3 ай бұрын
3 ай бұрын
3 ай бұрын
4 ай бұрын
4 ай бұрын
4 ай бұрын
4 ай бұрын
Пікірлер
@shubhankarshakhari9688 6 сағат бұрын
Thank you for the video. Can this code be used in production with a lot of simultaneous query?
@bharathjc4700 Күн бұрын
great video appriciate if can please share the note book link
@sebastiandiaz8173 2 күн бұрын
Great video! A lot of thanks, whith this i am advicing on my university investigation. Hi from Colombia!
@sebastiandiaz8173 2 күн бұрын
Great video! A lot of thanks, whith this i am advicing on my university investigation. Hi from Colombia!
@hamzabinumar910 3 күн бұрын
Sir I am doing a project in which will take natural language as input and give sql query as output. I am given a llama 3.1-8b. I am getting very bad results, I have tried multiple methods e.g. breaking the query into individual atomic statements, selecting only relevant tables and feeding the model only the schema of thag required table to minimize tokens. and more approaches, But the output is always bad and inconsistent, do you have any solution for this? I was thinking of making a sepetate code which will be a sql generator, and the task of the llm would be to make me a structured json which will capture all the conditions. What do you think of this approach?
@ronifintech9434 5 күн бұрын
Thank you for the knowledge sharing
@akashprabhakar6353 8 күн бұрын
Thanks Sridhar. Here we had the ground truth present with us. In Real world cases, how is it possible? Suppose I have 50 pdf, now how do I create the Ground truth to evaluate RAG? Is it possible? DO we need to manually create some 50-60 questions and their ground truths and then build the RAG-LLM chatbot and check its performance on same questions? Also, suppose we deploy the chatbot, now in real-time how to evaluate if we don't have ground truth for newly asked questions?
@akashprabhakar6353 8 күн бұрын
Thanks for the video. Suppose I want to check Context Precision, How do I calculate that the retrieved context is relevant? Is it by human feedback or how it can be automated.
@Ponix-n9m 14 күн бұрын
Bro the problem isnt fixed can u share ur code?
@kk008 14 күн бұрын
Excellent video but facing an error with Litellm
@冯旭晖-g7d 19 күн бұрын
How to fine-tune the timesfm model?
@danyalaslam8174 21 күн бұрын
Hello Thanks for amazing content, can you share script/notebook or GitHub repo for your solution ?
@anandvishwakarma933 21 күн бұрын
Amazing
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@ahmadmaroofkarimi9125 23 күн бұрын
How do we deal with the usecase when we have 10 tables each having around 100 columns? Is this approach of schema description scalable. Thank you
@soulaimanebahi741 25 күн бұрын
can we fine tune this model using a video dataset ?
@joycer5293 29 күн бұрын
I don't have description_embedding in my create_final_entities.parquet file... is this normal?
@aliabdelhadi1104 Ай бұрын
u are great .. easy steps helpful may allah bless u
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@navdeetsaini5553 Ай бұрын
Can you provide a code of final model.
@divyad4058 Ай бұрын
Does it have a performance impact by introducing these many fact identification and fact check steps?
@indrayne1840 Ай бұрын
Hey, why the code ban didn't work. Also in anonymize can we redact organization names, payment terms?
@gibraltor999 Ай бұрын
API key is free for a number of tokens and not infintely right?
@siddharthvj1 Ай бұрын
love this channel
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@joycer5293 Ай бұрын
Thank you for the video! I ran into this error ImportError: cannot import name 'GraphRagConfigInput' from 'graphrag.config.input_models' (unknown location) when trying to run python3 -m graphrag.index --root ./graphrag2 Do you know what might have caused the issue? Thank you very much
@stonkmaster6969 Ай бұрын
Is LightRAG's codebase not a little unstable for enterprise use? Also, it seems to have limitations with LLM model selection; supports only OpenAI models and Claude.
@rishavranaut7651 Ай бұрын
Why are we not learning the embeddings? It is possible one solution for one thing can be solution of other as well and share same embedding space but are different in reality
@vidurachathuranga-y5r Ай бұрын
A very clear explanation. Thank you!
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@Ash-bc8vw Ай бұрын
How to make changes in rag model after evaluation
@prashanthkolaneru3178 Ай бұрын
How do I handle documents has different layouts at each page
@sharanbiradar3615 Ай бұрын
It was very helpfull
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@sharanbiradar3615 Ай бұрын
Thank you sir😊
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@ashutoshpatel4701 Ай бұрын
Is it neccessary to have OpenAI API key for this implementation ? I didn't find any place where OpenAI API key is used .
@emmanuelolayemi2494 Ай бұрын
Hello, the link in the description is not working anymore.
@subhamlaha8232 Ай бұрын
Very useful content
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@ursusss Ай бұрын
Out of all the channels, your explanations are the most easy to understand. Thanks so much
@SridharKumarKannam 10 күн бұрын
Thank you very much. Please consider sharing it with others who might benefit. Your support is greatly appreciated :)
@wah866sky7 Ай бұрын
How can I collect the CSV files and all training image files for the Sagemaker Course? Thanks
@SandeepS-i4e Ай бұрын
Can it be used for pdfs or douments containing images and tables also? Could you pls do a video on that also?
@amruth505 Ай бұрын
can we do the same with Azure open AI?
@SridharKumarKannam Ай бұрын
Yes, we can.
@tonyseno 2 ай бұрын
Can the LightRAG show the references including the page numbers it refers to?
@SridharKumarKannam Ай бұрын
It doesn't have that feature out of the box, but the source code can be modified to save page number info as metadata for the nodes and can be returned to the user. Its not an easy task though...
@amruth505 2 ай бұрын
why not use LLMGraphTransformer?
@kk008 2 ай бұрын
Can I use Knowledge graph (RDF format) as input or what process I need to do ?
@SridharKumarKannam Ай бұрын
GraphRAG builds its own custom Knowledge graph with some new concepts like communities and summaries. We can't use RDF KGs GraphRAG unless you modify the source code substantially. I think, the best approach would be to build a RAG on top of your RDF KG. With all these RAG's the main thing, extracting the information relevant to the query and providing that to an LLM to create an answer.
@kk008 Ай бұрын
@@SridharKumarKannam thanks for the answer. :) Yes, as it generates KG internally, its not a good idea to modify source code right now as it is already have many open issues for GRAPHRAG. I didn't find any good implementation source to build RAG on top of my RDF KG.
@piotrbjastrzebski 2 ай бұрын
Good stuff! Thank you!!! Has anybody tried with Ollama Open source models, consistently I am getting nodes, but no relationships (other than MENTIONS from document to an entity). llm_transformer = LLMGraphTransformer(llm=llm, node_properties=True, relationship_properties=True, strict_mode = False) and we define llm = ChatOllama(model="llama3.1", temperature=0, format="json") - I enev increase temperature to >0, but that does not help either ???
@SridharKumarKannam Ай бұрын
there are function calling issues with ollama models. Try the solution suggested here, I've not tested it though.. github.com/langchain-ai/langchainjs/issues/6051
@dineshmani1846 2 ай бұрын
how can we do the Q&A using AWS neptune with Germlin.
@SridharKumarKannam 2 ай бұрын
What is Germlin? Instead of Neo4j you connect to neptune. Bothe are graph DB's and should work the same way.
@dineshmani1846 2 ай бұрын
@@SridharKumarKannam can i get any references or explanation for that
@SridharKumarKannam Ай бұрын
@@dineshmani1846 docs.aws.amazon.com/neptune/latest/userguide/access-graph-gremlin-python.html
@krishnanmanushresth3400 2 ай бұрын
Bro it is showing that context len horizontal len is not part of the syntax
@SridharKumarKannam Ай бұрын
Whats the exact error message? The variable name is "horizon_len". model = timesfm.TimesFm( context_len=512, horizon_len=128, input_patch_len=32, output_patch_len=128, num_layers=20, model_dims=1280, backend=timesfm_backend, )
@louortiz9395 2 ай бұрын
I can't seem to find information on how to use nougat. Is there a program I can download? I am not programming savvy but can follow directions. I have ebooks that I need formatted for AI use such as perplexity. Please help. Thank you.
@SridharKumarKannam 2 ай бұрын
you can follow the instructions here - github.com/facebookresearch/nougat
@SurajPrasad-bf9qn 2 ай бұрын
Thank you
@SridharKumarKannam 2 ай бұрын
If you found this content helpful, please consider liking, subscribing, and sharing it with others who might benefit. Your support is greatly appreciated :)
@icanride4long 2 ай бұрын
Hi, great content. Easy to follow. Thanks for that. Are you able to compare and contrast LightRag vs GraphReader? GraphReader is similar in flow to GraphRag so I assume it has the same disadvantages. But would love to hear your thoughts since you've posted content on both solutions. Which would you recommend for production, today?
@SridharKumarKannam 2 ай бұрын
thanks, I'll try but i'm occupied with quite a few things at the moment.
@薛帅-p7y 2 ай бұрын
it can be used in producation envs statbly?
@SridharKumarKannam 2 ай бұрын
yes, the source code is available, just make sure there are no security issues related to API call to the servers...
@JENNYOPJOD 2 ай бұрын
ImportError: cannot import name 'EmbeddingFunc' from 'lightrag.utils' (/usr/local/lib/python3.10/dist-packages/lightrag/utils/__init__.py) help me