Open
Conversation
fm1320
force-pushed
the
add-superlinked-integration
branch
3 times, most recently
from
e0e7441 to
a0bb9fc
Compare
kacperlukawski
requested changes
Apr 15, 2026
| github: superlinked | ||
| linkedin: superlinked | ||
| pypi: https://pypi.org/project/sie-haystack/ | ||
| repo: https://github.com/superlinked/sie |
Member
There was a problem hiding this comment.
It is supposed to point to the integration package itself, not the main project.
| from haystack import Document, Pipeline | ||
| from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever | ||
| from haystack.document_stores.in_memory import InMemoryDocumentStore | ||
| from sie_haystack import SIEDocumentEmbedder, SIETextEmbedder |
Member
There was a problem hiding this comment.
It's a bit more related to the integration itself, but a common convention is to put all the embedding integrations under haystack_integrations.components.embedders.INTEGRATION_NAME. It might be easier to navigate for Haystack users, as they are used to that structure.
Comment on lines
+88
to
+109
| `sie-haystack` exposes Haystack-native components for every SIE capability: | ||
|
|
||
| **Dense embedding** | ||
| - `SIETextEmbedder` - embed a query string | ||
| - `SIEDocumentEmbedder` - embed a list of `Document`s (supports `meta_fields_to_embed`) | ||
|
|
||
| **Sparse embedding** (for hybrid search) | ||
| - `SIESparseTextEmbedder` | ||
| - `SIESparseDocumentEmbedder` | ||
|
|
||
| **Multivector / ColBERT** | ||
| - `SIEMultivectorTextEmbedder` | ||
| - `SIEMultivectorDocumentEmbedder` | ||
|
|
||
| **Multimodal** | ||
| - `SIEImageEmbedder` - CLIP, SigLIP, ColPali | ||
|
|
||
| **Reranking** | ||
| - `SIERanker` - reranking with cross-encoder models (e.g. `jinaai/jina-reranker-v2-base-multilingual`) or ColBERT / late-interaction models (e.g. `jinaai/jina-colbert-v2`) | ||
|
|
||
| **Extraction** | ||
| - `SIEExtractor` - zero-shot entity extraction (GLiNER), relation extraction (GLiREL), classification (GLiClass), and object detection (GroundingDINO, OWL-v2) |
Member
There was a problem hiding this comment.
I can't find the sources of the package, so I couldn't see how the other components would fit Haystack's pipelines/agents. It would be great to have a complete documentation using all the components provided.
Author
There was a problem hiding this comment.
as in you mean for these to lead to Superlinked's docs where the integrations are described?
fm1320
force-pushed
the
add-superlinked-integration
branch
2 times, most recently
from
c28ccc8 to
d25ce66
Compare
Adds an integration page for Superlinked (SIE), a self-hosted inference engine for embeddings, reranking, and extraction. The sie-haystack package provides Haystack 2.0 components for 85+ embedding models (dense, sparse, multivector/ColBERT, multimodal), cross-encoder and late-interaction reranking, and zero-shot entity/relation/classification extraction.
fm1320
force-pushed
the
add-superlinked-integration
branch
from
d25ce66 to
727cdde
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds an integration page for Superlinked (SIE), a self-hosted inference engine for embeddings, reranking, and extraction. The
sie-haystackpackage exposes Haystack 2.0 components for 85+ embedding models (dense, sparse, multivector/ColBERT, multimodal), cross-encoder reranking, and zero-shot entity/relation/classification extraction — all backed by a single SIE endpoint.Files added
integrations/superlinked.md— integration page with install, usage example, and component referencelogos/superlinked.png— logo assetType
Model Provider— matches the convention used by Cohere, Jina, Voyage, and Fastembed integrations, which similarly wrap an external embedding/reranking backend behind Haystack embedder and ranker components.Links
Opened as a draft for maintainer review of placement,
type:choice, and frontmatter. Happy to adjust.