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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add information about Cohere Embed v3 #79

Merged
merged 1 commit into from
Dec 12, 2023
Merged

Add information about Cohere Embed v3 #79

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
Add information about Cohere Embed v3
  • Loading branch information
@bilgeyucel
bilgeyucel committed Dec 11, 2023
commit 1485b1102dd3906c4ce98bfed50be77fb3097c52
8 changes: 4 additions & 4 deletions integrations/cohere.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ You can use Cohere models in various ways:

#### Embedding Models

You can leverage `/embed` models from Cohere through two components: [CohereTextEmbedder](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/cohere/src/cohere_haystack/embedders/text_embedder.py) and [CohereDocumentEmbedder](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/cohere/src/cohere_haystack/embedders/document_embedder.py).
You can leverage `/embed` models from Cohere through two components: [CohereTextEmbedder](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/cohere/src/cohere_haystack/embedders/text_embedder.py) and [CohereDocumentEmbedder](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/cohere/src/cohere_haystack/embedders/document_embedder.py). These components support both Embed v2 and Embed v3 models.

To create semantic embeddings for documents, use `CohereDocumentEmbedder` in your indexing pipeline. For generating embeddings for queries, use `CohereTextEmbedder`. Once you've selected the suitable component for your specific use case, initialize the component with the model name and Cohere API key.

Expand All @@ -54,15 +54,15 @@ from haystack.document_stores import InMemoryDocumentStore
from haystack.components.writers import DocumentWriter
from cohere_haystack.embedders.document_embedder import CohereDocumentEmbedder

document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
document_store = InMemoryDocumentStore()

documents = [Document(content="My name is Wolfgang and I live in Berlin"),
Document(content="I saw a black horse running"),
Document(content="People speak French in France"),
Document(content="Germany has many big cities")]

indexing_pipeline = Pipeline()
indexing_pipeline.add_component("embedder", CohereDocumentEmbedder(api_key="COHERE_API_KEY", model_name="embed-multilingual-v2.0"))
indexing_pipeline.add_component("embedder", CohereDocumentEmbedder(api_key="COHERE_API_KEY", model_name="embed-multilingual-v3.0", input_type="search_document"))
indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
indexing_pipeline.connect("embedder", "writer")

Expand Down Expand Up @@ -184,4 +184,4 @@ document_retrieval_pipeline = Pipeline()
document_retrieval_pipeline.add_node(component=retriever, name="Retriever", inputs=["Query"])
document_retrieval_pipeline.add_node(component=ranker, name="Ranker", inputs=["Retriever"])
document_retrieval_pipeline.run("YOUR_QUERY")
```
```