Farzad E 6eb251d1f0

fix: Support for gpt-4-32k (#4825) ...

* Add step to loook up tokenizers by prefix in openai_utils

* Updated tiktoken min version + openai_utils test

* Added test case for GPT-4 and Azure model naming

* Broken down tests

* Added default case

---------

Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>

2023-05-12 19:02:12 +02:00

..

agents

skip flaky test (#4846)

2023-05-09 20:26:59 +02:00

benchmarks

refactor: remove direct logging without a logger (#4253)

2023-02-23 20:42:42 +01:00

document_stores

fix: Add support for _split_overlap meta to Pinecone and dict metadata in general to Weaviate (#4805)

2023-05-05 11:20:21 +02:00

mocks

style: Update black (#4101)

2023-02-08 15:34:43 +01:00

modeling

Add modeling to unit tests so it we can get coverage for that (#4809)

2023-05-08 19:05:21 +02:00

nodes

Revert "refactor!: Deprecate name param in PromptTemplate and introduce template_name instead (#4810)" (#4834)

2023-05-08 11:31:04 +02:00

others

test: Update unit tests for schema (#4835)

2023-05-10 16:16:45 +02:00

pipelines

bug: (rest_api) remove full logging of overwritten env variables (#4791)

2023-05-02 16:48:19 +02:00

preview

fix: improve Document comparison (v2) (#4860)

2023-05-11 18:28:56 +02:00

prompt

feat: Add Cohere PromptNode invocation layer (#4827)

2023-05-12 17:50:09 +02:00

samples

test: Update unit tests for schema (#4835)

2023-05-10 16:16:45 +02:00

utils

fix: Support for gpt-4-32k (#4825)

2023-05-12 19:02:12 +02:00

__init__.py

Pipeline's YAML: syntax validation (#2226)

2022-03-15 11:17:26 +01:00

conftest.py

refactor!: extract elasticsearch (#4668)

2023-04-26 10:14:20 +02:00