Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Update cohere embedding models #3704

Merged
merged 1 commit into from
Dec 16, 2022
Merged

feat: Update cohere embedding models #3704

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion haystack/nodes/retriever/_embedding_encoder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -477,7 +477,14 @@ def __init__(self, retriever: "EmbeddingRetriever"):
self.api_key = retriever.api_key
self.batch_size = min(16, retriever.batch_size)
self.progress_bar = retriever.progress_bar
self.model: str = next((m for m in ["small", "medium", "large"] if m in retriever.embedding_model), "large")
self.model: str = next(
(
m
for m in ["small", "medium", "large", "multilingual-22-12", "finance-sentiment"]
if m in retriever.embedding_model
),
"multilingual-22-12",
)
self.tokenizer = AutoTokenizer.from_pretrained("gpt2")

def _ensure_text_limit(self, text: str) -> str:
Expand Down
2 changes: 1 addition & 1 deletion haystack/nodes/retriever/dense.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1819,7 +1819,7 @@ def _preprocess_documents(self, docs: List[Document]) -> List[Document]:
def _infer_model_format(model_name_or_path: str, use_auth_token: Optional[Union[str, bool]]) -> str:
if any(m in model_name_or_path for m in ["ada", "babbage", "davinci", "curie"]):
return "openai"
if model_name_or_path in ["small", "medium", "large"]:
if model_name_or_path in ["small", "medium", "large", "multilingual-22-12", "finance-sentiment"]:
return "cohere"
# Check if model name is a local directory with sentence transformers config file in it
if Path(model_name_or_path).exists():
Expand Down