Azure AI Studio - Prompt Flow RAG

In this video, we are demonstrating the ingestion, chunking, overlapping, embedding and vectorization process of documents in Azure AI Studio Prompt Flows using an Azure AI Search as the vectorization database.

[ImranKhan-ncwp]

That was the best tutorial I've watched so far. Thanks a lot.

[anthonyorzechowski]

Excellent video. Very practical and down to earth for non-CS folks. Great job!

[Jonathan_wow]

Hi Lino, I have few questions about indexing. Hope you can clarify for me. I have uploaded my documents. My documents are mix types like pdf, excel, word, images. Also, some of these like images and pdf have text in non-english languages, so when I choose to do the indexing (consiering vector), will it automatically consider ocr, document intelligence, language detection and translation to target language ? Would you please tell me about it ?

[nicoladuru]

awesome tthank you helped with my masters health assistant llm

[behrouzbeheshti]

I noticed you had to wait for some time for the indexing to finish. Do you recommend indexing the documents (separately) on Azure Search Service-which should be faster-and then connecting the index? Thanks!

[gouthamvijay]

Excellent video, I have followed the exact same procedure except I did indexing in AI search and used the same in prompt flow. When i ran it by asking a question, the bot is loading forever without replying to the question. Any idea or suggestion?

[denizwhite]

Please upload different videos about prompt flow

[itpe_exercise]

very nice. i have a one question. what should i do, if i change the chunking size when the ai search created?

[SendhurapandiS]

Excellent video!, Is there any limitations to upload file size. example this much mb files only it will support like that.

[TadjouLionelIT]

Thanks @LinoTV for this great tutorial. The default number of tokens for chunking is 1024 tokens. Do you have any idea on how to change this value for example to 256 tokens?

[feedali]

Hi lino, I have done the setup as following your instructions. But here I am getting a error on Prompt Flow, On the lookup section there is a error occuring everytime.

It saying this: Run failed: Exception: Exception occured in search_function_construction

Also here is the traceback error:

Traceback (most recent call last):
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/site-packages/pydantic/_internal/_generate_schema.py", line 864, in _resolve_forward_ref
obj = _typing_extra.eval_type_backport(obj,
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/site-packages/pydantic/_internal/_typing_extra.py", line 279, in eval_type_backport
return _eval_type_backport(value, globalns, localns, type_params)
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/site-packages/pydantic/_internal/_typing_extra.py", line 303, in _eval_type_backport
return _eval_type(value, globalns, localns, type_params)
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/site-packages/pydantic/_internal/_typing_extra.py", line 332, in _eval_type
return typing._eval_type( # type: ignore
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/typing.py", line 292, in _eval_type
return t._evaluate(globalns, localns, recursive_guard)
File "/azureml-envs/prompt-flow/runtime/lib/python3.9/typing.py", line 554, in _evaluate
eval(self.__forward_code__, globalns, localns),
File "<string>", line 1, in <module>
NameError: name 'AzureSearch' is not defined

The above exception was the direct cause of the following exception:

Could you please tell me how can I fix it? I have looked a lot of documents but non of them are working.

[nguyenvanly]

Azure AI is really a pain in ass. Errors, synchronization issues and warnings everywhere. And super expensive. Do Microsoft know that this product is garbage ?