Summarization models #393

Kolpnick · 2023-04-16T18:21:24Z

No description provided.

smilni · 2023-06-30T15:48:09Z

annotators/summarization_annotator/server.py

+    logger.info(dialog)
+
+    try:
+        summary = requests.post(SUMMARIZATION_SERVICE_URL, json={"sentences": dialog}, timeout=3).json()[0]['batch']


3 -- мало. у меня один из твоих тестов из-за этого не проходит (логи). я бы поставила ну хотя бы 5 (хотя для пересказов диалогов с генеративками где одна реплика может содержать кучу токенов и этого будет мало) или вообще этот таймаут вынесла как аргумент, как сделано у генеративных сервисов. но про вынести не уверена, надо у Дили уточнить.

в пайплане соответственно тоже увеличить надо будет

Исправил в коммите

annotators/summarization_annotator/test.py

annotators/summarization_annotator/server.py

smilni · 2023-06-30T16:21:39Z

annotators/summarization_annotator/pipeline.yml

+- group: annotators
+  connector:
+    protocol: http
+    timeout: 2.0


в других местах у тебя другой таймаут у summarization-annotator

Исправил в коммите

smilni · 2023-06-30T16:22:44Z

services/brio_summarizer/pipeline.yml

+- group: services
+  connector:
+    protocol: http
+    timeout: 2.0


Исправил в коммите

smilni · 2023-06-30T16:23:03Z

services/ruT5_summarizer/pipeline.yml

+- group: services
+  connector:
+    protocol: http
+    timeout: 2.0


тоже мало

Исправил в коммите

smilni · 2023-06-30T16:32:39Z

annotators/summarization_annotator/component.yml

+  is_customizable: false
+  author: DeepPavlov
+  description: Annotator that accesses summarization services
+  ram_usage: 1G


так много? в докер-компоуз файле 256мб

Исправил в коммите

256мб, не гб 😦

Не заметил)) Но данный файл всё равно был удалён при изменении карточек в коммите

smilni · 2023-06-30T16:34:58Z

еще -- подмержь свежий дев, разреши конфликт. посмотри на то, как изменились карточки, сделай по образцу сервисов и аннотаторов в деве. добавь карточки в папку components, порты в файл components.tsv (проверь чтоб твои были незаняты, кстати)

annotators/summarization_annotator/server.py

smilni · 2023-07-12T17:32:30Z

assistant_dists/dream/pipeline_conf.json

+                    "directory": "annotators/summarization_annotator",
+                    "container": "summarization-annotator",
+                    "endpoint": "respond"


посмотри как это сделано в других сервисах, сделай по аналогии. карточки сейчас обязательны для всего

то же самое про русский дрим

Исправил в коммите

smilni · 2023-07-13T12:18:39Z

пожалуйста, подмержь свежий дев! и в целом каждый раз когда вносишь изменения, 1) подмерживай дев, 2) разрешай конфликты, если они есть (щас их много)

annotators/summarization_annotator/server.py

smilni · 2023-07-13T14:44:28Z

Общий комментарий по архитектуре -- ты не совсем правильно работаешь с батчами.
Во-первых, в форматтерах по аналогии с другими (utt_sentseg_punct_dialog, full_dialog, etc.) возвращай [{"dialogs": [dialog]}]
И тогда в аннотаторе соответственно доставай и обрабатывай батч (request.json.get('dialogs', [])), а не один диалог

assistant_dists/dream/docker-compose.override.yml

smilni · 2023-07-24T12:22:50Z

annotators/summarization_annotator/server.py

+        result = ""
+        result += prev_summary


может просто result = prev_summary вместо двух строк?

Исправил в коммите

smilni · 2023-07-24T12:25:15Z

annotators/summarization_annotator/server.py

+        if new_summary:
+            result += " " + new_summary
+        result = result.strip()


я бы заменила на

if new_summary: result = f"{result} {new_summary}".strip()

Исправил в коммите

smilni · 2023-07-24T12:26:47Z

services/dialog_summarizer/server.py

+    start_time = time.time()
+    sentences = request.json.get("sentences", [])
+    logger.debug(f"Sentences: {sentences}")
+    tokenized_text = tokenizer(sentences, max_length=512, return_tensors="pt", truncation=True,


а почему больше 512 не может быть?

Исправил в коммите

dilyararimovna

почти все, пару вопросов и все

dilyararimovna · 2023-08-04T13:09:37Z

annotators/summarization_annotator/server.py

+
+    for dialog, prev_summary in zip(dialogs_batch, summaries_batch):
+        logger.info(f"summarization-annotator received dialog: {dialog}")
+        logger.info(f"summarization-annotator received previous summary: {[prev_summary]}")


мб перевести в режим debug эти два лога, а то логи будут быстро разрастаться

Исправил в коммите

dilyararimovna · 2023-08-04T13:09:49Z

annotators/summarization_annotator/server.py

+        if new_summary:
+            result = f"{result} {new_summary}".strip()
+        summarization_attribute.append({"bot_attributes": {"summarized_dialog": result}})
+        logger.info(f"summarization-annotator output: {summarization_attribute}")


ну или оставить только этот принт что ли

dilyararimovna · 2023-08-04T13:11:02Z

annotators/summarization_annotator/server.py

+
+
+def get_summary(dialog):
+    summary = []


почему дефолтное значение лист, если обычно там строка лежит? надо пустую строку сделать дефолтным значением тогда

Исправил в коммите

* Added abstractive summarization model for English texts * Added abstractive summarization model for Russian texts * Added summarization annotator * Moved rut5 summarizer to dream_russian * Changed endpoint * Added model path to Dockerfile * Updated test * Updated summarization annotator input * Updated test * Changed summarization service url * Changed test * Increased timeout * Updated ram_usage * Updated ports * Updated models cards * Added more info messages * Fixed path error * Added summarization output to bot attributes * Added timeout param to dockerfile * Updated model cards and ports * Fixed problem with incorrect batch processing * Updated summarization save format * Updated dialog summarization model * Updated tests * Minor formatting changes * Fixed black and flake8 codestyle * Fixed black codestyle * Updated models ports * Small fixes

* robot first commit (no cards) * feat: do not use sentence ranker url from env (#535) * Feat/ruxglm prompted dist (#528) * feat: ignore env secret ru * feat: add access token * feat: distribution ruxglm * fix: ruxglm cards * fix: use use_auth_token * fix: eos tokens type * fix: stats cpu ram * fix: skills cards * fix: components cards * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: cards and table * fix: ADDITIONAL_EOS_TOKENS * fix: ADDITIONAL_EOS_TOKENS * fix: codestyle * fix: universal * fix: dream persona ru skill name * fix: prompt selector ru * fix: replacement * fix: prompt selecrto * fix: use params * fix: timeout and history * fix: trye very short persona * fix: increase timeout * fix: sub replacement tokens correctly * fix: sub replacement tokens correctly * fix: use stopping criteria * fix: typing * fix: revert long persona * fix: duplicate spaces * fix: correct components for russian distribution * fix: proxy for russian distribution * feat: universal distr for ru * feat: universal distr for ru * fix: remove extra * fix: working configs * fix: configs * feat: ruxglm prompted dists * fix: component cards * fix: container name * fix: remove extra space after new line * fix: remove extra space after new line * feat: tests for dream ruxglm * fix: proxy and ru lang * fix: change port of universal ru * fix: rights on file * fix: tests skills * fix: test for resp selector * fix: tests for proxied components * fix: remove do sample true * fix: generative params * feat: used sentence ranker url * feat: utilized default llm * Feat/ru prompted dists (#532) * feat: ignore env secret ru * feat: add access token * feat: distribution ruxglm * fix: ruxglm cards * fix: use use_auth_token * fix: eos tokens type * fix: stats cpu ram * fix: skills cards * fix: components cards * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: cards and table * fix: ADDITIONAL_EOS_TOKENS * fix: ADDITIONAL_EOS_TOKENS * fix: codestyle * fix: universal * fix: dream persona ru skill name * fix: prompt selector ru * fix: replacement * fix: prompt selecrto * fix: use params * fix: timeout and history * fix: trye very short persona * fix: increase timeout * fix: sub replacement tokens correctly * fix: sub replacement tokens correctly * fix: use stopping criteria * fix: typing * fix: revert long persona * fix: duplicate spaces * fix: correct components for russian distribution * fix: proxy for russian distribution * feat: universal distr for ru * feat: universal distr for ru * fix: remove extra * fix: working configs * fix: configs * feat: ruxglm prompted dists * fix: component cards * fix: container name * first dist (no cards) * fix: remove extra space after new line * fix: remove extra space after new line * feat: tests for dream ruxglm * fix: proxy and ru lang * fix: change port of universal ru * fix: rights on file * fix: tests skills * fix: test for resp selector * multiskill_ru_assistant * fix: tests for proxied components * fairytale and action stories dists * journalist helper dist * fairytale fixes * one more fix * action stories cards * add quotation marks * fairytale cards * storyteller cards * journalist helper cards * multiskill ru cards * agent services cards * minor fixes * fix: utilize sentence ranker url --------- Co-authored-by: dilyararimovna <[email protected]> * update components.tsv (#537) * update components.tsv * tabulation * Feat/rugpt 3.5 distribution (#534) * feat: ignore env secret ru * feat: add access token * feat: distribution ruxglm * fix: ruxglm cards * fix: use use_auth_token * fix: eos tokens type * fix: stats cpu ram * fix: skills cards * fix: components cards * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: eos tokens * fix: cards and table * fix: ADDITIONAL_EOS_TOKENS * fix: ADDITIONAL_EOS_TOKENS * fix: codestyle * fix: universal * fix: dream persona ru skill name * fix: prompt selector ru * fix: replacement * fix: prompt selecrto * fix: use params * fix: timeout and history * fix: trye very short persona * fix: increase timeout * fix: sub replacement tokens correctly * fix: sub replacement tokens correctly * fix: use stopping criteria * fix: typing * fix: revert long persona * fix: duplicate spaces * fix: correct components for russian distribution * fix: proxy for russian distribution * feat: universal distr for ru * feat: universal distr for ru * fix: remove extra * fix: working configs * fix: configs * feat: ruxglm prompted dists * fix: component cards * fix: container name * fix: remove extra space after new line * fix: remove extra space after new line * feat: tests for dream ruxglm * fix: proxy and ru lang * fix: change port of universal ru * fix: rights on file * fix: tests skills * fix: test for resp selector * fix: tests for proxied components * feat: rugpt-3.5 by sber in universal russian distribution * fix; wait for it * fix: models card * fix: models card * fix: add to list * fix: change port * fix: change port * fix: change size to correct * feat: instruction how to add a new model * fix ru prompt selector, remove unused component (#538) * feat: replace oasst12b with gptjt (#541) * Feat/utilize rugpt35 (#540) * feat: utilize rugpt35 * feat: tests for jounrlist rugpt35 * feat: tests for jounrlist rugpt35 * fix: rights for tfile * feat: names * fix: ru_dists_names_and_prompts (#543) * rename ruxglm to u * more renaming * tabs * tabs * some more renaming * short prompt * many cards and name changes * fix typo * fixes for Dilya * tiny fix * tiny fix * huge name check * names * typo prompt * fix: no tests for non existing skills --------- Co-authored-by: dilyararimovna <[email protected]> * fix: cards for ru dists (#544) * fix: rugpt35 config and envs (#546) * Summarization models (#393) * Added abstractive summarization model for English texts * Added abstractive summarization model for Russian texts * Added summarization annotator * Moved rut5 summarizer to dream_russian * Changed endpoint * Added model path to Dockerfile * Updated test * Updated summarization annotator input * Updated test * Changed summarization service url * Changed test * Increased timeout * Updated ram_usage * Updated ports * Updated models cards * Added more info messages * Fixed path error * Added summarization output to bot attributes * Added timeout param to dockerfile * Updated model cards and ports * Fixed problem with incorrect batch processing * Updated summarization save format * Updated dialog summarization model * Updated tests * Minor formatting changes * Fixed black and flake8 codestyle * Fixed black codestyle * Updated models ports * Small fixes * Models table upd (#539) * Fix requirements.txt (#84) * fix itsdangerous requirements * pin itsdangerous requirements for all flask==1.1.1 servers * updated MODELS.md table: added info about models' licensing and commercial use + merged link+name cols to improve overall readability and decrease redundancy * Update MODELS.md fixed "is" for better consistency * fix: format table and add new models back * fix: sizes of models on gpu * updated table --------- Co-authored-by: Andrii.Hura <[email protected]> Co-authored-by: mtalimanchuk <[email protected]> Co-authored-by: Dilyara Baymurzina <[email protected]> * fix: anthropic model params (#547) * fix summarization annotator card (#549) * add cards for prompted robot * ports and n_utt * port * increase WAIT_HOSTS_TIMEOUT in cards --------- Co-authored-by: Dilyara Zharikova (Baymurzina) <[email protected]> Co-authored-by: Maxim Talimanchuk <[email protected]> Co-authored-by: Nikolay <[email protected]> Co-authored-by: Anastásis <[email protected]> Co-authored-by: Andrii.Hura <[email protected]>

Kolpnick and others added 12 commits April 16, 2023 21:17

Added abstractive summarization model for English texts

a627aef

Added abstractive summarization model for Russian texts

75c4a74

Added summarization annotator

783e3ba

Moved rut5 summarizer to dream_russian

f754ff9

Changed endpoint

4be04a4

Added model path to Dockerfile

d41b8bc

Updated test

42bb9c6

Updated summarization annotator input

6c86a2f

Updated test

19bdfe6

Changed summarization service url

1e67609

Changed test

7805fe8

Merge branch 'dev' into summarization_models

bf3ebf4

dilyararimovna requested a review from smilni June 30, 2023 06:34

smilni requested changes Jun 30, 2023

View reviewed changes

smilni reviewed Jun 30, 2023

View reviewed changes

Kolpnick and others added 8 commits July 4, 2023 10:34

Merge branch 'dev' into summarization_models

5419d7e

Increased timeout

8c54ef8

Updated ram_usage

9398288

Updated ports

9364d4e

Updated models cards

9ba8452

Added more info messages

69ee92d

Fixed path error

b90597b

Added summarization output to bot attributes

b115153

smilni reviewed Jul 12, 2023

View reviewed changes

annotators/summarization_annotator/server.py Show resolved Hide resolved

smilni reviewed Jul 12, 2023

View reviewed changes

smilni reviewed Jul 13, 2023

View reviewed changes

annotators/summarization_annotator/server.py Show resolved Hide resolved

Merge branch 'dev' into summarization_models

c94de38

Kolpnick added 6 commits July 20, 2023 11:53

Added timeout param to dockerfile

9ca6ad8

Updated model cards and ports

c60225c

Fixed problem with incorrect batch processing

8def7d0

Updated summarization save format

e744657

Updated dialog summarization model

4ad6e46

Updated tests

487ad86

smilni reviewed Jul 24, 2023

View reviewed changes

Kolpnick and others added 5 commits July 24, 2023 15:52

Minor formatting changes

8d1f484

Fixed black and flake8 codestyle

71cad71

Fixed black codestyle

f2820ef

Merge branch 'dev' into summarization_models

09e2145

Updated models ports

da489f1

dilyararimovna requested changes Aug 4, 2023

View reviewed changes

Small fixes

03b675f

dilyararimovna approved these changes Aug 4, 2023

View reviewed changes

dilyararimovna merged commit fe6adc7 into deeppavlov:dev Aug 4, 2023
2 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Summarization models #393

Summarization models #393

Kolpnick commented Apr 16, 2023

smilni Jun 30, 2023

smilni Jun 30, 2023

Kolpnick Jul 4, 2023

smilni Jun 30, 2023

Kolpnick Jul 4, 2023

smilni Jun 30, 2023

Kolpnick Jul 4, 2023

smilni Jun 30, 2023

Kolpnick Jul 4, 2023

smilni Jun 30, 2023

Kolpnick Jul 4, 2023 •

edited

Loading

smilni Jul 12, 2023

Kolpnick Jul 20, 2023

smilni commented Jun 30, 2023

smilni Jul 12, 2023

smilni Jul 13, 2023

Kolpnick Jul 20, 2023

smilni commented Jul 13, 2023

smilni commented Jul 13, 2023

smilni Jul 24, 2023

Kolpnick Jul 24, 2023

smilni Jul 24, 2023

Kolpnick Jul 24, 2023

smilni Jul 24, 2023

Kolpnick Jul 24, 2023

dilyararimovna left a comment

dilyararimovna Aug 4, 2023

Kolpnick Aug 4, 2023

dilyararimovna Aug 4, 2023

dilyararimovna Aug 4, 2023

Kolpnick Aug 4, 2023

Summarization models #393

Summarization models #393

Conversation

Kolpnick commented Apr 16, 2023

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Kolpnick Jul 4, 2023 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

smilni commented Jun 30, 2023

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

smilni commented Jul 13, 2023

smilni commented Jul 13, 2023

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

dilyararimovna left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Kolpnick Jul 4, 2023 •

edited

Loading