Make it possible to control the HuggingFaceEmbeddings and HuggingFaceInstructEmbeddings client model kwargs. Additionally, the cache folder was added for HuggingFaceInstructEmbedding as the client inherits from SentenceTransformer (client of HuggingFaceEmbeddings).
It can be useful, especially to control the client device, as it will be defaulted to GPU by sentence_transformers if there is any.
---------
Co-authored-by: Yoann Poupart <66315201+Xmaster6y@users.noreply.github.com>
Separated the deployment from model to support Azure OpenAI Embeddings
properly.
Also removed the deprecated document_model_name and query_model_name
attributes.
**Problem:**
OpenAI Embeddings has a few minor issues: method name and comment for
_completion_with_retry seems to be a copypasta error and a few comments
around usage of embedding_ctx_length seem to be incorrect.
**Solution:**
Clean up issues.
---------
Co-authored-by: Vijay Rajaram <vrajaram3@gatech.edu>
Added support for passing the openai_organization as an argument, as it
was only supported by the environment variable but openai_api_key was
supported by both environment variables and arguments.
`ChatOpenAI(temperature=0, model_name="gpt-4", openai_api_key="sk-****",
openai_organization="org-****")`
#991 has already implemented this convenient feature to prevent
exceeding max token limit in embedding model.
> By default, this function is deactivated so as not to change the
previous behavior. If you specify something like 8191 here, it will work
as desired.
According to the author, this is not set by default.
Until now, the default model in OpenAIEmbeddings's max token size is
8191 tokens, no other openai model has a larger token limit.
So I believe it will be better to set this as default value, other wise
users may encounter this error and hard to solve it.
Add support for defining the organization of OpenAI, similarly to what
is done in the reference code below:
```
import os
import openai
openai.organization = os.getenv("OPENAI_ORGANIZATION")
openai.api_key = os.getenv("OPENAI_API_KEY")
```
Add `n_batch` and `last_n_tokens_size` parameters to the LlamaCpp class.
These parameters (epecially `n_batch`) significantly effect performance.
There's also a `verbose` flag that prints system timings on the `Llama`
class but I wasn't sure where to add this as it conflicts with (should
be pulled from?) the LLM base class.
# What does this PR do?
This PR adds similar to `llms` a SageMaker-powered `embeddings` class.
This is helpful if you want to leverage Hugging Face models on SageMaker
for creating your indexes.
I added a example into the
[docs/modules/indexes/examples/embeddings.ipynb](https://github.com/hwchase17/langchain/compare/master...philschmid:add-sm-embeddings?expand=1#diff-e82629e2894974ec87856aedd769d4bdfe400314b03734f32bee5990bc7e8062)
document. The example currently includes some `_### TEMPORARY: Showing
how to deploy a SageMaker Endpoint from a Hugging Face model ###_ ` code
showing how you can deploy a sentence-transformers to SageMaker and then
run the methods of the embeddings class.
@hwchase17 please let me know if/when i should remove the `_###
TEMPORARY: Showing how to deploy a SageMaker Endpoint from a Hugging
Face model ###_` in the description i linked to a detail blog on how to
deploy a Sentence Transformers so i think we don't need to include those
steps here.
I also reused the `ContentHandlerBase` from
`langchain.llms.sagemaker_endpoint` and changed the output type to `any`
since it is depending on the implementation.
This PR fixes the types returned by Cohere embeddings. Currently, Cohere
client returns instances of `cohere.embeddings.Embeddings`. Since the
transport layer relies on JSON, some numbers might be represented as
ints, not floats, which happens quite often. While that doesn't seem to
be an issue, it breaks some pydantic models if they require strict
floats.
https://github.com/hwchase17/langchain/issues/1100
When faiss data and doc.index are created in past versions, error occurs
that say there was no attribute. So I put hasattr in the check as a
simple solution.
However, increasing the number of such checks is not good for
conservatism, so I think there is a better solution.
Also, the code for the batch process was left out, so I put it back in.
Currently, the 'truncate' parameter of the cohere API is not supported.
This means that by default, if trying to generate and embedding that is
too big, the call will just fail with an error (which is frustrating if
using this embedding source e.g. with GPT-Index, because it's hard to
handle it properly when generating a lot of embeddings).
With the parameter, one can decide to either truncate the START or END
of the text to fit the max token length and still generate an embedding
without throwing the error.
In this PR, I added this parameter to the class.
_Arguably, there should be a better way to handle this error, e.g. by
optionally calling a function or so that gets triggered when the token
limit is reached and can split the document or some such. Especially in
the use case with GPT-Index, its often hard to estimate the token counts
for each document and I'd rather sort out the troublemakers or simply
split them than interrupting the whole execution.
Thoughts?_
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Currently, the class parameter 'model_name' of the CohereEmbeddings
class is not supported, but 'model' is. The class documentation is
inconsistent with this, though, so I propose to either fix the
documentation (this PR right now) or fix the parameter.
It will create the following error:
```
ValidationError: 1 validation error for CohereEmbeddings
model_name
extra fields not permitted (type=value_error.extra)
```
`SentenceTransformer` returns a NumPy array, not a `List[List[float]]`
or `List[float]` as specified in the interface of `Embeddings`. That PR
makes it consistent with the interface.
Now that OpenAI has deprecated all embeddings models except
text-embedding-ada-002, we should stop specifying a legacy embedding
model in the example. This will also avoid confusion from people (like
me) trying to specify model="text-embedding-ada-002" and having that
erroneously expanded to text-search-text-embedding-ada-002-query-001
Running the Cohere embeddings example from the docs:
```python
from langchain.embeddings import CohereEmbeddings
embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)
text = "This is a test document."
query_result = embeddings.embed_query(text)
doc_result = embeddings.embed_documents([text])
```
I get the error:
```bash
CohereError(message=res['message'], http_status=response.status_code, headers=response.headers)
cohere.error.CohereError: embed is not an available endpoint on this model
```
This is because the `model` string is set to `medium` which is not
currently available.
From the Cohere docs:
> Currently available models are small and large (default)
Add support for calling HuggingFace embedding models
using the HuggingFaceHub Inference API. New class mirrors
the existing HuggingFaceHub LLM implementation. Currently
only supports 'sentence-transformers' models.
Closes#86
Addresses the issue in #76 by either using the relevant environment
variable if set or using a string passed in the constructor.
Prefers the constructor string over the environment variable, which
seemed like the natural choice to me.
Davis Chase
