Видео

Hello @tonykipkemboi, i finaly find the solution, i use langchain_chroma and change this line of code : vector_db = Chroma.from_documents(persist_directory=CHROMA_PATH, documents=chunks, embedding=embeddings, collection_name="myRAG" ) Thanks !

Great Video Tony, I want to know if what is the method to display the metadata of the pdf while publishing the answer ?

Great content. I'm getting an error when I try to upload the file on the streamlit interface. I also tried to run the local_ollama_rag.ipynb file in juptyer notebook and get the same error when I execute upload pdf tab. can someone advice how to resolve this? OSError: No such file or directory: '/Users/nltk_data/tokenizers/punkt/PY3_tab'.

Error code 404 the model gpt-4o does not exist or you do not have access to it. What to do?

its not working giving error ConnectError: [Errno 61] Connection refused Traceback: File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/exec_code.py", line 75, in exec_func_with_error_handling result = func() ^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 574, in code_to_exec exec(code, module.__dict__) File "/Users/adityagupta/Desktop/rag/ollama_pdf_rag/streamlit_app.py", line 278, in <module> main() File "/Users/adityagupta/Desktop/rag/ollama_pdf_rag/streamlit_app.py", line 200, in main models_info = ollama.list() ^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/ollama/_client.py", line 464, in list return self._request('GET', '/api/tags').json() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/ollama/_client.py", line 69, in _request response = self._client.request(method, url, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_client.py", line 827, in request return self.send(request, auth=auth, follow_redirects=follow_redirects) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_client.py", line 914, in send response = self._send_handling_auth( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_client.py", line 942, in _send_handling_auth response = self._send_handling_redirects( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_client.py", line 979, in _send_handling_redirects response = self._send_single_request(request) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_client.py", line 1015, in _send_single_request response = transport.handle_request(request) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_transports/default.py", line 232, in handle_request with map_httpcore_exceptions(): File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/contextlib.py", line 158, in __exit__ self.gen.throw(value) File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/httpx/_transports/default.py", line 86, in map_httpcore_exceptions raise mapped_exc(message) from exc

Hello Tony and thank you for your amazing Job !! I have just an error that actually streamlit always interrup it self like that : 2024-09-10 18:24:16 - INFO - HTTP Request: GET localhost:11434/api/tags "HTTP/1.1 200 OK" 2024-09-10 18:24:16 - INFO - Extracting model names from models_info 2024-09-10 18:24:16 - INFO - Extracted model names: ('nomic-embed-text:latest', 'mistral-nemo:latest', 'mistral:latest') 2024-09-10 18:24:18 - INFO - HTTP Request: GET localhost:11434/api/tags "HTTP/1.1 200 OK" 2024-09-10 18:24:21 - INFO - HTTP Request: GET localhost:11434/api/tags "HTTP/1.1 200 OK" 2024-09-10 18:24:21 - INFO - Creating vector DB from file upload: monopoly.pdf 2024-09-10 18:24:21 - INFO - File saved to temporary path: C:\Users\XXX\AppData\Local\Temp\tmpobt9kjka\monopoly.pdf 2024-09-10 18:24:24 - INFO - pikepdf C++ to Python logger bridge initialized 2024-09-10 18:24:25 - INFO - Document split into chunks OllamaEmbeddings: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 5.06it/s] (OllamaChat) PS C:\Dev\tony\OllamaChat\ollama_pdf_rag> Let me know if you want more info :)

how to use multiple pdfs?

I looking for 2 weeks this type of video but finally I got it Thank you brother.

can we pre process data for this?if yes can you please tell me how

Awesome!! Thank you Tony! Just leaving a fix, the failed bank link has been changed. The current one is: www.fdic.gov/system/files/2024-07/banklist.csv Additionally, what kind of recommendations do you have to csv files with columns as value (dollar currency, for example)? By some reason, when I ask something like 'give me the 3 biggest expenses with Traveling category' never works, he fails listing. Any advice would be really appreciated! Thanks!

Can you upload a tutorial where from scratch, we can create AI assistant on data we have....eg : HR assistant...

Great video! There's any way I can let a LLM read a folder on my PC and answer me using archives (pdfs, .md, .doc, sheets, etc) from that source?

This is excellent!! Thank you!!

I got error for langdetect, is there any solutions?

That cool be nice to see multiple pdfs loaded, to see if can be made handle different topics at once.

Bro.. can i ask something like the document we input will be save on the local database? Or will be published somewhere? Anyone who know the answer please tell me, sharing with me bro.. thank you

You sir are awesome! It is easy to make things hard, yet hard to make them simple. Thanks for working so hard to make this simple. Excellent presentation. I will be coming back for more!!

I am a layman and have been trying to figure this out for a week, I've watched alot of video's but yours has been by far the best. You cadence is good, you are direct while making it accessible on a high level to follow along. No obfuscation or assumptions. etc etc etc. Great video thank you, have a comment like and subscribe.

A robust AI agent stack is essential for success. SmythOS offers cutting-edge AI agent solutions that may significantly improve your projects.

Can you do for a next.js project

What I don't get is, where is yhe database? If I want to launch this into production, then when is my database? Or will it be virtual forever?

Is it possible to make a video about a chatbot using Groq and open source models and open embeddings which is shareable and used by others. It must be pre-trained on data for example Google drive link containing videos, photos, multiple pdf files, website urls.

How i will get this code

When I add any pdf including the pdf that you have included in your github account, ValueError: Error raised by inference API HTTP code: 404, {‘error’: ‘model \’nomic-embed-text\‘ not found, try pulling it first’} I get this error, I searched but I could not find the reason? Can you help me?

that was a really helpful video thanks a lot , but i have only one problem is that it took me so long to respond like 30min , btw im using weviate image in docker as vector db and nominic embeddings also the ollama's phi3 as my pretrained llm but it doesnt take so much time could u please suggest me to do smth to make it work

anyone else having a problem installing chroma on a mac m2 osx14.5?

What do you use to record your screen capture??

very good!

It work also for scanned pdf and images ?

Wonderful Video, I followed till the last step but then I am getting this error:ValueError: Environment variable OCR_AGENT module name unstructured.partition.utils.ocr_models must be set to a whitelisted module part of ['unstructured.partition.utils.ocr_models.tesseract_ocr', 'unstructured.partition.utils.ocr_models.paddle_ocr', 'unstructured.partition.utils.ocr_models.google_vision_ocr'].....................What to do in thiscase? I used chatGPT. I set the Path variable . Please could you tell me exactly what to do.The error is not going.

After embedding for the first time. Do i have to do it the second time i need to requery the vector database

am getting this error, help me someone resolve this issue PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH? Traceback: File "C:\Users\RajeevSingh\.conda\envs\myenv\Lib\site-packages\streamlit untime\scriptrunner\exec_code.py", line 85, in exec_func_with_error_handling result = func() ^^^^^^ File "C:\Users\RajeevSingh\.conda\envs\myenv\Lib\site-packages\streamlit untime\scriptrunner\script_runner.py", line 576, in code_to_exec exec(code, module.__dict__) File "C:\Users\RajeevSingh\pdfReadingusingOllama\ollama_pdf_rag\streamlit_app.py", line 278, in <module> main() File "C:\Users\RajeevSingh\pdfReadingusingOllama\ollama_pdf_rag\streamlit_app.py", line 223, in main st.session_state["vector_db"] = create_vector_db(file_upload) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

This is a really good video. Thanks a lot for making it, I found it very helpful!

doesnt work.

Only, why would you use a WEF PDF document as a example PDF? Bit suspicious of all things wef.. :P

Can we deploy this in streamlet? if yes Can you make a video about it.

why does the streamlit disconnected after the embedding process is completed?

Can't wait for the RAG part! :D great video!

Hello Sir, First thanks for making this video. I am trying this solution in my local Windows Machine but while uploading File getting below error, "OSError: [WinError 126] The specified module could not be found. Error loading "C:\Data\GharAdhar\workspace\ollama_pdf_rag\venv\lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies." Can you please quide me what I am missing.

Hi, I've been trying to follow along but the first few lines: "local_path = "WEF_The_Global_Cooperation_Barometer_2024.pdf" # Local PDF file uploads if local_path: loader = UnstructuredPDFLoader(file_path=local_path) data = loader.load() else: print("Upload a PDF file")" give me this error: "FileNotFoundError: [WinError 2] The system cannot find the file specified During handling of the above exception, another exception occurred: PDFInfoNotInstalledError Traceback (most recent call last) Cell In[8], line 6 4 if local_path: 5 loader = UnstructuredPDFLoader(file_path=local_path) ----> 6 data = loader.load() 7 else: 8 print("Upload a PDF file") PDFInfoNotInstalledError: Unable to get page count. Is poppler installed and in PATH?" I'm using vscode and the Jupyter notebook extension for the same. I have installed all the libraries in a virtual environment and have been trying to run it there.

Does this pdf library encode embedded tables in the pdf document

when i execute this code local_path = "test.pdf" # Local PDF file uploads if local_path: loader = UnstructuredPDFLoader(file_path=local_path) data = loader.load() else: print("Upload a PDF file") i have an error can u help me with the solution File ~\anaconda3\Lib\urllib equest.py:250, in urlretrieve(url, filename, reporthook, data) 248 # Handle temporary file setup. 249 if filename: --> 250 tfp = open(filename, 'wb') 251 else: 252 tfp = tempfile.NamedTemporaryFile(delete=False) PermissionError: [Errno 13] Permission denied: 'C:\\Users\\monta\\AppData\\Local\\Temp\\tmpbzvo7wzp'

your video is very mindful, i have tried the code, i want to ask some, why every time i run invoke, it will run embedding first, the process of embedding is rather long, is it normal? i want to build some new product using llm based to my client

I am getting the error message below when I upload the pdf. Mark you, I have installed all the dependencies including torch. OSError: [WinError 126] The specified module could not be found. Error loading "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\torch\lib\fbgemm.dll" or one of its dependencies. Traceback: File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\streamlit untime\scriptrunner\exec_code.py", line 75, in exec_func_with_error_handling result = func() ^^^^^^ File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\streamlit untime\scriptrunner\script_runner.py", line 574, in code_to_exec exec(code, module.__dict__) File "C:\Users\HP\Downloads\ollama_pdf_rag\streamlit_app.py", line 278, in <module> main() File "C:\Users\HP\Downloads\ollama_pdf_rag\streamlit_app.py", line 223, in main st.session_state["vector_db"] = create_vector_db(file_upload) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\HP\Downloads\ollama_pdf_rag\streamlit_app.py", line 82, in create_vector_db data = loader.load() ^^^^^^^^^^^^^ File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_core\document_loaders\base.py", line 30, in load return list(self.lazy_load()) ^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_community\document_loaders\unstructured.py", line 89, in lazy_load elements = self._get_elements() ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\langchain_community\document_loaders\pdf.py", line 72, in _get_elements from unstructured.partition.pdf import partition_pdf File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\unstructured\partition\pdf.py", line 54, in <module> from unstructured.partition.pdf_image.analysis.bbox_visualisation import ( File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\unstructured\partition\pdf_image\analysis\bbox_visualisation.py", line 16, in <module> from unstructured_inference.inference.layout import DocumentLayout File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\unstructured_inference\inference\layout.py", line 19, in <module> from unstructured_inference.models.base import get_model File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\unstructured_inference\models\base.py", line 7, in <module> from unstructured_inference.models.chipper import MODEL_TYPES as CHIPPER_MODEL_TYPES File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\unstructured_inference\models\chipper.py", line 9, in <module> import torch File "C:\Users\HP\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\torch\__init__.py", line 148, in <module> raise err

What are the Ollama modules that were used, I don't want to install unimportant modules on my machine since it has only limited space.

Ahsante sana Kip. Working on a bank/ fintech chatbot and will use this info to build it.

Can any one tell this is completely free to implement this video technique???

If I use python_repl tool in combination with my sql agent to create plotly chart, how do I show it in streamlit app?

Thank you for posting this video? It appears that the inference is pretty fast on your Macbook. Could you please share your Macbook config?

Is it compulsory to pull mistral model from Ollama to run the project which size around 4GB??