Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-04 06:00:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updated LocalAIEmbeddings docstring to better explain why openai (#10946)

Browse Source 
Fixes my misgivings in
https://github.com/langchain-ai/langchain/issues/10912
This commit is contained in:
James Braza 2023-09-28 19:56:42 -07:00 committed by GitHub
parent 2c114fcb5e
commit b11f21c25f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
libs/langchain/langchain/embeddings/localai.py
View File

@ -120,16 +120,19 @@ async def async_embed_with_retry(embeddings: LocalAIEmbeddings, **kwargs: Any) -
class LocalAIEmbeddings(BaseModel, Embeddings): class LocalAIEmbeddings(BaseModel, Embeddings):
"""LocalAI embedding models. """LocalAI embedding models.
To use, you should have the ``openai`` python package installed, and the Since LocalAI and OpenAI have 1:1 compatibility between APIs, this class
environment variable ``OPENAI_API_KEY`` set to a random string. You need to uses the ``openai`` Python package's ``openai.Embedding`` as its client.
specify ``OPENAI_API_BASE`` to point to your LocalAI service endpoint. Thus, you should have the ``openai`` python package installed, and defeat
the environment variable ``OPENAI_API_KEY`` by setting to a random string.
You also need to specify ``OPENAI_API_BASE`` to point to your LocalAI
service endpoint.
Example: Example:
.. code-block:: python .. code-block:: python
from langchain.embeddings import LocalAIEmbeddings from langchain.embeddings import LocalAIEmbeddings
openai = LocalAIEmbeddings( openai = LocalAIEmbeddings(
openai_api_key="random-key", openai_api_key="random-string",
openai_api_base="http://localhost:8080" openai_api_base="http://localhost:8080"
) )