Changelog

v3.0.0 (2024-05-27)

🌟 Highlights

• Add llama 3 model 🦙🦙🦙

• Add fine tuning with deployments

• Add lm-evaluation-harness extension

See 📚 Examples for more information.

🚀 Features / Enhancements

• feat: new llama model #(356) [@David-Kristek]

• feat: add lm_eval extension #(345) [@jezekra1, @yoavkatz]

• feat: add fine-tuning with deployments #(357) [@David-Kristek]

🐛 Bug Fixes

• fix(huggingface): fix not working default tool #(355) [@David-Kristek]

• fix(llama-index): avoid batching in embeddings #(353) [@David-Kristek]

📖 Docs

• docs: update migration guide [@jezekra1]

• docs(example): typo in text moderation [@lmandel]

• docs(moderation): update description [@Tomas2D]

⚙️ Other

• chore: remove deprecated code #(358) [@jezekra1]

• ci: deploy documentation after new version gets published [@Tomas2D]

• chore: update dependencies [@Tomas2D]

Full Changelog: v2.3.0…v3.0.0

Warning

We have removed deprecations introduced after v2 release. See the V3 Migration Guide for detailed information.

🔗 API Endpoint Versions

API Endpoint Versions

Method	Path	Version (YYYY-MM-DD)
GET	/v2/api_key	2023-11-22
POST	/v2/api_key/regenerate	2023-11-22
GET	/v2/beta/evaluations	2023-11-22
POST	/v2/beta/evaluations	2023-11-22
GET	/v2/beta/evaluations/experiments	2023-11-22
POST	/v2/beta/evaluations/experiments	2023-11-22
DELETE	/v2/beta/evaluations/experiments/{id}	2023-11-22
GET	/v2/beta/evaluations/experiments/{id}	2023-11-22
GET	/v2/beta/evaluations/limits	2023-11-22
POST	/v2/beta/evaluations/preview	2023-11-22
GET	/v2/beta/evaluations/templates	2023-11-22
GET	/v2/beta/evaluations/templates/{id}	2023-11-22
DELETE	/v2/beta/evaluations/{id}	2023-11-22
GET	/v2/beta/evaluations/{id}	2023-11-22
GET	/v2/beta/evaluations/{id}/instance_results	2023-11-22
POST	/v2/beta/text/classification	2023-11-22
POST	/v2/beta/text/rerank	2023-11-22
POST	/v2/beta/text/sentence-similarity	2023-11-22
POST	/v2/beta/time_series/forecasting	2023-11-22
GET	/v2/beta/time_series/limits	2023-11-22
GET	/v2/deployments	2023-11-22
POST	/v2/deployments	2023-11-22
DELETE	/v2/deployments/{id}	2023-11-22
GET	/v2/deployments/{id}	2023-11-22
GET	/v2/files	2024-05-13
POST	/v2/files	2024-05-13
DELETE	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}	2024-05-13
PATCH	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}/content	2023-11-22
GET	/v2/folders	2023-11-22
POST	/v2/folders	2023-11-22
DELETE	/v2/folders/{id}	2023-11-22
GET	/v2/folders/{id}	2023-11-22
PATCH	/v2/folders/{id}	2024-01-10
PUT	/v2/folders/{id}	2023-11-22
GET	/v2/models	2023-11-22
GET	/v2/models/{id}	2024-01-30
GET	/v2/prompts	2024-03-19
POST	/v2/prompts	2024-03-19
DELETE	/v2/prompts/{id}	2023-11-22
GET	/v2/prompts/{id}	2024-03-19
PATCH	/v2/prompts/{id}	2024-03-19
PUT	/v2/prompts/{id}	2024-03-19
GET	/v2/requests	2023-11-22
DELETE	/v2/requests/chat/{conversation_id}	2023-11-22
GET	/v2/requests/chat/{conversation_id}	2024-03-19
DELETE	/v2/requests/{id}	2023-11-22
GET	/v2/requests/{id}/feedback	2023-11-22
POST	/v2/requests/{id}/feedback	2023-11-22
PUT	/v2/requests/{id}/feedback	2023-11-22
GET	/v2/system_prompts	2023-11-22
POST	/v2/system_prompts	2023-11-22
DELETE	/v2/system_prompts/{id}	2023-11-22
GET	/v2/system_prompts/{id}	2023-11-22
PUT	/v2/system_prompts/{id}	2023-11-22
GET	/v2/tags	2023-11-22
GET	/v2/tasks	2023-11-22
POST	/v2/text/chat	2024-03-19
POST	/v2/text/chat/output	2024-03-19
POST	/v2/text/chat_stream	2024-03-19
POST	/v2/text/embeddings	2024-04-15
GET	/v2/text/embeddings/limits	2023-11-22
GET	/v2/text/extraction/limits	2023-11-22
POST	/v2/text/generation	2024-03-19
POST	/v2/text/generation/comparison	2024-03-19
GET	/v2/text/generation/limits	2023-11-22
POST	/v2/text/generation/output	2024-03-19
GET	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation/{id}/feedback	2024-02-20
PUT	/v2/text/generation/{id}/feedback	2024-02-20
POST	/v2/text/generation_stream	2024-03-19
POST	/v2/text/moderations	2024-03-19
POST	/v2/text/tokenization	2024-01-10
GET	/v2/tunes	2023-11-22
POST	/v2/tunes	2023-11-22
POST	/v2/tunes/import	2023-11-22
POST	/v2/tunes/preflight	2023-11-22
DELETE	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}	2023-11-22
PATCH	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}/content	2023-11-22
GET	/v2/tunes/{id}/content/{type}	2023-12-15
GET	/v2/tuning_types	2024-01-30
DELETE	/v2/user	2023-11-22
GET	/v2/user	2023-11-22
PATCH	/v2/user	2023-11-22
POST	/v2/user	2023-11-22

v2.3.0 (2024-03-22)

• Add Text Experimental module (see client.text.experimental)

  • Sentence Similarity (client.text.sentence_similarity).

  • Rerank (client.text.experimental.rerank).

  • Classification (client.text.experimental.classification).

• Add Folder module (client.folder).

• Add Tags module (client.tag).

• Add Tasks module (client.task).

• Add Request Feedback Service (client.request.feedback).

• Update Moderations.

  • Add Social Bias model.

  • Remove Implicit Hate and Stigma model.

• Add tune creation from an existing file (client.tune.create_from_file).

• Allow to upload arbitrary files (remove old constraints for json files only).

• Add support to update the file content (see client.file.update method).

• Add support for the latest LangChain / LLamaIndex (migrate to 0.10.x) / Transformers versions.

• Unify schemas between various services.

Deprecation Warnings

• Stigma (ModerationStigma class) has been deprecated, use Social Bias instead (ModerationSocialBias class).

• Implicit Hate (ModerationImplicitHate class) has been deprecated, use Social Bias instead (ModerationSocialBias class).

from genai.schema import ModerationHAP, ModerationHAPInput

 # ❌ Old Way
ModerationHAP(input=True, output=True, threshold=0.8)

 # ✅ New Way
ModerationHAP(
    input=ModerationHAPInput(enabled=True, threshold=0.8),
    output=ModerationHAPOutput(enabled=True, threshold=0.8)
)

• Deprecate TuningType enum; use values from client.tune.types() method.

• Following schemas or their properties were renamed.

  • UserPromptResult -> PromptResult

  • PromptsResponseResult -> PromptResult

  • UserResponseResult -> UserResult

  • UserCreateResultApiKey -> UserApiKey

  • PromptRetrieveRequestParamsSource -> PromptListSource

  • TextChatStreamCreateResponse.moderation -> TextChatStreamCreateResponse.moderations

  • TextGenerationStreamCreateResponse.moderation -> TextGenerationStreamCreateResponse.moderations

  • TextGenerationResult.moderation -> TextGenerationResult.moderations

  • BaseMessage.file_ids -> BaseMessage.files

🚀 Features / Enhancements

• feat(text): update schemas [@Tomas2D]

• feat(request): update schemas [@Tomas2D]

• feat(user): update schemas [@Tomas2D]

• feat(model): update schemas [@Tomas2D]

• feat(prompt): update schemas [@Tomas2D]

• feat(task): init task module [@Tomas2D]

• feat(text): init text experimental module (sentence similarity, rerank, classification) [@Tomas2D]

• feat(tags): init tags module [@Tomas2D]

• feat(folder): init folder module [@Tomas2D]

• feat(llama-index): migrate to v0.10.x #(331) [@Tomas2D]

• feat: add request feedback module and deprecate text generation feedback [@Tomas2D]

• feat: improve schema generation [@Tomas2D]

• feat: infer openapi schema type [@Tomas2D]

• feat: add fallback for deprecated/removed schemas [@Tomas2D]

• feat: add support for custom auth #(335) [@jezekra1]

• feat(text): add input property to text generation to align with API [@Tomas2D]

• feat(tune): replace static tuning type enum by dynamic retrieval [@Tomas2D]

• feat(extension): add comments to the local server example [@Tomas2D]

• feat(prompt): update folder_id parameter [@Tomas2D]

• feat(user): update schemas (email property added) [@Tomas2D]

• feat(file): add update method, add ‘origin_id’ parameter and schema [@Tomas2D]

• feat(request): update request chat conversation response body [@Tomas2D]

🐛 Bug Fixes

• fix(tune): unexpected access to non-enum property [@Tomas2D]

📖 Docs

• docs(readme): update watsonx SDK URL #(339) [@JanPokorny]

• docs: update furo template [@Tomas2D]

• docs: update authors [@Tomas2D]

• docs: update examples descriptions [@Tomas2D]

• docs: switch to sphinx-multiversion fork #(326) [@Tomas2D]

• docs(folder): update example [@Tomas2D]

• docs(folder): update folder example [@Tomas2D]

⚙️ Other

• test(langchain): use ‘invoke’ method instead ‘__call__’ [@Tomas2D]

• test: add tests for schema deprecation [@Tomas2D]

• test: add tests for endpoint aliases [@Tomas2D]

• test: remove non existing models [@Tomas2D]

Full Changelog: v2.2.0…v2.3.0

🔗 API Endpoint Versions

API Endpoint Versions

Method	Path	Version (YYYY-MM-DD)
GET	/v2/api_key	2023-11-22
POST	/v2/api_key/regenerate	2023-11-22
POST	/v2/beta/text/classification	2023-11-22
POST	/v2/beta/text/rerank	2023-11-22
POST	/v2/beta/text/sentence-similarity	2023-11-22
POST	/v2/beta/time_series/forecasting	2023-11-22
GET	/v2/beta/time_series/limits	2023-11-22
GET	/v2/files	2023-12-15
POST	/v2/files	2023-12-15
DELETE	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}	2023-12-15
PATCH	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}/content	2023-11-22
GET	/v2/folders	2023-11-22
POST	/v2/folders	2023-11-22
DELETE	/v2/folders/{id}	2023-11-22
GET	/v2/folders/{id}	2023-11-22
PATCH	/v2/folders/{id}	2024-01-10
PUT	/v2/folders/{id}	2023-11-22
GET	/v2/models	2023-11-22
GET	/v2/models/{id}	2024-01-30
GET	/v2/prompts	2024-03-19
POST	/v2/prompts	2024-03-19
DELETE	/v2/prompts/{id}	2023-11-22
GET	/v2/prompts/{id}	2024-03-19
PATCH	/v2/prompts/{id}	2024-03-19
PUT	/v2/prompts/{id}	2024-03-19
GET	/v2/requests	2023-11-22
DELETE	/v2/requests/chat/{conversation_id}	2023-11-22
GET	/v2/requests/chat/{conversation_id}	2024-03-19
DELETE	/v2/requests/{id}	2023-11-22
GET	/v2/requests/{id}/feedback	2023-11-22
POST	/v2/requests/{id}/feedback	2023-11-22
PUT	/v2/requests/{id}/feedback	2023-11-22
GET	/v2/system_prompts	2023-11-22
POST	/v2/system_prompts	2023-11-22
DELETE	/v2/system_prompts/{id}	2023-11-22
GET	/v2/system_prompts/{id}	2023-11-22
PUT	/v2/system_prompts/{id}	2023-11-22
GET	/v2/tags	2023-11-22
GET	/v2/tasks	2023-11-22
POST	/v2/text/chat	2024-03-19
POST	/v2/text/chat/output	2024-03-19
POST	/v2/text/chat_stream	2024-03-19
POST	/v2/text/embeddings	2023-11-22
GET	/v2/text/embeddings/limits	2023-11-22
GET	/v2/text/extraction/limits	2023-11-22
POST	/v2/text/generation	2024-03-19
POST	/v2/text/generation/comparison	2024-03-19
GET	/v2/text/generation/limits	2023-11-22
POST	/v2/text/generation/output	2024-03-19
GET	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation/{id}/feedback	2024-02-20
PUT	/v2/text/generation/{id}/feedback	2024-02-20
POST	/v2/text/generation_stream	2024-03-19
POST	/v2/text/moderations	2024-03-19
POST	/v2/text/tokenization	2024-01-10
GET	/v2/tunes	2023-11-22
POST	/v2/tunes	2023-11-22
POST	/v2/tunes/import	2023-11-22
DELETE	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}	2023-11-22
PATCH	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}/content/{type}	2023-12-15
GET	/v2/tuning_types	2024-01-30
DELETE	/v2/user	2023-11-22
GET	/v2/user	2023-11-22
PATCH	/v2/user	2023-11-22
POST	/v2/user	2023-11-22

v2.2.0 (2024-02-20)

🚀 Features / Enhancements

• feat(llama-index): add embeddings #(316) [@David-Kristek]

🐛 Bug Fixes

• fix: improve http error handling #(320) [@Tomas2D]

• fix: allow the remaining limit to have a negative value #(317) [@Tomas2D]

• fix: correct typo in url #(310) [SOTAkkkk]

📖 Docs

• docs: add simple text generation example #(323) [@Tomas2D]

⚙️ Other

• chore: fixes and updates #(318) [@Tomas2D]

• typo: fix bam api url in documentation #(319) [Aditya Gupta]

• docs(langchain): add langchain sql agent example #(314) [@Tomas2D]

• chore: less strict typings #(315) [@David-Kristek]

• chore: improve types generation #(312) [@Tomas2D]

Full Changelog: v2.1.1…v2.2.0

🔗 API Endpoint Versions

API Endpoint Versions

Method	Path	Version (YYYY-MM-DD)
GET	/v2/api_key	2023-11-22
POST	/v2/api_key/regenerate	2023-11-22
GET	/v2/files	2023-12-15
POST	/v2/files	2023-12-15
DELETE	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}	2023-12-15
GET	/v2/files/{id}/content	2023-11-22
GET	/v2/models	2023-11-22
GET	/v2/models/{id}	2024-01-30
GET	/v2/prompts	2024-01-10
POST	/v2/prompts	2024-01-10
DELETE	/v2/prompts/{id}	2023-11-22
GET	/v2/prompts/{id}	2024-01-10
PATCH	/v2/prompts/{id}	2024-01-10
PUT	/v2/prompts/{id}	2024-01-10
GET	/v2/requests	2023-11-22
DELETE	/v2/requests/chat/{conversationId}	2023-11-22
GET	/v2/requests/chat/{conversationId}	2023-11-22
DELETE	/v2/requests/{id}	2023-11-22
GET	/v2/system_prompts	2023-11-22
POST	/v2/system_prompts	2023-11-22
DELETE	/v2/system_prompts/{id}	2023-11-22
GET	/v2/system_prompts/{id}	2023-11-22
PUT	/v2/system_prompts/{id}	2023-11-22
GET	/v2/tasks	2023-11-22
POST	/v2/text/chat	2024-01-10
POST	/v2/text/chat/output	2024-01-10
POST	/v2/text/chat_stream	2024-01-10
POST	/v2/text/embeddings	2023-11-22
GET	/v2/text/embeddings/limits	2023-11-22
GET	/v2/text/extraction/limits	2023-11-22
POST	/v2/text/generation	2024-01-10
POST	/v2/text/generation/comparison	2023-11-22
GET	/v2/text/generation/limits	2023-11-22
POST	/v2/text/generation/output	2023-11-22
GET	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation/{id}/feedback	2023-11-22
PUT	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation_stream	2024-01-10
POST	/v2/text/moderations	2023-11-22
POST	/v2/text/tokenization	2024-01-10
GET	/v2/tunes	2023-11-22
POST	/v2/tunes	2023-11-22
POST	/v2/tunes/import	2023-11-22
DELETE	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}	2023-11-22
PATCH	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}/content/{type}	2023-12-15
GET	/v2/tuning_types	2024-01-30
DELETE	/v2/user	2023-11-22
GET	/v2/user	2023-11-22
PATCH	/v2/user	2023-11-22
POST	/v2/user	2023-11-22

v2.1.1 (2024-02-02)

🐛 Bug Fixes

• fix: make SharedResource threadsafe #(307) [@jezekra1]

• fix: point readme documentation links to latest version #(306) [@jezekra1]

⚙️ Other

• feat(langchain): validate peer dependency #(308) [@Tomas2D]

• fix(docs): update pre-build hook [@Tomas2D]

Full Changelog: v2.1.0…v2.1.1

v2.1.0 (2024-01-30)

Schema Import (deprecation warning)

Schemas are now exported from genai.schema (the old way of importing remains to work, but you will receive a warning)

🚀 Features / Enhancements

• feat: refactor schemas for better user experience #(294) [@jezekra1]

• feat: add truncate_input_tokens parameter for embeddings #(280) [@jezekra1]

• feat: migrate to langchain_core #(261) [@David-Kristek]

• feat: adjust tests and pipeline to ensure 3.12 compatibility #(259) [@jezekra1]

• feat: retrieve service actions metadata #(260) [@Tomas2D]

• feat(example): add chromadb embedding function #(270) [@Tomas2D]

• feat(langchain): correctly handles prompt_id and model_id #(293) [@Tomas2D]

• feat(system-prompts): init module #(292) [@Tomas2D]

• feat(langchain): add embeddings support #(289) [@Tomas2D]

• feat(examples): add example of langchain agent with tools #(268) [@David-Kristek]

• feat(langchain): update core and related dependencies #(282) [@Tomas2D]

🐛 Bug Fixes

• fix: rewrite test casettes due to vcrpy update #(290) [@jezekra1]

• fix: update vcrpy to released version #(284) [@jezekra1]

• fix: external limiter implementation #(274) [@Tomas2D]

• fix: include overhead in payload size calculation when batching #(266) [@jezekra1]

• fix: reduce maximum payload size [@jezekra1]

• fix: schema action metadata inheritance #(262) [@Tomas2D]

• fix(docs): redirects #(298) [@Tomas2D]

• fix(langchain): templates and models #(293) [@Tomas2D]

📖 Docs

• docs: update links in README [@Tomas2D]

• docs: update link to the migration guide [@Tomas2D]

• docs: init documentation versioning #(296) [@Tomas2D]

• docs: add installation note for extensions #(291) [@Tomas2D]

• docs: update prompt usage example #(275) [@Tomas2D]

• docs: update migration guide, examples, deploy #(271) [@Tomas2D]

• docs: update migration guide #(269) [@jezekra1]

• docs: update README [@Tomas2D]

• docs: update faq / credentials / migration guide #(263) [@Tomas2D]

• docs: add changelog #(257) [@jezekra1]

• docs: improve examples #(258) [@jezekra1]

⚙️ Other

• build: add langchain to dev dependencies [@Tomas2D]

• refactor: remove list comprehensions to preserve type-hints #(301) [@jezekra1]

• ci: update git checkout for documentation build [@Tomas2D]

• ci: update docs build script [@Tomas2D]

• ci: set CODEOWNERS #(267) [@Tomas2D]

• build: remove unused dependencies and update versions #(264) [@Tomas2D]

• ci: check if all tests have markers #(265) [@jezekra1]

Full Changelog: v2.0.0…v2.1.0

🔗 API Endpoint Versions

API Endpoint Versions

Method	Path	Version (YYYY-MM-DD)
GET	/v2/api_key	2023-11-22
POST	/v2/api_key/regenerate	2023-11-22
GET	/v2/files	2023-12-15
POST	/v2/files	2023-12-15
DELETE	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}	2023-12-15
GET	/v2/files/{id}/content	2023-11-22
GET	/v2/models	2023-11-22
GET	/v2/models/{id}	2024-01-30
GET	/v2/prompts	2024-01-10
POST	/v2/prompts	2024-01-10
DELETE	/v2/prompts/{id}	2023-11-22
GET	/v2/prompts/{id}	2024-01-10
PATCH	/v2/prompts/{id}	2024-01-10
PUT	/v2/prompts/{id}	2024-01-10
GET	/v2/requests	2023-11-22
DELETE	/v2/requests/chat/{conversationId}	2023-11-22
GET	/v2/requests/chat/{conversationId}	2023-11-22
DELETE	/v2/requests/{id}	2023-11-22
GET	/v2/system_prompts	2023-11-22
POST	/v2/system_prompts	2023-11-22
DELETE	/v2/system_prompts/{id}	2023-11-22
GET	/v2/system_prompts/{id}	2023-11-22
PUT	/v2/system_prompts/{id}	2023-11-22
GET	/v2/tasks	2023-11-22
POST	/v2/text/chat	2024-01-10
POST	/v2/text/chat/output	2024-01-10
POST	/v2/text/chat_stream	2024-01-10
POST	/v2/text/embeddings	2023-11-22
GET	/v2/text/embeddings/limits	2023-11-22
GET	/v2/text/extraction/limits	2023-11-22
POST	/v2/text/generation	2024-01-10
POST	/v2/text/generation/comparison	2023-11-22
GET	/v2/text/generation/limits	2023-11-22
POST	/v2/text/generation/output	2023-11-22
GET	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation/{id}/feedback	2023-11-22
PUT	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation_stream	2024-01-10
POST	/v2/text/moderations	2023-11-22
POST	/v2/text/tokenization	2024-01-10
GET	/v2/tunes	2023-11-22
POST	/v2/tunes	2023-11-22
POST	/v2/tunes/import	2023-11-22
DELETE	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}	2023-11-22
PATCH	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}/content/{type}	2023-12-15
GET	/v2/tuning_types	2024-01-30
DELETE	/v2/user	2023-11-22
GET	/v2/user	2023-11-22
PATCH	/v2/user	2023-11-22
POST	/v2/user	2023-11-22

v2.0.0 (2024-01-15)

On November 22nd, 2023, the API (v2) was announced. We reflected this change on the Python SDK by rewriting its core to be faster, more reliable and mainly in sync with the API. The new SDK brings the concept of the central client, which gives you access to the API very straightforward. This concept was recently integrated into OpenAI SDK / Cohere SDK, and more are joining.

To seamlessly migrate from V0.X versions to 2.0, we have prepared the Migration Guide. The reborn documentation with a lot of examples will help you get started.

Here is a little sneak peek.

• Very Performant.

• Generated Typings directly from the API.

• Smart Requests Concurrency Handling.

• Retry Mechanism in case of network or API failure.

• Batching Large Requests automatically.

• Easy to extend.

Full Changelog: v0.6.1…v2.0.0

🔗 API Endpoint Versions

API Endpoint Versions

Method	Path	Version (YYYY-MM-DD)
GET	/v2/api_key	2023-11-22
POST	/v2/api_key/regenerate	2023-11-22
GET	/v2/files	2023-12-15
POST	/v2/files	2023-12-15
DELETE	/v2/files/{id}	2023-11-22
GET	/v2/files/{id}	2023-12-15
GET	/v2/files/{id}/content	2023-11-22
GET	/v2/models	2023-11-22
GET	/v2/models/{id}	2024-01-10
GET	/v2/prompts	2024-01-10
POST	/v2/prompts	2024-01-10
DELETE	/v2/prompts/{id}	2023-11-22
GET	/v2/prompts/{id}	2024-01-10
PATCH	/v2/prompts/{id}	2024-01-10
PUT	/v2/prompts/{id}	2024-01-10
GET	/v2/requests	2023-11-22
DELETE	/v2/requests/chat/{conversationId}	2023-11-22
GET	/v2/requests/chat/{conversationId}	2023-11-22
DELETE	/v2/requests/{id}	2023-11-22
GET	/v2/tasks	2023-11-22
POST	/v2/text/chat	2024-01-10
POST	/v2/text/chat/output	2024-01-10
POST	/v2/text/chat_stream	2024-01-10
POST	/v2/text/embeddings	2023-11-22
GET	/v2/text/embeddings/limits	2023-11-22
GET	/v2/text/extraction/limits	2023-11-22
POST	/v2/text/generation	2024-01-10
POST	/v2/text/generation/comparison	2023-11-22
GET	/v2/text/generation/limits	2023-11-22
POST	/v2/text/generation/output	2023-11-22
GET	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation/{id}/feedback	2023-11-22
PUT	/v2/text/generation/{id}/feedback	2023-11-22
POST	/v2/text/generation_stream	2024-01-10
POST	/v2/text/moderations	2023-11-22
POST	/v2/text/tokenization	2024-01-10
GET	/v2/tunes	2023-11-22
POST	/v2/tunes	2023-11-22
POST	/v2/tunes/import	2023-11-22
DELETE	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}	2023-11-22
PATCH	/v2/tunes/{id}	2023-11-22
GET	/v2/tunes/{id}/content/{type}	2023-12-15
GET	/v2/tuning_types	2023-11-22
DELETE	/v2/user	2023-11-22
GET	/v2/user	2023-11-22
PATCH	/v2/user	2023-11-22
POST	/v2/user	2023-11-22

v0.6.1 (2023-12-20)

• fix: correct llama-index import for new version by @David-Kristek in #(243)

• fix(examples): correct Hugging Face example prompt by @David-Kristek in #(244)

• fix: prevent duplicating template with same name by @Tomas2D in #(245)

Full Changelog: v0.6.0…v0.6.1

v0.6.0 (2023-12-08)

• feat(extensions): add support for llamaindex by @David-Kristek in #(238)

• fix: update aiohttp to support python 3.12 by @Tomas2D in #(239)

• fix: add missing init.py in package to fix broken import by @jezekra1 in #(241)

• fix: update maximal local concurrency limit based on API response by @Tomas2D in #(242)

New Contributors

• @jezekra1 made their first contribution in #(241)

Full Changelog: v0.5.1…v0.5.2

v0.5.1 (2023-11-17)

🐛 Bug fixes

• Add missing rate-limit check for tokenize methods

• Unify error messages between sync and async methods

Full Changelog: v0.5.0…v0.5.1

v0.5.0 (2023-11-13)

🚀 Features / Enhancements

• Added integration for LangChain Chat Models; see an example of generation and streaming.

• Added support for LangChain Model Serialization (saving and loading models); see an example.

• Added support for the Chat endpoint in Model class; see an example.

• Added support for new moderation models (HAP, STIGMA, Implicit Hate) - not released on API yet but will be available soon.

• Added type validation for input_tokens property in generate response.

• Extend LangChain generation information / LLM Output (token_usage structure, generated tokens, stop_reason, conversation_id, created_at, …).

• Add optional raw_response=True/False parameter to generate_stream / generate_as_complete and generate methods to receive a raw response instead of unwrapped results.

🐛 Bug fixes

• LangChain extension now correctly tokenizes the inputs (previously, the GPT2 tokenizer had been used).

• Improve general error handling.

Full Changelog: v0.4.1…v0.5.0

v0.4.1 (2023-10-27)

🐛 Bug fixes

• Correctly handle file responses

• Use tqdm.auto instead of tqdm.tqdm to improve display in Jupyter Notebooks

Full Changelog: v0.4.0…v0.4.1

v0.4.0 (2023-10-24)

⚠️ Switch to Pydantic V2

• In case your application is dependent on Pydantic V1, refer to the migration guide.

• If you cannot upgrade, stick to the previous version 0.3.2.

Full Changelog: v0.3.2…v0.4.0

v0.3.2 (2023-10-23)

🐛 Bug fixes

• Correctly handle async errors and process abortion

🔧 Configuration Changes

• Increase async generate/tokenize retry limits from 3 to 5

Full Changelog: v0.3.1…v0.3.2

v0.3.1 (2023-10-20)

🚀 Features / Enhancements

• Handle concurrency limits for generate and generate_as_completed methods.

• Add automatic handling of rate limits for the tokenize endpoint (tokenize_async method).

• Added stop_sequence parameter for generated output (non-empty token which caused the generation to stop) + added - include_stop_sequence parameter for the GenerateParams (it indicates whether the stop sequence (which caused the generation to stop) is part of the generated text. The default value depends on the model in use).

• Removed hidden stop_sequences removal inside the LangChainInterface, which can now be controlled via the include_stop_sequence parameter.

• Improve general error handling + method signatures (improve Python typings).

🐛 Bug fixes

• Fix stacked progress bar (generate_async method)

• Handle cases when the package is used inside the asyncio environment

• Hide warning when an unknown field is retrieved in the generated response

Full Changelog: v0.3.0…v0.3.1

v0.3.0 (2023-10-12)

🚀 Features / Enhancements

• Added Hugging Face Agent support; see an example.

• Drastically improve the speed of generate_async method - the concurrency limit is now automatically inferred from the API. (custom setting of ConnectionManager.MAX_CONCURRENT_GENERATE will be ignored). In case you want to slow down the speed of generating, just pass the following parameter to the method: max_concurrency_limit=1 or any other value.

• Increase the default tokenize processing limits from 5 requests per second to 10 requests per second (this will be increased in the future).

🐛 Bug fixes

• Throws on unhandled exceptions during the generate_async calls. Correctly cleanups the async HTTP clients when the task/calculation is being cancelled (for instance, you call generate_async in Jupyter - Notebook and then click the stop button). This should prevent receiving the Can't have two active async_generate_clients error.

• Fix async support for newer LangChain versions (>=0.0.300)

• Fix LangChain PromptTemplate import warning in newer versions of LangChain

• Correctly handle server errors when streaming

• Fix tune_methods method

v0.2.8 (2023-09-25)

🚀 Features / Enhancements

• Added moderation support; now you can retrieve HAP for generated requests (example)

• Internally improve streaming processing (poor or unstable internet connection)

• Internally improve server response parsing and error handling

• Add a user-agent header to distinguish Python SDK on the API

🐛 Bug fixes

• LangChain - correct handling of stop_sequences

• Correctly set versions of used dependencies (httpx / pyyaml)

• Prevents unexpected modifications to user’s GenerateParams passed to the Model class

• Prevents unexpected errors when GenerateParams contains stream=True and generate (non-stream) version is called

🔧 Configuration changes

• Remove API version from the API endpoint string

Full Changelog: v0.2.7…v0.2.8

v0.2.7 (2023-09-15)

• feat(langchain) - generate method by @Tomas2D in #(157)

• fix(params): do not strip special characters by @Tomas2D in #(153)

• fix: correct httpx dependency version by @Tomas2D in #(158)

Full Changelog: v0.2.6…v0.2.7

v0.2.6 (2023-09-11)

• feat(langchain): add streaming support by @Tomas2D in #(144)

• feat(http): allow override httpx options by @Tomas2D in #(149)

• feat: add typical_p parameter by @Tomas2D in #(135)

• chore: update examples by @Tomas2D in #(136)

• docs: mention CLI in README by @Tomas2D in #(143)

• chore: adding escapting of backslashes for re.sub value by @assaftibm in #(84)

• chore: correct README.md typo by @ind1go in #(148)

• update schema for stop_sequences generate param by @mirianfsilva in #(142)

New Contributors

• @assaftibm made their first contribution in #(84)

• @ind1go made their first contribution in #(148)

Full Changelog: v0.2.5…v0.2.6

v0.2.5 (2023-08-21)

• TOUs handling

• Update Pydantic version

• Update examples

Full Changelog: v0.2.4…v0.2.5

v0.2.4 (2023-08-01)

Updated the documentation (imports of credentials) Updated schemas for config Added params in GeneratedParams Updated examples Updated tests

v0.2.3 (2023-07-24)

• Remove ModelType enum

• Add utils for Model class: listing, info, available, etc.

• Pydantic model allows extra params

• Tests

v0.2.2 (2023-07-11)

Documentation Updates.

v0.2.1 (2023-07-10)

Documentation update Example update

v0.2.0 (2023-07-10)

Model Tuning File manager Tuning Manager ModelType deprecation warning Open Source documentation update

v0.1.19 (2023-06-30)

Fixed pydantic version issue

v0.1.18 (2023-06-30)

Watsonx Templating support Documentation and examples’ update Parameters updated for upstream compatibility with sampling method Retry mechanism update

v0.1.17 (2023-06-23)

• Modifications to examples/tests to avoid sampling-related parameters with greedy decoding

• Updates to build process

• Modifications to error messages

v0.1.16 (2023-06-21)

• Documentation update

• Local server example

• Open source contributions information

• Example endpoints updated

v0.1.15 (2023-06-08)

• 🔨 GitHub Workflows

• ✨ Progress bar in async_generate function

• 🐛 Updating Terms of Use to use PATCH

• 🎨 Adding accessors attribute to model class

• ✨Search Space example and utils

• ✨ Localserver Extension