[Docs]: Add Instructor embeddings and rate limit handler docs (#651)

docs/src/embeddings/default_embedding_functions.md

@@ -1,7 +1,9 @@
 There are various Embedding functions available out of the box with lancedb. We're working on supporting other popular embedding APIs.
 
 ## Text Embedding Functions
-Here are the text embedding functions registered by default
+Here are the text embedding functions registered by default.
+Embedding functions have inbuilt rate limit handler wrapper for source and query embedding function calls that retry with exponential standoff. 
+Each `EmbeddingFunction` implementation automatically takes `max_retries` as an argument which has the deafult value of 7.
 
 ### Sentence Transformers
 Here are the parameters that you can set when registering a `sentence-transformers` object, and their default values:
@@ -66,6 +68,56 @@ actual = table.search(query).limit(1).to_pydantic(Words)[0]
 print(actual.text)
 ```
 
+### Instructor Embeddings
+Instructor is an instruction-finetuned text embedding model that can generate text embeddings tailored to any task (e.g., classification, retrieval, clustering, text evaluation, etc.) and domains (e.g., science, finance, etc.) by simply providing the task instruction, without any finetuning
+
+If you want to calculate customized embeddings for specific sentences, you may follow the unified template to write instructions:
+
+                          Represent the `domain` `text_type` for `task_objective`:
+
+* `domain` is optional, and it specifies the domain of the text, e.g., science, finance, medicine, etc.
+* `text_type` is required, and it specifies the encoding unit, e.g., sentence, document, paragraph, etc.
+* `task_objective` is optional, and it specifies the objective of embedding, e.g., retrieve a document, classify the sentence, etc.
+
+More information about the model can be found here - https://github.com/xlang-ai/instructor-embedding
+
+| Argument | Type | Default | Description |
+|---|---|---|---|
+| `name` | `str` | "hkunlp/instructor-base" | The name of the model to use |
+| `batch_size` | `int` | `32` | The batch size to use when generating embeddings |
+| `device` | `str` | `"cpu"` | The device to use when generating embeddings |
+| `show_progress_bar` | `bool` | `True` | Whether to show a progress bar when generating embeddings |
+| `normalize_embeddings` | `bool` | `True` | Whether to normalize the embeddings |
+| `quantize` | `bool` | `False` | Whether to quantize the model |
+| `source_instruction` | `str` | `"represent the docuement for retreival"` | The instruction for the source column |
+| `query_instruction` | `str` | `"represent the document for retreiving the most similar documents"` | The instruction for the query |
+
+
+
+```python
+import lancedb
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.embeddings import get_registry, InstuctorEmbeddingFunction
+
+instructor = get_registry().get("instructor").create(
+                            source_instruction="represent the docuement for retreival",
+                            query_instruction="represent the document for retreiving the most similar documents"
+                            )
+
+class Schema(LanceModel):
+    vector: Vector(instructor.ndims()) = instructor.VectorField()
+    text: str = instructor.SourceField()
+
+db = lancedb.connect("~/.lancedb")
+tbl = db.create_table("test", schema=Schema, mode="overwrite")
+
+texts = [{"text": "Capitalism has been dominant in the Western world since the end of feudalism, but most feel[who?] that..."},
+        {"text": "The disparate impact theory is especially controversial under the Fair Housing Act because the Act..."},
+        {"text": "Disparate impact in United States labor law refers to practices in employment, housing, and other areas that.."}]
+
+tbl.add(texts)
+```
+
 ## Multi-modal embedding functions
 Multi-modal embedding functions allow you query your table using both images and text.
 

docs/src/embeddings/embedding_functions.md

@@ -57,6 +57,19 @@ query_image = Image.open(p)
 table.search(query_image)
 
 ```
+### Rate limit Handling
+`EmbeddingFunction` class wraps the calls for source and query embedding generation inside a rate limit handler that retries the requests with exponential backoff after successive failures. By default the maximum retires is set to 7. You can tune it by setting it to a different number or disable it by setting it to 0.
+Example
+----
+
+```python
+clip = registry.get("open-clip").create() # Defaults to 7 max retries
+clip = registry.get("open-clip").create(max_retries=10) # Increase max retries to 10
+clip = registry.get("open-clip").create(max_retries=0) # Retries disabled
+````
+
+NOTE:
+Embedding functions can also fail due to other errors that have nothing to do with rate limits. This is why the error is also logged.
 
 ### A little fun with PyDantic
 LanceDB is integrated with PyDantic. Infact we've used the integration in the above example to define the schema. It is also being used behing the scene by the embdding function API to ingest useful information as table metadata.