This change speeds up OCR extraction by allowing bypassing OCR for texts that are irrelevant (not in table).
---------
Co-authored-by: Nguyen Trung Duc (john) <trungduc1992@gmail.com>
This change provides the base interface of an embedding, and wrap the Langchain's OpenAI embedding. Usage as follow:
```python
from kotaemon.embeddings import AzureOpenAIEmbeddings
model = AzureOpenAIEmbeddings(
model="text-embedding-ada-002",
deployment="embedding-deployment",
openai_api_base="https://test.openai.azure.com/",
openai_api_key="some-key",
)
output = model("Hello world")
```
