Replace this entire comment with:
- **Description:** @kurtisvg has raised a point that it's a good idea to
have a fixed version for embeddings (since otherwise a user might run a
query with one version vs a vectorstore where another version was used).
In order to avoid breaking changes, I'd suggest to give users a warning,
and make a `model_name` a required argument in 1.5 months.
- **Description:** Introducing an ability to work with the
[YandexGPT](https://cloud.yandex.com/en/services/yandexgpt) embeddings
models.
---------
Co-authored-by: Dmitry Tyumentsev <dmitry.tyumentsev@raftds.com>
- **Description:** The Qianfan SDK offers multiple authentication
methods, but in the `QianfanEndpoint` of Langchain, it currently only
supports authentication through AK and SK. In order to accommodate users
who wish to use alternative authentication methods, this pull request
makes AK and SK optional. This change should not impact existing users,
while allowing users to configure other authentication methods as per
the Qianfan SDK documentation.
- **Issue:** /
- **Dependencies:** No
- **Tag maintainer:** No
- **Twitter handle:**
- **Description:** Going forward, we have a own API `pip install
gradientai`. Therefore gradually removing the self-build packages in
llamaindex, haystack and langchain.
- **Issue:** None.
- **Dependencies:** `pip install gradientai`
- **Tag maintainer:** @michaelfeil
This is technically a breaking change because it'll switch out default
models from `text-davinci-003` to `gpt-3.5-turbo-instruct`, but OpenAI
is shutting off those endpoints on 1/4 anyways.
Feels less disruptive to switch out the default instead.
- **Description:** VertexAIEmbeddings performance improvements
- **Twitter handle:** @vladkol
## Improvements
- Dynamic batch size, starting from 250, lowering down to 5. Batch size
varies across regions.
Some regions support larger batches, and it significantly improves
performance.
When running large batches of texts in `us-central1`, performance gain
can be up to 3.5x.
The dynamic batching also makes sure every batch is below 20K token
limit.
- New model parameter `embeddings_type` that translates to `task_type`
parameter of the API. Newer model versions support [different embeddings
task
types](https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings#api_changes_to_models_released_on_or_after_august_2023).
**Description:** This PR fixes `HuggingFaceHubEmbeddings` by making the
API token optional (as in the client beneath). Most models don't require
one. I also updated the notebook for TEI (text-embeddings-inference)
accordingly as requested here #14288. In addition, I fixed a mistake in
the POST call parameters.
**Tag maintainers:** @baskaryan
