Want to HIRE us to implement AI into your Business or Workflow? Fill out this work form: td730kenue7.typeform.com/to/WndMD5l7 💗 Thank you so much for watching guys! I would highly appreciate it if you subscribe (turn on notifcation bell), like, and comment what else you want to see! 📆 Book a 1-On-1 Consulting Call WIth Me: calendly.com/worldzofai/ai-consulting-call-1 🔥 Become a Patron (Private Discord): patreon.com/WorldofAi 🧠 Follow me on Twitter: twitter.com/intheworldofai Love y'all and have an amazing day fellas. Thank you so much guys! Love yall!
I got massive issues: SET /p app_version= no file or folder "version" [nltk_data] main\install_dir\env\lib\site- [nltk_data] packages\llama_index\core\_static/nltk_cache... [nltk_data] Package punkt_tab is already up-to-date! GraphRAG dependencies not installed. GraphRAG retriever pipeline will not work properly. -> what is it? How to install GraphRAG? Setting up a local model ****************************************************** Local model not found: llama3.1:8b -> how to download the LLM? Any help would appreciated
Does anybody know if other data types can added with available code? Like json / geojson for example. I think this repo is based and or created with other frameworks? I know langchain has jsontools, but I like to know if I can add dataloaders from the "orriginal" framework if available. Or does someone know a repo that has a lot of different data type as input, so I can create the RAG / GraphRAG with another repo, or maybe convert the files first and use an available/builtin loader? If conversion first is needed, what data type is best to use (mostly for tabular files) so it can be loaded with the least extra (double) conversion?
Want to HIRE us to implement AI into your Business or Workflow? Fill out this work form: td730kenue7.typeform.com/to/WndMD5l7
💗 Thank you so much for watching guys! I would highly appreciate it if you subscribe (turn on notifcation bell), like, and comment what else you want to see!
📆 Book a 1-On-1 Consulting Call WIth Me: calendly.com/worldzofai/ai-consulting-call-1
🔥 Become a Patron (Private Discord): patreon.com/WorldofAi
🧠 Follow me on Twitter: twitter.com/intheworldofai
Love y'all and have an amazing day fellas. Thank you so much guys! Love yall!
At the moment, for MacOS silicon the docker installation fails due to the lack of arm image.
I got massive issues:
SET /p app_version= no file or folder "version"
[nltk_data] main\install_dir\env\lib\site-
[nltk_data] packages\llama_index\core\_static/nltk_cache...
[nltk_data] Package punkt_tab is already up-to-date!
GraphRAG dependencies not installed. GraphRAG retriever pipeline will not work properly.
-> what is it? How to install GraphRAG?
Setting up a local model
******************************************************
Local model not found: llama3.1:8b
-> how to download the LLM?
Any help would appreciated
you have to have ollama or any openai like api provider app or framework to install and use LLMs. I am using ollama at background, it easy for me.
[Must Watch]:
HybridRAG: Ultimate RAG Engine - Knowledge Graphs + Vector Retrieval! Better Than GraphRAG!: th-cam.com/video/rtmDQO3ESoE/w-d-xo.htmlsi=Ggdrh-smzPj5r7cN
GraphRAG: Ultimate RAG Engine - Semantic Search, Embeddings, Vector Search, & More!: th-cam.com/video/kHZHMzv3Shg/w-d-xo.html
Claude Engineer UPDATE: Generate Full-Stack Apps EASILY! FREE Cursor Composer Alternative: th-cam.com/video/gl5Mk7rRrcw/w-d-xo.html
So Kotaemon or Ragflow ? Seems ragflow are adding rapidly integration with tier sources like Wikipedia and so on.
Ragflow as of now but that is because kotaemon is fairly new. Its UI is fairly easy to work around which is nice.
What about open webui
RagFlow is being difficult to deploy
Check out NVIDIA NIM Agent Blueprints: nvda.ws/3MlKBYj
RapidPages: Generate UI Compoents In Real-Time! (Opensource) - th-cam.com/video/UUiiy-zyaNI/w-d-xo.html
Does anybody know if other data types can added with available code? Like json / geojson for example. I think this repo is based and or created with other frameworks? I know langchain has jsontools, but I like to know if I can add dataloaders from the "orriginal" framework if available.
Or does someone know a repo that has a lot of different data type as input, so I can create the RAG / GraphRAG with another repo, or maybe convert the files first and use an available/builtin loader?
If conversion first is needed, what data type is best to use (mostly for tabular files) so it can be loaded with the least extra (double) conversion?