[NeuralChat] Enable RAG's table extraction and summary

[xmx-521]

Type of Change

feature
API changed

Description

Enable RAG's table extraction functionality for pdf
Enable RAG's table summary functionality, with three modes to choose: [none, title, llm]

Expected Behavior & Potential Risk

User can use RAG's table extraction and summary functionality to get better RAG experience

How has this PR been tested?

Local test and pre-CI

Dependency Change?

add tesseract dependency
add poppler dependency
change unstructured dependency unstructured[all-docs] dependency

[github-actions]

⚡ Required checks status: All passing 🟢

Groups summary

🟢 Format Scan Tests workflow

Check ID	Status	Error details
format-scan (pylint)	success		✅
format-scan (bandit)	success		✅
format-scan (cloc)	success		✅
format-scan (cpplint)	success		✅

These checks are required after the changes to intel_extension_for_transformers/neural_chat/assets/docs/LLAMA2_page6.pdf, intel_extension_for_transformers/neural_chat/chatbot.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/README.md, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/context_utils.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/parser.py, intel_extension_for_transformers/neural_chat/prompts/prompt.py, intel_extension_for_transformers/neural_chat/tests/ci/plugins/retrieval/test_parameters.py, intel_extension_for_transformers/neural_chat/tests/requirements.txt.

🟢 NeuralChat Unit Test

Check ID	Status	Error details
neuralchat-unit-test-baseline	success		✅
neuralchat-unit-test-PR-test	success		✅
Generate-NeuralChat-Report	success		✅

These checks are required after the changes to .github/workflows/script/unitTest/run_unit_test_neuralchat.sh, intel_extension_for_transformers/neural_chat/chatbot.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/README.md, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/context_utils.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/parser.py, intel_extension_for_transformers/neural_chat/prompts/prompt.py, intel_extension_for_transformers/neural_chat/tests/ci/plugins/retrieval/test_parameters.py, intel_extension_for_transformers/neural_chat/tests/requirements.txt.

🟢 Chat Bot Test workflow

Check ID	Status	Error details
call-inference-llama-2-7b-chat-hf / inference test	success		✅
call-inference-mpt-7b-chat / inference test	success		✅

These checks are required after the changes to intel_extension_for_transformers/neural_chat/chatbot.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/README.md, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/context_utils.py, intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/parser/parser.py, intel_extension_for_transformers/neural_chat/prompts/prompt.py, intel_extension_for_transformers/neural_chat/tests/requirements.txt.

---

Thank you for your contribution! 💜

Note
This comment is automatically generated and will be updates every 180 seconds within the next 6 hours. If you have any other questions, contact VincyZhang or XuehaoSun for help.

[Liangyx2]

please add Installation and instruction for pdf table-to-text in intel_extension_for_transformers/neural_chat/pipeline/plugins/retrieval/README.md

[XinyuYe-Intel]

From the code, seems "fast" table_strategy would only return None instead of table content, is this somewhat unreasonable?

It appears "hq" strategy uses unstructured pkg to extract table, I also used this pkg, and find it actually performed worse than table-transformer.

Also does the "llm" strategy return the reliable table contents? From the code, looks like it uses LLM and a prompt to generate the table summarization of the document, but from my previous experience, such way would generate results that significantly deviate the table content sometimes.

[xmx-521]

Thanks for insightful comments, my opinion on these issues are as follows:

From the code, seems "fast" table_strategy would only return None instead of table content, is this somewhat unreasonable?

In fact, by default, our program will use OCR to extract all text information in files including table information, which has been implemented in other PRs. This PR is just to further enhance the understanding of the table, so no content is returned in fast mode (fast mode is also the default mode).

It appears "hq" strategy uses unstructured pkg to extract table, I also used this pkg, and find it actually performed worse than table-transformer.

At present, we do use unstructured to extract table information, and the extraction performance is quite satisfactory. We have not tried the table transformer, but it is indeed worth considering.

Also does the "llm" strategy return the reliable table contents? From the code, looks like it uses LLM and a prompt to generate the table summarization of the document, but from my previous experience, such way would generate results that significantly deviate the table content sometimes.

Your understanding of what llm mode does is correct. It is true that llm's table summary is not completely reliable, but according to the experimental results, there will be much better table QA performance in llm mode overall.