh5fu4/видео.html
no dude its still giving me an error. please can you have another look?
Notebook loading error
There was an error loading this notebook. Ensure that the file is accessible and try again.
Request had invalid authentication credentials. Expected OAuth 2 access token, login cookie or other valid authentication credential. See developers.google.com/identity/sign-in/web/devconsole-project.
How to increase output size. It works great, but output text is too short and I don't see an obvious way to increase it.
@@cvetelingeorgiev1527 You can pass on temperature to the OpenAI object, play around with it. That will change the behavior.
still, the file isn't accessible
The notebook is not available. 😢
A very clear explanation. Before this video, I was confused about the purpose of embeddings and how the actual answers are produced and the video explained it very well.
Great work! Thanks! Works out of the box. Shorter and clearer impossible 🙂
Great to hear!
AWESOME Video! This kind of apps are really good :)) the workflow gets improved too much
Great example, please cover how to do same using FreeGpt, Dolly or other Opensource models
hello, how do you get the location of the pdf files on the drive?
Langchain works with essentially any model with an api
Excellent educator. loved the well paced video. Thanks for sharing your knowledge and findings
Thank you!
ChatPDF is also good. I have used it.. and its free for 120 pages, 3 PDFs/day, and 50 questions/day... one can pay $5 per month to get very good upgrades
Nice work - very clearly explained and you addressed the code fragments really well - look forward to more vids!!
Thank you :)
Is it possible to feed an entire GitHub project to GPT and ask it to explain or give ideas on how to modify the code?
Really interesting and helpful! Thanks for taking the time to put this video together.
Glad it was helpful!
what is the approx cost of API, if I use a University Subject's textbook with 1000 pages? I mean cost of embedding the pdf data to model and also the search cost for questions. Can you tell the cost in the form of API pricing or tokens?
Wow, I stared at that opening graph for like 10 minutes being in awe, realizing the implications and uses, marveling at the elegance. This is insanely similar to an approach I thought of to extract new information during conversation, but this is more elegant.
I should start making graphs of my approaches, since they do tend to get pretty complex and sometimes I lose track of what I'm doing or trying to do.
Thanks for a very instructive video and learned quite a bit from your step by step guide. Much appreciate the effort you put in & you have inspired me to keep expanding my knowledge in this area. Thank you.
Glad you found it useful.
The Best tool for this is ruclips.net/video/bcK7LldB3dk/видео.html
I like some of the transitions, but sometimes they're a bit too much and are seemingly random. Since we use these persistent elements that transition across pages to indicate some kind of relationship between the previous and the next states, some of your transitions confuse me because I can't immediately see what the relationship is.
For example 1:23 of the selectable tiles (which weren't selected) transition into being two switches... does that mean anything? are they related in some way? I see this as random and a bad use of the design language. However, at 3:14 I like the transition from switches to the ticks on a paper, that makes sense to me. Epic presentation tho
video unavailable :/
Fantastic video. I'm sure someone has made a follow-up somewhere, but can you help me understand how to wrap everything into my own UI where I can pass a parameter through to the search query so it can effectively act as a chatbot?
It was a very helpful guide. Thanks! Great that I was able to test it quickly thanks to your notebook link.
hello, how do you get the location of the pdf files on the drive?
@@dongnguyenanh7282 This is the default that u should use /content/gdrive/My Drive/data/2023_GPT4All_Technical_Report.pdf.
i would suggest to make a folder named 'data' and place your pdf file in it. It worked for me
@@dongnguyenanh7282 Hi, I uploaded my own file to my Google Drive. You must allow access to the drive while signed in to your Google account. For me it looks like this:
reader = PdfReader('/content/gdrive/My Drive/my.pdf')
Mindblowing! Very clear and your explanation is excellent! Thanks ;)
Very nice... explained at the right pace.... keep up the good work... it would be more helpful if a repo is maintained...
Thank you, that’s a great idea
Alright, let's be real here. I have no idea who you are, what IDE you're using, or how AI works (I still think it stands for "Artificial Iguanas"). but I can confidently say that your video is fantastic!
🔥Great job! 🔥
Thank you, comments like this keeps me going :-)
@@engineerprompt Seriously, you know your subject and you take the time to explain the concept behind it. Thanks for your content 🙏🙏
Just found your channel, Excellent Content! - Another sub for you sir!
Thank you!
Very well laid out and all answered. Thank you.
Thanks, can we also use it with non pay-for-each-token models like ChatGPT3.5 or ChatGPT4? (Might be a stupid question; but i did not find an answer to this so far)
I'd like to know as well
Hello, thanks for this amazing content !
I tried it with multiple PDF and CHATGPT get confused when I ask him generic questions that are similar on multiple documents (for example : "what are the skills of Jhon DOE ? " when I uploaded multiple PDF resume, it send me back the skills of everyone in the vector database)
How do you manage multiple PDF ?
I have another video on dealing with multiplle PDF files. Have a look at that. You can set it to give you the top k responses. Will be making a video on it soon.
@@engineerprompt Your explanation is very didactic. Your code is very clear. I look forward to your new video on chatting with multiple PDFs. Congratulations.
@@victorgianordoli5403 Thank you, you probably want to check out this here: ruclips.net/video/s5LhRdh5fu4/видео.html
Your explanation is very clear! Love it! Thank you very much!
Glad you found it useful. Appreciate the kind words.
I have a question.. So what If I want to have like a knowledge of chatGPT model which I specify, plus the added information from the PDF file? How is this achievable?
Super useful, this is what I have been looking for, ❤ love it!
hello, how do you get the location of the pdf files on the drive?
@@dongnguyenanh7282 "/content/gdrive/My Drive/" is the root dir of your gdrive, you can append you file path in gdrive after this root dir. you can treat it as a real folder and use 'ls' to find out where your file is.
I have some JSON files which I want to use for chatbot data source. How to store the JSON information in Croma DB using embedding and then retrieve it based on the user query. I googled a lot but did not find any answers.
Nice, I don't have the basic coding skills and I feel that's a must. I will like to challenge you though to create an App that can compare two or more than two documents and to discover if there are issues of copy and paste or plagiarism between the documents without running a search across the whole internet. Is this doable?
Thanks! Is there a cost associated when you call OpenAIEmbeddings(). Can I run a local LLM model to answer the query?
Thanks this out: ruclips.net/video/MlyoObdIHyo/видео.html
I assume there is no one-click .exe file (yet) or a clear GUI?
You sir I am buying you a coffee
It was amazing learning for me. I built my application successfully. Can we take user input using a window? Can we use pdf in Arabic or Urdu?
You can build GUI application on top of it. Check this out:
ruclips.net/video/RIWbalZ7sTo/видео.html
I haven't used it for any other language but I think it can be done.
the 3 questions you are asking are very simple. running this on a company's annual report 10-K. There are many questions e.g. what is the capital expenditure for 2022. The answers exist in the PDF yet it says 'i don't know'.
You will have to do some prompt engineering on top of the simple examples I have shown here.
Thanks for this video it's really helpful. Could you make a video on how to do embedding with gpt4all and langchain on colab , it would be cool to be able to run your own models and have your own extra data sets
Very nice content - thank you for that introduction
Thanks! This was super helpful and I was able to query my own PDF's but I can't figure out where and how to specify the LLM I want to use GPT-4. Can you please let me know?
Watch the latest video on the channel. I have provided detailed explanation there.
Hello, how do you think i can handle the same process with lot of files of my own company database, i have few Gigabytes of files that i would need to scan & chunks to create my own database, then connect with GPT4all to interact with question regarding my company, give some tasks etc...
thx for the head up
Amazing tutorial, but is there a way to have multiple pdf all stored in the same place once for all and then go there for the query as we are doing in this tutorial? From a practical point it would have much more sense...
There is more interest that I anticipated :-) I am going to be making more videos on the topic with practical use cases (multiple files, different file formats etc.). Keep an eye out for those!
Godspeed sir
is it possible to replace openAI with alternatives like Alpaca or Vicuna, given the cost?
Tried searching a lot. Every example uses OpenAPI. No one has used LLama, Alpaca or Vicuna.
No.. body has the compute hardware that openai has or will have..
Hello in the case that i had a diagram, graph, chart, or any kind of graphic organizer in the pdf, is it possible for that too to be inputed? Thank you so much btw for the excellent video.
OSM, I really liked your to the point video, Thank you
Excellent video!
I love you. thank you for making this so easy!
That was a great video, thanks!
But in the end, how do you then output the ChatGPT message outside of Langchain into your apps?
If I ask questions about graphs, tables, or images present in the PDF, will it provide an answer?
Well explained. Thank you for sharing your knowledge with us. I want to ask if it is possible to get response of a query from the vector database and ad well as the outside the vector database
So when does this use the API the most? During the embedding or during the query? If its during the embedding, can I pickle the results so I can query the same stuff faster and more cheaply in the future?
At both stages, and yes, you can get embeddings of your documents and store them locally and then do the api call for the query.
I am waiting for multiple file read, thanks a lot!
What's the best video for someone with little to no python experience but wants to use langchain
Thanks for sharing!
I have been looking for something like this for almost 2 months, and watched at least a dozen youtube videos. This is the first video/code that acutally works! Question... suggestions on how to connect this to streamlit or another webbased query platform?
Thank you! You want to check out this video: ruclips.net/video/RIWbalZ7sTo/видео.html
Hi, thank you for the video. I need your help. I want to use this solution. However, i would to base gpt answers on one hundreds pdf files. Each pdf file is a book about 200 pages. I do not see in this video how we can rely on several pdf.
Check this out for multiple files. Will be making more detailed videos on the topic soon ruclips.net/video/s5LhRdh5fu4/видео.html
great simplified video explanation. In the part where you choose the text-ada model. Can you replace that with the model id of an openai fine-tuned model we created? This way we can use the fine-tuned model to speak with the pdf?
Yes, you should be able to do that easily.
@@engineerprompt so basically if i wanted, i can say have a fine tuned model that speaks like Thor read my pdf knowledge base and answer in the way of Thor. is this correct?
Nice video! I assume that DeepL uses a similar approach to translate PDFs. I used it but encountered some problems. For example, if a sentence does not end on one page, it can cause problems and return nonsense. This may have been the reason for our "Overlap"? So, I rewrote some 250-page-long documents to eliminate any overlapping sentences from page to page. (From now on, I will compare translating a text to making queries, since both require a comparable amount of "work" for GPT.) This helped a lot, but not always.
In my opinion, the reason for the occasional issues is that it is difficult to predict the number of tokens required for each page. If the text, like in my case, is complex scientific or technical content, GPT will need more tokens for the same number of characters than it would for a fairy tale, for example. Therefore, with a technical or scientific document, you may run out of tokens very quickly if the content is complex. Whether it's translating or making queries, I believe this problem will arise.
Perhaps we need to wait for GPT to upgrade the maximum number of tokens by 2-3 times from now until it can handle any kind of text. Currently, you could reduce the format of your pages to ensure that each page has less (con)text.
The model used by default is text-davinci-003 and it is now deprecated so what should we do now ?
Any latest code for the above project ?
How can I combine the RetrievalQAWithSourcesChain from your other tutorial into these codes. Basically, I want to provide the references which will return the page number or numbers, within the PDF document, that the answer is found. Please help.
Thanks, this was my this afternoon to do.
When I try to query it gives me an error "This model's maximum context length is 4097 tokens, however you requested 4372 tokens (4116 in your prompt; 256 for the completion). Please reduce your prompt; or completion length."
This may be because I can't seem to get a gpt model that supports large proms. Honestly, it won't let me specify any model at all. Although I put it in the right place according to the timecode (8:59). When trying to specify the model, it gives the error "File "", line 1
chain = load_qa_chain(OpenAI(gpt-4-32k-0314), chain_type="stuff")
^
SyntaxError: invalid decimal literal"
If you have access to the 32k tokens model then change it like this.
chain = load_qa_chain(OpenAI(model_name='gpt-4-32k-0314'), chain_type="stuff")
This will work. However, if you are using the default model, then as the error message is showing you are providing more tokens than what the model supports. In this case you want to reduce the number of documents that are being return by the similarity search results. Pass a value of k (by defult its set to 4). I will recommend starting with 3 and if it still doesn't resolve the issue, go even lower.
docsearch.similarity_search(query, k=4)
Hope this helps.
How do u load multiple pdfs in LangChain ?
The cost question was incorrect tho. It says they got GPU's for 800$ and failed trainings for about 500$ using the OpenAI API, then they say the full training could be done with 100$ renting a gpu. :/
Thank you!
I have this use-case where there are different types of documents. I can parse documents using document loaders using langchain. But, there are images also in these documents. I want to store them as metadata and if answer generated from a context chunk it show the image also. Please help.
Is exact openai model configured implicitly? I'm wondering how to know which model we use based on the pricing section listed on openai page. You use embeddings. Shoud it be that one then - Embeddings - Ada? Would be nice to see video about calculating prices based on various factors (so that we can plan costs acording to the requirements).
that's a good point, will add those details in another video for sure. You can pass the model to OpenAI function (there is a model parameter). Thanks for the suggestion.
It uses text davinci
I am passing the entire document and able to retrieve all the details I need in a single prompt. But response time goes higher. Vice versa if I go with multiple prompts response time is less but since I need to pass the input document everytime usage of token goes high. I am building an application in drf and I don't need any user interface for this. Just need to hit the openAI once to get relevant results from the document and send as json response. Any solutions?
having data in a file and real time embeddings vs embeddings in a db for chatbot for an application (provides information about an application)?
Nice work! If i want to process multiple. Can we do this by adding more inputs?
How does this compare to simply asking BingBot in the Edge Browser's sidebar about a currently displayed PDF document?
Thanks so much, this was very helpful! You mentioned doing a version that can take in multiple files within a folder, what are the changes required? Will the embeddings retain a correlation to the rest of their respective file (e.g. if i ask who are the authors of a particular quote somewhere in the middle of a paper, how will it know that it relates to the names right at the beginning if there are multiple different papers embedded?)
Man I love your tutorials! Do you have any advice on converting scanned pdfs to text for this same application? what are tools you'd recommend?
Thank you!. Fantastic stuff.
I need an App that can read multiple files to answer questions in another uploaded file. Any suggestions?
Brilliant tutorial mate
Very good and clear.
Could we do this with a folder of txt documents. I’m thinking of querying a Zettlekasten created in an app like Obsidian
Yes, there is a loader for text files in langchain
Excellent!! 🎉
Very good video. Thank you
Magnificent!!
I have now an idea how chatGPT is trained with large data and be able to retrieve a response for your query within seconds. Thank you!
I used a research paper as input pdf and i want it to create a 1500 word summary but it cuts off at 200 something words, also where you specified i cant input any models. ( 8:59 )
Can images in a PDF be interpreted and described using a similar method as text?
how can I save the vector database in a physical one, not in memory ?
Thank you. Very interesting
Thanks, this helps me a lot!
Thanks for the very well detailed tutorial. I'm working with a large pdf (10mb, 580 pages) and I have this error message when running docsearch = FAISS.from_texts(texts, embeddings): RateLimitError: Error code: 429 - {'error': {'message': 'You exceeded your current quota, please check your plan and billing details.
That means you don't have enough money in your openai account. You need to look at your billing page
Can you make an update video on the project? it kinda blew up and I am really interested in how it is going 😊
Yes, updates coming soon!
thank you! Is there a way to adjust the token size of the output? i would like to add more context to the output. also on minute 9 you mention changing ai model. how exactly do i do that?
thanks for the video, just wonder how do you do extraction if the pdf page contains mixed text and image/chart
The file I tested has table and images but this will ignore them. It can only do text based info retrieval.
Thanks for the videos! They've helped understand a lot about GPT stuff. But how do I change the language model?
i guess you can change the api key
Hi Prompt Engineering,
can we implement the same logic with our custom model, ( without taking any help from OpenAI)?
waiting to here from your side....
Yes
Thanks for your video! How can I change the PDF file using URL instead of google drive?
Great tutorial! thank you very much!
what is the token limit on this? can it read 1000 pages PDFs and answer questions accuaretly?
hey the way u explain seems extremely simple to implement can we use PDF gpt for commercial use
Yes, there are actual products out there using the EXACT same approach :)
Hi! When i ask things not related to the documents,alwats returns informations . Information not inside my context