docs: add chatbot tutorial

[alaeddine-13]

closes: https://github.com/jina-ai/internal-tasks/issues/170

[codecov]

Codecov Report

Merging #3382 (aa726e4) into master (d37e6ab) will increase coverage by 0.53%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #3382      +/-   ##
==========================================
+ Coverage   89.71%   90.24%   +0.53%     
==========================================
  Files         152      152              
  Lines       10840    10840              
==========================================
+ Hits         9725     9783      +58     
+ Misses       1115     1057      -58     

Flag	Coverage Δ
daemon	45.55% <ø> (-0.02%)	⬇️
jina	90.23% <ø> (+0.54%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
jina/peapods/runtimes/jinad/__init__.py	91.42% <0.00%> (-1.91%)	⬇️
jina/types/document/__init__.py	96.07% <0.00%> (+0.78%)	⬆️
jina/helper.py	83.33% <0.00%> (+1.81%)	⬆️
jina/peapods/runtimes/gateway/http/app.py	92.40% <0.00%> (+2.53%)	⬆️
jina/clients/request/__init__.py	100.00% <0.00%> (+5.00%)	⬆️
jina/clients/request/helper.py	83.92% <0.00%> (+5.35%)	⬆️
jina/clients/request/asyncio.py	88.88% <0.00%> (+5.55%)	⬆️
jina/clients/base/__init__.py	92.42% <0.00%> (+18.18%)	⬆️
jina/types/document/generators.py	93.33% <0.00%> (+36.00%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update e7d47c0...aa726e4. Read the comment docs.

[github-actions]

Latency summary

Current PR yields:

• 😶 index QPS at 1118, delta to last 2 avg.: +3%
• 😶 query QPS at 45, delta to last 2 avg.: +1%
• 😶 dam extend QPS at 39289, delta to last 2 avg.: +0%
• 😶 avg flow time within 1.7896 seconds, delta to last 2 avg.: -1%
• 😶 import jina within 0.5008 seconds, delta to last 2 avg.: +3%

Breakdown

Version	Index QPS	Query QPS	DAM Extend QPS	Avg Flow Time (s)	Import Time (s)
current	1118	45	39289	1.7896	0.5008
2.1.0	1154	46	41299	1.7953	0.4554
2.0.24	1006	41	37349	1.8355	0.5155

Backed by latency-tracking. Further commits will update this comment.

[tadejsv]

The code in this tutorial is currently too obtuse, most of the lines are just about downloading the dataset and not actual flow/executor things.

Can you refactor it using huggingface datasets dataset (I think it should be possible), and add some line breaks for readability in the code snippets.

Also, assume that the users are very lazy, when possible try to show what the output of the code snippets would be (huggingface course does this well, see for example https://huggingface.co/course/chapter3/2?fw=pt)

[tadejsv]

My bad, the HF dataset is not the same one as the one used by kaggle. Still, check if the HF one can be a good substitute for Kaggle one

[tadejsv]

I've left some comments that will improve readability, but we really need to get rid of all the downloading code - it's complexity is just dominating over this whole tutorial.

Either we figure out how to use HF datasets (I would create one myself, but am not sure about licensing), or we add instructions in pre-requisites for how to manually download the file from kaggle - that would be much nicer.

[alaeddine-13]

I've left some comments that will improve readability, but we really need to get rid of all the downloading code - it's complexity is just dominating over this whole tutorial.

@tadejsv I think authors of the tutorial opted for downloading each time to make usage faster and easy. Also keep in mind that the downloaded dataset is hosted by jina not kaggle: https://static.jina.ai/chatbot/dataset.csv
I have reduced the size of download_data so that's no more dominating, can you re-check ?

[tadejsv]

Great job, looks much better now. Just some final minor changes

[tadejsv]

Looks good 👍

[alexcg1]

Hmmm...I'm unable to do line comments in the file. Here's my feedback:

We will build a fuzzy search demo on the source code
Change to: We will build a fuzzy search demo for source code

Also re-order tutorials in docs/index.md:

1. Chatbot
2. Executor
3. Executor on GPU
4. Practice learning

[alaeddine-13]

Hmmm...I'm unable to do line comments in the file. Here's my feedback:

We will build a fuzzy search demo on the source code
Change to: We will build a fuzzy search demo for source code

Also re-order tutorials in docs/index.md:

1. Chatbot
2. Executor
3. Executor on GPU
4. Practice learning

done

[alexcg1]

LGTM 👍

[ghost]

Hmmm...I'm unable to do line comments in the file. Here's my feedback:

We will build a fuzzy search demo on the source code

Change to: We will build a fuzzy search demo for source code

Also re-order tutorials in docs/index.md:

1. Chatbot

2. Executor

3. Executor on GPU

4. Practice learning