Our great sponsors
-
-
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
-
llama-hub
Discontinued A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain
-
unstructured
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
-
WorkOS
The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.
-
To get good RAG performance you will need a good chunking strategy. Simply getting all the text is not good enough and knowing the boundaries of table, list, paragraph, section etc. is helpful.
Great work by llamaindex team. Also feel free to try https://github.com/nlmatics/llmsherpa which takes into account some of the things I mentioned.
I'm part of the team that build LlamaParse. It's net improvement compare to other PDF->Structured Text extractors (I build several in the past, includig https://github.com/axa-group/Parsr).
For character extraction, LlamaParse use a mixture of OCR / character extraction from the PDF (it's the only parser I'm aware of that address some of the buggy PDF font issues, check the 'text' mode to see raw document before reconstruction), use a mixture of heuristic and Machine learning models to reconstruct the document.
Once plug with a Recursive retrieval strategy, allow you to get Sota result on question answering over complexe text (see notebook: https://github.com/run-llama/llama_parse/blob/main/examples/...).
AMA
I'm part of the team that build LlamaParse. It's net improvement compare to other PDF->Structured Text extractors (I build several in the past, includig https://github.com/axa-group/Parsr).
For character extraction, LlamaParse use a mixture of OCR / character extraction from the PDF (it's the only parser I'm aware of that address some of the buggy PDF font issues, check the 'text' mode to see raw document before reconstruction), use a mixture of heuristic and Machine learning models to reconstruct the document.
Once plug with a Recursive retrieval strategy, allow you to get Sota result on question answering over complexe text (see notebook: https://github.com/run-llama/llama_parse/blob/main/examples/...).
AMA
You may want to try https://github.com/VikParuchuri/surya (I'm the author). I've only benchmarked against tesseract, but it outperforms it by a lot (benchmarks in repo). Happy to discuss.
You could also try https://github.com/VikParuchuri/marker for general PDF parsing (I'm also the author) - it seems like you're more focused on tables.
You may want to try https://github.com/VikParuchuri/surya (I'm the author). I've only benchmarked against tesseract, but it outperforms it by a lot (benchmarks in repo). Happy to discuss.
You could also try https://github.com/VikParuchuri/marker for general PDF parsing (I'm also the author) - it seems like you're more focused on tables.
mean_faithfulness_score 0.667
Notably, the faithfulness score I measured for the baseline solution was actually higher than that reported for your proprietary LlamaParse based solution.
[1] https://github.com/run-llama/llama-hub/tree/main/llama_hub/l...
Be careful with unstructured:
https://github.com/Unstructured-IO/unstructured/blob/d11c70c...
from: https://github.com/open-webui/open-webui/issues/687
Be careful with unstructured:
https://github.com/Unstructured-IO/unstructured/blob/d11c70c...
from: https://github.com/open-webui/open-webui/issues/687