Skip to content

fix: replace legacy TransformersSimilarityRanker with SentenceTransformersSimilarityRanker #446

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

Open
vominh1919 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: replace legacy TransformersSimilarityRanker with SentenceTransformersSimilarityRanker #446

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
6 changes: 3 additions & 3 deletions tutorials/33_Hybrid_Retrieval.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -233,7 +233,7 @@
"source": [
"### 2) Rank the Results\n",
"\n",
"Use the [TransformersSimilarityRanker](https://docs.haystack.deepset.ai/docs/transformerssimilarityranker) that scores the relevancy of all retrieved documents for the given search query by using a cross encoder model. In this example, you will use [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) model to rank the retrieved documents but you can replace this model with other cross-encoder models on Hugging Face."
"Use the [SentenceTransformersSimilarityRanker](https://docs.haystack.deepset.ai/docs/sentencetransformerssimilarityranker) that scores the relevancy of all retrieved documents for the given search query by using a cross encoder model. In this example, you will use [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) model to rank the retrieved documents but you can replace this model with other cross-encoder models on Hugging Face."
]
},
{
Expand All @@ -244,9 +244,9 @@
},
"outputs": [],
"source": [
"from haystack.components.rankers import TransformersSimilarityRanker\n",
"from haystack.components.rankers import SentenceTransformersSimilarityRanker\n",
"\n",
"ranker = TransformersSimilarityRanker(model=\"BAAI/bge-reranker-base\")"
"ranker = SentenceTransformersSimilarityRanker(model=\"BAAI/bge-reranker-base\")"
]
},
{
Expand Down
10 changes: 5 additions & 5 deletions tutorials/44_Creating_Custom_SuperComponents.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,7 +245,7 @@
"from haystack import Document, Pipeline, super_component\n",
"from haystack.components.joiners import DocumentJoiner\n",
"from haystack.components.embedders import SentenceTransformersTextEmbedder\n",
"from haystack.components.rankers import TransformersSimilarityRanker\n",
"from haystack.components.rankers import SentenceTransformersSimilarityRanker\n",
"from haystack.components.retrievers import InMemoryBM25Retriever, InMemoryEmbeddingRetriever\n",
"from haystack.document_stores.in_memory import InMemoryDocumentStore\n",
"\n",
Expand All @@ -265,7 +265,7 @@
" bm25_retriever = InMemoryBM25Retriever(document_store)\n",
" text_embedder = SentenceTransformersTextEmbedder(embedder_model)\n",
" document_joiner = DocumentJoiner()\n",
" ranker = TransformersSimilarityRanker(ranker_model)\n",
" ranker = SentenceTransformersSimilarityRanker(ranker_model)\n",
"\n",
" # Create the pipeline\n",
" self.pipeline = Pipeline()\n",
Expand Down Expand Up @@ -513,7 +513,7 @@
"\n",
"The main differences between the two retrievers are:\n",
"\n",
"1. **Added Ranker Component**: The second version includes a `TransformersSimilarityRanker` that re-ranks the documents based on their semantic similarity to the query.\n",
"1. **Added Ranker Component**: The second version includes a `SentenceTransformersSimilarityRanker` that re-ranks the documents based on their semantic similarity to the query.\n",
"2. **Updated Input Mapping**: We added `\"text_embedder.text\"`, `\"bm25_retriever.query\"` and `\"ranker.query\"` to the input mapping to ensure the input query is sent to all three components while simplifying the `retriever.run` method.\n",
"\n",
"The ranker can significantly improve the quality of the results by re-ranking the documents based on their semantic similarity to the query, even if they were not ranked highly by the initial retrievers."
Expand Down Expand Up @@ -629,7 +629,7 @@
"from haystack.components.joiners import DocumentJoiner\n",
"from haystack.components.embedders import SentenceTransformersTextEmbedder\n",
"from haystack.components.retrievers import InMemoryBM25Retriever, InMemoryEmbeddingRetriever\n",
"from haystack.components.rankers import TransformersSimilarityRanker\n",
"from haystack.components.rankers import SentenceTransformersSimilarityRanker\n",
"from haystack.document_stores.in_memory import InMemoryDocumentStore\n",
"\n",
"\n",
Expand All @@ -646,7 +646,7 @@
" bm25_retriever = InMemoryBM25Retriever(document_store)\n",
" text_embedder = SentenceTransformersTextEmbedder(embedder_model)\n",
" document_joiner = DocumentJoiner()\n",
" ranker = TransformersSimilarityRanker(ranker_model)\n",
" ranker = SentenceTransformersSimilarityRanker(ranker_model)\n",
"\n",
" # Create the pipeline\n",
" self.pipeline = Pipeline()\n",
Expand Down
2 changes: 1 addition & 1 deletion tutorials/guide_evaluation.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,7 +110,7 @@
"### Methods to Improve Generation:\n",
"\n",
"- **Ranking**: Incorporate a ranking mechanism into your retrieved documents before providing the context to your prompt\n",
" - **Order by similarity**: Reorder your retrieved documents by similarity using cross-encoder models from Hugging Face with [TransformersSimilarityRanker](https://docs.haystack.deepset.ai/docs/transformerssimilarityranker), Rerank models from Cohere with [CohereRanker](https://docs.haystack.deepset.ai/docs/cohereranker), or Rerankers from Jina with [JinaRanker](https://docs.haystack.deepset.ai/docs/jinaranker)\n",
" - **Order by similarity**: Reorder your retrieved documents by similarity using cross-encoder models from Hugging Face with [SentenceTransformersSimilarityRanker](https://docs.haystack.deepset.ai/docs/sentencetransformerssimilarityranker), Rerank models from Cohere with [CohereRanker](https://docs.haystack.deepset.ai/docs/cohereranker), or Rerankers from Jina with [JinaRanker](https://docs.haystack.deepset.ai/docs/jinaranker)\n",
" - **Increase diversity by ranking**: Maximize the overall diversity among your context using sentence-transformers models with [SentenceTransformersDiversityRanker](https://docs.haystack.deepset.ai/docs/sentencetransformersdiversityranker) to help increase the semantic answer similarity (SAS) in LFQA applications.\n",
" - **Address the \"Lost in the Middle\" problem by reordering**: Position the most relevant documents at the beginning and end of the context using [LostInTheMiddleRanker](https://docs.haystack.deepset.ai/docs/lostinthemiddleranker) to increase faithfulness.\n",
"- **Different Generators**: Try different large language models and benchmark the results. The full list of model providers is in [Generators](https://docs.haystack.deepset.ai/docs/generators).\n",
Expand Down
Loading