top | item 40529501 (no title) pierre | 1 year ago RAG cli from llamaindex, allow you to do it 100% locally when used with ollama or llamacpp instead of OpenAI.https://docs.llamaindex.ai/en/stable/getting_started/starter... discuss order hn newest homarp|1 year ago and at some point (https://github.com/ggerganov/llama.cpp/issues/7444) you will be able to use Phi-3-vision https://huggingface.co/microsoft/Phi-3-vision-128k-instructbut for now you will have to use python.You can try it here https://ai.azure.com/explore/models/Phi-3-vision-128k-instru... to get an idea of its OCR + QA abilities nl|1 year ago Does the llamaindex PDF indexer correctly deal with multi-column PDFs? Most I've seen don't, and you get very odd results because of this. rspoerri|1 year ago i've made quite good conversions from pdf to markdown with https://github.com/VikParuchuri/marker . it's slow but worth a shot. Markdown should be easily parseable by a rag.i'm trying to get a similar system setup on my computer. load replies (1) pierre|1 year ago Locally you can choose pypdf or mupdf wich are good but not perfect. If you can send your data online llamaparse is quite good. load replies (1) jd3|1 year ago basically, still the same answer(s) fromhttps://news.ycombinator.com/item?id=38759877https://news.ycombinator.com/item?id=36832572 tspann|1 year ago https://milvus.io/docs/integrate_with_llamaindex.mdPretty easy to run local and lightweight with Milvus Lite with LlamaIndex ekianjo|1 year ago llamaindex has an horrible API, very poor docs and is constantly changing. I do not recommend it. papichulo2023|1 year ago Any alternative? load replies (2)
homarp|1 year ago and at some point (https://github.com/ggerganov/llama.cpp/issues/7444) you will be able to use Phi-3-vision https://huggingface.co/microsoft/Phi-3-vision-128k-instructbut for now you will have to use python.You can try it here https://ai.azure.com/explore/models/Phi-3-vision-128k-instru... to get an idea of its OCR + QA abilities
nl|1 year ago Does the llamaindex PDF indexer correctly deal with multi-column PDFs? Most I've seen don't, and you get very odd results because of this. rspoerri|1 year ago i've made quite good conversions from pdf to markdown with https://github.com/VikParuchuri/marker . it's slow but worth a shot. Markdown should be easily parseable by a rag.i'm trying to get a similar system setup on my computer. load replies (1) pierre|1 year ago Locally you can choose pypdf or mupdf wich are good but not perfect. If you can send your data online llamaparse is quite good. load replies (1)
rspoerri|1 year ago i've made quite good conversions from pdf to markdown with https://github.com/VikParuchuri/marker . it's slow but worth a shot. Markdown should be easily parseable by a rag.i'm trying to get a similar system setup on my computer. load replies (1)
pierre|1 year ago Locally you can choose pypdf or mupdf wich are good but not perfect. If you can send your data online llamaparse is quite good. load replies (1)
jd3|1 year ago basically, still the same answer(s) fromhttps://news.ycombinator.com/item?id=38759877https://news.ycombinator.com/item?id=36832572
tspann|1 year ago https://milvus.io/docs/integrate_with_llamaindex.mdPretty easy to run local and lightweight with Milvus Lite with LlamaIndex
ekianjo|1 year ago llamaindex has an horrible API, very poor docs and is constantly changing. I do not recommend it. papichulo2023|1 year ago Any alternative? load replies (2)
homarp|1 year ago
but for now you will have to use python.
You can try it here https://ai.azure.com/explore/models/Phi-3-vision-128k-instru... to get an idea of its OCR + QA abilities
nl|1 year ago
rspoerri|1 year ago
i'm trying to get a similar system setup on my computer.
pierre|1 year ago
jd3|1 year ago
https://news.ycombinator.com/item?id=38759877
https://news.ycombinator.com/item?id=36832572
tspann|1 year ago
Pretty easy to run local and lightweight with Milvus Lite with LlamaIndex
ekianjo|1 year ago
papichulo2023|1 year ago