feat: Integrated Vectorization - adding OCR skill

[komalg1]

Purpose

• This PR adds the OCR skill when using Integrated Vectorization to enable search on images.
• Relates to Support image search in Integrated Vectorization #973

Does this introduce a breaking change?

• Yes
• No

How to Test

• Get the code

git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install

What to Check

Verify that the following are valid

• When Integrated Vectorization is enabled, user should be able to upload images with text and search those images

[github-actions]

Coverage Report

File	Stmts	Miss	Cover	Missing
code
app.py	14	14	0%	5–8, 10–11, 14, 17–19, 22, 24, 26–27
create_app.py	137	1	99%	334
code/backend
Admin.py	23	23	0%	5–9, 11, 13–14, 17, 20–21, 23–24, 27, 35–37, 41, 44–46, 48, 50
code/backend/batch
add_url_embeddings.py	47	0	100%
batch_push_results.py	36	0	100%
batch_start_processing.py	26	0	100%
function_app.py	17	17	0%	1–8, 10, 12–14, 16, 19–22
get_conversation_response.py	32	0	100%
code/backend/batch/utilities/common
answer.py	28	2	92%	23, 51
source_document.py	60	5	91%	44, 47, 51, 55, 128
code/backend/batch/utilities/document_chunking
__init__.py	7	0	100%
chunking_strategy.py	15	1	93%	25
document_chunking_base.py	10	2	80%	10, 16
fixed_size_overlap.py	19	0	100%
layout.py	19	0	100%
page.py	17	0	100%
paragraph.py	9	2	77%	9, 15
strategies.py	15	3	80%	15–16, 18
code/backend/batch/utilities/document_loading
__init__.py	15	1	93%	16
document_loading_base.py	9	1	88%	13
layout.py	12	5	58%	9, 12–13, 16, 25
read.py	12	5	58%	9, 12–13, 16, 25
strategies.py	20	5	75%	17, 19, 22–23, 25
web.py	18	1	94%	22
word_document.py	25	13	48%	11–12, 22–24, 27, 30, 33–37, 45
code/backend/batch/utilities/helpers
azure_blob_storage_client.py	85	31	63%	19, 23–25, 33, 57–58, 61, 78–79, 81, 85, 172–175, 179, 182, 184, 192–196, 219, 223–227, 229
azure_computer_vision_client.py	53	0	100%
azure_form_recognizer_helper.py	81	70	13%	11, 13, 16–17, 25, 27, 44–45, 52–55, 60–68, 73–75, 77–78, 81, 84–86, 88–90, 93, 97–98, 105–109, 111–114, 117–131, 133, 135–137, 139–140, 143, 145–147
azure_search_helper.py	57	0	100%
document_chunking_helper.py	13	1	92%	19
document_loading_helper.py	12	1	91%	15
env_helper.py	143	6	95%	246–248, 267–269
llm_helper.py	48	7	85%	42–43, 52, 63–64, 75, 96
orchestrator_helper.py	13	1	92%	24
code/backend/batch/utilities/helpers/config
config_helper.py	138	0	100%
conversation_flow.py	4	0	100%
embedding_config.py	12	1	91%	27
code/backend/batch/utilities/helpers/embedders
embedder_base.py	5	1	80%	7
embedder_factory.py	10	0	100%
integrated_vectorization_embedder.py	36	3	91%	39–41
push_embedder.py	73	0	100%
code/backend/batch/utilities/integrated_vectorization
azure_search_datasource.py	19	0	100%
azure_search_index.py	35	0	100%
azure_search_indexer.py	23	0	100%
azure_search_skillset.py	24	0	100%
code/backend/batch/utilities/loggers
conversation_logger.py	36	2	94%	33–34
code/backend/batch/utilities/orchestrator
__init__.py	11	0	100%
lang_chain_agent.py	60	19	68%	21–24, 26, 61–62, 82–85, 102–103, 106–109, 116–117
open_ai_functions.py	54	11	79%	110–112, 115, 118–119, 122, 127–129, 134
orchestration_strategy.py	6	0	100%
orchestrator_base.py	50	1	98%	33
prompt_flow.py	52	0	100%
semantic_kernel.py	54	0	100%
strategies.py	15	4	73%	12, 15–16, 18
code/backend/batch/utilities/parser
__init__.py	7	2	71%	7, 11
output_parser_tool.py	39	0	100%
parser_base.py	9	2	77%	9, 19
code/backend/batch/utilities/plugins
chat_plugin.py	15	0	100%
post_answering_plugin.py	8	0	100%
code/backend/batch/utilities/search
azure_search_handler.py	64	2	96%	25, 31
integrated_vectorization_search_handler.py	72	1	98%	35
search.py	14	0	100%
search_handler_base.py	48	15	68%	16–18, 21–23, 28, 34, 38, 42, 46, 50, 54, 58, 62
code/backend/batch/utilities/tools
answer_processing_base.py	8	2	75%	8, 12
answering_tool_base.py	9	2	77%	9, 15
content_safety_checker.py	41	9	78%	19, 52–54, 57–59, 66–67
post_prompt_tool.py	17	0	100%
question_answer_tool.py	70	0	100%
text_processing_tool.py	16	0	100%
code/backend/pages
01_Ingest_Data.py	72	72	0%	1–10, 12–14, 16, 24–26, 30, 33–34, 37–40, 42–45, 49–51, 54–56, 59–66, 69–71, 73, 76–79, 82, 87–89, 91–92, 94–95, 98–99, 103–105, 110–113, 120–121, 126, 132–133
02_Explore_Data.py	28	28	0%	1–7, 9–10, 12, 20, 28, 31–33, 37, 40–41, 43–46, 48–51, 54–55
03_Delete_Data.py	41	41	0%	1–8, 10–12, 14, 22–24, 28, 32, 40, 42–43, 45–48, 50, 52–53, 57, 61–65, 67, 70–71, 74–75, 77–79
04_Configuration.py	137	137	0%	1–9, 11–12, 14, 22–24, 28, 30, 35–44, 47–48, 51–62, 64–65, 67–69, 73–74, 86–90, 93–94, 98–100, 103–104, 107–108, 111–112, 135, 137–138, 140–144, 146–149, 152–156, 163–164, 174–176, 178, 198–199, 201, 203, 209, 217, 225, 232–233, 240, 242–243, 247, 255, 261, 268, 286–290, 296–297, 316–317, 321, 323–324, 347, 381–382, 386–387, 390–391, 394–397, 399–400, 402–404, 406–409, 411–412
TOTAL	2579	573	77%

Tests	Skipped	Failures	Errors	Time
288	0 💤	0 ❌	0 🔥	39.180s ⏱️

[adamdougal]

I assume this still works fine for non image based data?

Do any functional tests need adding/updating for this?

[adamdougal]

Great work!

[github-actions]

🎉 This PR is included in version 1.7.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀