Skip to content

Releases: deepset-ai/haystack

v1.12.0rc1

19 Dec 09:40
@ZanSara ZanSara
v1.12.0rc1
c62b5fb
Compare
Choose a tag to compare
v1.12.0rc1 Pre-release
Pre-release

⭐ Highlights

Large Language Models with PromptNode

Introducing PromptNode, a new feature that brings the power of large language models (LLMs) to various NLP tasks. PromptNode is an easy-to-use, customizable node you can run on its own or in a pipeline. We've designed the API to be user-friendly and suitable for everyday experimentation, but also fully compatible with production-grade Haystack deployments.

By setting a prompt template for a PromptNode you define what task you want it to do. This way, you can have multiple PromptNodes in your pipeline, each performing a different task. But that's not all. You can also inject the output of one PromptNode into the input of another one.

Out of the box, we support both Google T5 Flan and OpenAI GPT-3 models, and you can even mix and match these models in your pipelines.

from haystack.nodes.prompt import PromptNode

# Initialize the node:
prompt_node = PromptNode("google/flan-t5-base")  # try also 'text-davinci-003' if you have an OpenAI key

prompt_node("What is the capital of Germany?")

This node can do a lot more than simply querying LLMs: they can manage prompt templates, run batches, share models among instances, be chained together in pipelines, and more. Check its documentation for details!

Support for BM25Retriever in InMemoryDocumentStore

InMemoryDocumentStore has always been the go-to document store for small prototypes. The addition of BM25 support makes it officially one of the document stores to support all Retrievers available to Haystack, just like FAISS and Elasticsearch-like stores, but without the external dependencies. Don't use it in your million-documents-throughput deployments to production, though. It's not the fastest document store out there.

🏆 Honorable mention to @anakin87 for this outstanding contribution, among many many others! 🏆

Haystack is always open to external contributions, and every little bit is appreciated. Don't know where to start? Have a look at the Contributors Guidelines.

Extended support for Cohere and OpenAI embeddings

We enabled EmbeddingRetriever to use the latest Cohere multilingual embedding models and OpenAI embedding models.

Simply use the model's full name (along with your API key) in EmbeddingRetriever to get them:

# Cohere
retriever = EmbeddingRetriever(embedding_model="multilingual-22-12", batch_size=16, api_key=api_key)
# OpenAI
retriever = EmbeddingRetriever(embedding_model="text-embedding-ada-002", batch_size=32, api_key=api_key, max_seq_len=8191)

Speeding up dense searches in batch mode (Elasticsearch and OpenSearch)

Whenever you need to execute multiple dense searches at once, ElasticsearchDocumentStore and OpenSearchDocumentStore can now do it in parallel. This not only speeds up run_batch and eval_batch for dense pipelines when used with those document stores but also significantly speeds up multi-embedding retrieval pipelines like, for example, MostSimilarDocumentsPipeline.

For this, we measured a speed up of up to 49% on a realistic dataset.

Under the hood, our newly introduced query_by_embedding_batch document store function uses msearch to unchain the full power of your Elasticsearch/OpenSearch cluster.

⚠️ Deprecated Docker images discontinued

1.12 is the last release we're shipping with the old Docker images deepset/haystack-cpu, deepset/haystack-gpu, and their relative tags. We'll remove the corresponding, deprecated Docker files /Dockerfile, /Dockerfile-GPU, and /Dockerfile-GPU-minimal from the codebase after the release.

What's Changed

Pipeline

  • fix: ParsrConverter fails on pages without text by @anakin87 in #3605
  • fix: Convert eval metrics to python float by @tstadel in #3612
  • feat: add support for BM25Retriever in InMemoryDocumentStore by @anakin87 in #3561
  • chore: fix return type of aggregate_labels by @tstadel in #3617
  • refactor: change MultiModal retriever to be of type DenseRetriever by @mayankjobanputra in #3598
  • fix: Move entire forward pass of TableQA within torch.no_grad() by @sjrl in #3636
  • feat: add offsets_in_context to evaluation result by @julian-risch in #3640
  • bug: Use tqdm auto instead of plain tqdm by @vblagoje in #3672
  • fix: monkey patch for SklearnQueryClassifier by @anakin87 in #3678
  • feat: Update table reader tests to check the answer scores by @sjrl in #3641
  • feat: Adds all_terms_must_match parameter to BM25Retriever at runtime by @ugm2 in #3627
  • fix: fix PreProcessor split_by schema by @ZanSara in #3680
  • refactor: Generate JSON schema when missing by @masci in #3533
  • refactor: replace torch.no_grad with torch.inference_mode (where possible) by @anakin87 in #3601
  • Adjust get_type() method for pipelines by @vblagoje in #3657
  • refactor: improve Multilabel design by @anakin87 in #3658
  • feat: Update cohere embedding models #3704 by @vblagoje #3704
  • feat: Enable text-embedding-ada-002 for EmbeddingRetriever #3721 by @vblagoje #3721

DocumentStores

Documentation

Contributors to Tutorials

Other Changes

New Contributors

Full Changelog: v1.11.1...v1.12.0rc1

Contributors

masci, vblagoje, and 12 other contributors
Assets 2
Loading

v1.11.1

06 Dec 18:11
@bogdankostic bogdankostic
v1.11.1
05ea711
Compare
Choose a tag to compare
v1.11.1

What's Changed

  • fix: Pin faiss-cpu as 1.7.3 seems to have problems by @masci in #3603

Full Changelog: v1.11.0...v1.11.1

Contributors

masci
Assets 2
Loading

v1.11.1rc1

06 Dec 16:15
@bogdankostic bogdankostic
v1.11.1rc1
bf27a0c
Compare
Choose a tag to compare
v1.11.1rc1 Pre-release
Pre-release

What's Changed

  • fix: Pin faiss-cpu as 1.7.3 seems to have problems by @masci in #3603

Full Changelog: v1.11.0...v1.11.1rc1

Contributors

masci
Assets 2
Loading

v1.11.0

21 Nov 11:22
@masci masci
v1.11.0
0b106f6
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.11.0

⭐ Highlights

Expanding Haystack’s LLM support further with the new CohereEmbeddingEncoder (#3356)

Now you can easily create document and query embeddings using Cohere’s large language models: if you have a Cohere account, all you have to do is set the name of one of the supported models (small, medium, or large) and add your API key to the EmbeddingRetriever component in your pipelines (see docs).

Extracting headlines from Markdown and PDF files (#3445 #3488)

Using the MarkdownConverter or the ParsrConverter you can set the parameter extract_headlines to True to extract the headlines out of your files together with their start start position in the file and their level. Headlines are stored as a list of dictionaries in the Document's meta field "headlines" and are structured as followed:

{
    "headline": <THE HEADLINE STRING>,
    "start_idx": <IDX OF HEADLINE START IN document.content >,
    "level": <LEVEL OF THE HEADLINE>
}

Introducing the proposals design process (#3333)

We've introduced the proposal design process for substantial changes. A proposal is a single Markdown file that explains why a change is needed and how it would be implemented. You can find a detailed explanation of the process and a proposal template in the proposals directory.

⚠️ Breaking change: removing Milvus1DocumentStore

From this version onwards, Haystack no longer supports version 1 of Milvus. We still support Milvus version 2. We removed Milvus1DocumentStore and renamed Milvus2DocumentStore to MilvusDocumentStore.

What's Changed

Breaking Changes

  • bug: removed duplicated meta "name" field addition to content before embedding in update_embeddings workflow by @mayankjobanputra in #3368
  • BREAKING CHANGE: remove Milvus1DocumentStore along with support for Milvus < 2.x by @masci in #3552

Pipeline

  • fix: Fix the error of wrong page numbers when documents contain empty pages. by @brunnurs in #3330
  • bug: change type of split_by to Literal including None by @julian-risch in #3389
  • Fix: update pyworld pin by @anakin87 in #3435
  • feat: send event if number of queries exceeds threshold by @vblagoje in #3419
  • Feat: allow decreasing size of datasets loaded from BEIR by @ugm2 in #3392
  • feat: add __cointains__ to Span by @ZanSara in #3446
  • Bug: Fix prompt length computation by @Timoeller in #3448
  • Add indexing pipeline type by @vblagoje in #3461
  • fix: warning if doc store similarity function is incompatible with Sentence Transformers model by @anakin87 in #3455
  • feat: Add CohereEmbeddingEncoder to EmbeddingRetriever by @vblagoje in #3453
  • feat: Extraction of headlines in markdown files by @bogdankostic in #3445
  • bug: replace decorator with counter attribute for pipeline event by @julian-risch in #3462
  • feat: add document_store to all BaseRetriever.retrieve() and BaseRetriever.retrieve_batch() implementations by @ZanSara in #3379
  • refactor: TableReader by @sjrl in #3456
  • fix: do not reference package directory in PDFToTextOCRConverter.convert() by @ZanSara in #3478
  • feat: Create the TextIndexingPipeline by @brandenchan in #3473
  • refactor: remove YAML save/load methods for subclasses of BaseStandardPipeline by @ZanSara in #3443
  • fix: strip whitespaces safely from FARMReader's answers by @ZanSara in #3526

DocumentStores

  • Document Store test refactoring by @masci in #3449
  • fix: support long texts for labels in ElasticsearchDocumentStore by @anakin87 in #3346
  • feat: add SQLDocumentStore tests by @masci in #3517
  • refactor: Refactor Weaviate tests by @masci in #3541
  • refactor: Pinecone tests by @masci in #3555
  • fix: write metadata to SQL Document Store when duplicate_documents!="overwrite" by @anakin87 in #3548
  • fix: Elasticsearch / OpenSearch brownfield function does not incorporate meta by @tstadel in #3572
  • fix: discard metadata fields if not set in Weaviate by @masci in #3578

UI / Demo

Documentation

Other Changes

New Contributors

Full Changelog: v1.10.0...v1.11.0rc1

Contributors

masci, vblagoje, and 12 other contributors
Assets 2
Loading

v1.11.0rc1

18 Nov 07:38
@bogdankostic bogdankostic
v1.11.0rc1
893d2d4
Compare
Choose a tag to compare
v1.11.0rc1 Pre-release
Pre-release

⭐ Highlights

Expanding Haystack’s LLM support further with the new CohereEmbeddingEncoder (#3356)

Now you can easily create document and query embeddings using Cohere’s large language models: if you have a Cohere account, all you have to do is set the name of one of the supported models (small, medium, or large) and add your API key to the EmbeddingRetriever component in your pipelines (see docs).

Extracting headlines from Markdown and PDF files (#3445 #3488)

Using the MarkdownConverter or the ParsrConverter you can set the parameter extract_headlines to True to extract the headlines out of your files together with their start start position in the file and their level. Headlines are stored as a list of dictionaries in the Document's meta field "headlines" and are structured as followed:

{
    "headline": <THE HEADLINE STRING>,
    "start_idx": <IDX OF HEADLINE START IN document.content >,
    "level": <LEVEL OF THE HEADLINE>
}

Introducing the proposals design process (#3333)

We've introduced the proposal design process for substantial changes. A proposal is a single Markdown file that explains why a change is needed and how it would be implemented. You can find a detailed explanation of the process and a proposal template in the proposals directory.

⚠️ Breaking change: removing Milvus1DocumentStore

From this version onwards, Haystack no longer supports version 1 of Milvus. We still support Milvus version 2. We removed Milvus1DocumentStore and renamed Milvus2DocumentStore to MilvusDocumentStore.

What's Changed

Breaking Changes

  • bug: removed duplicated meta "name" field addition to content before embedding in update_embeddings workflow by @mayankjobanputra in #3368
  • BREAKING CHANGE: remove Milvus1DocumentStore along with support for Milvus < 2.x by @masci in #3552

Pipeline

  • fix: Fix the error of wrong page numbers when documents contain empty pages. by @brunnurs in #3330
  • bug: change type of split_by to Literal including None by @julian-risch in #3389
  • Fix: update pyworld pin by @anakin87 in #3435
  • feat: send event if number of queries exceeds threshold by @vblagoje in #3419
  • Feat: allow decreasing size of datasets loaded from BEIR by @ugm2 in #3392
  • feat: add __cointains__ to Span by @ZanSara in #3446
  • Bug: Fix prompt length computation by @Timoeller in #3448
  • Add indexing pipeline type by @vblagoje in #3461
  • fix: warning if doc store similarity function is incompatible with Sentence Transformers model by @anakin87 in #3455
  • feat: Add CohereEmbeddingEncoder to EmbeddingRetriever by @vblagoje in #3453
  • feat: Extraction of headlines in markdown files by @bogdankostic in #3445
  • bug: replace decorator with counter attribute for pipeline event by @julian-risch in #3462
  • feat: add document_store to all BaseRetriever.retrieve() and BaseRetriever.retrieve_batch() implementations by @ZanSara in #3379
  • refactor: TableReader by @sjrl in #3456
  • fix: do not reference package directory in PDFToTextOCRConverter.convert() by @ZanSara in #3478
  • feat: Create the TextIndexingPipeline by @brandenchan in #3473
  • refactor: remove YAML save/load methods for subclasses of BaseStandardPipeline by @ZanSara in #3443
  • fix: strip whitespaces safely from FARMReader's answers by @ZanSara in #3526

DocumentStores

  • Document Store test refactoring by @masci in #3449
  • fix: support long texts for labels in ElasticsearchDocumentStore by @anakin87 in #3346
  • feat: add SQLDocumentStore tests by @masci in #3517
  • refactor: Refactor Weaviate tests by @masci in #3541
  • refactor: Pinecone tests by @masci in #3555
  • fix: write metadata to SQL Document Store when duplicate_documents!="overwrite" by @anakin87 in #3548
  • fix: Elasticsearch / OpenSearch brownfield function does not incorporate meta by @tstadel in #3572
  • fix: discard metadata fields if not set in Weaviate by @masci in #3578

UI / Demo

Documentation

Other Changes

New Contributors

Full Changelog: v1.10.0...v1.11.0rc1

Contributors

masci, vblagoje, and 12 other contributors
Assets 2
Loading

v1.10.0

25 Oct 13:47
@masci masci
v1.10.0
3a2714e
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.10.0

⭐ Highlights

Expanding Haystack's LLM support with the new OpenAIEmbeddingEncoder (#3356)

Now you can easily create document and query embeddings using large language models: if you have an OpenAI account, all you have to do is set the name of one of the supported models (ada, babbage, davinci or curie) and add your API key to the EmbeddingRetriever component in your pipelines (see docs).

Multimodal retrieval is here! (#2891)

Multimodality with Haystack just made a big leap forward with the addition of MultiModalRetriever: a Retriever that can handle different modalities for query and documents independently. Take it for a spin and experiment with new Document formats, like images. You can now use the same Retriever for text-to-image, text-to-table, and text-to-text retrieval but also image similarity, table similarity, and more! Feed your favorite multimodal model to MultiModalRetriever and see it in action.

retriever = MultiModalRetriever(
    document_store=InMemoryDocumentStore(embedding_dim=512),
    query_embedding_model = "sentence-transformers/clip-ViT-B-32",
    query_type="text",
    document_embedding_models = {"image": "sentence-transformers/clip-ViT-B-32"}
)

Multi-platform Docker images

Starting with 1.10, we're making the deepset/haystack images available for linux/amd64 and linux/arm64.

⚠️ Breaking change in embed_queries method (#3252)

We've changed the text argument in the embed_queries method for DensePassageRetriever and EmbeddingRetriever to queries.

What's Changed

Breaking Changes

Pipeline

  • fix: ONNX FARMReader model conversion is broken by @vblagoje in #3211
  • bug: JoinDocuments nodes produce incorrect results if preceded by another JoinDocuments node by @JeffRisberg in #3170
  • fix: eval() with add_isolated_node_eval=True breaks if no node supports it by @tstadel in #3347
  • feat: extract label aggregation by @tstadel in #3363
  • feat: Add OpenAIEmbeddingEncoder to EmbeddingRetriever by @vblagoje in #3356
  • fix: stable YAML schema generation by @ZanSara in #3388
  • fix: Update how schema is ordered by @sjrl in #3399
  • feat: MultiModalRetriever by @ZanSara in #2891

DocumentStores

  • feat: FAISS in OpenSearch: Support HNSW for cosine by @tstadel in #3217
  • feat: add support for Elasticsearch 7.16.2 by @masci in #3318
  • refactor: remove dead code from FAISSDocumentStore by @anakin87 in #3372
  • fix: allow same vector_id in different indexes for SQL-based Document stores by @anakin87 in #3383

UI / Demo

  • fix: demo won't start through Docker compose on Apple M1 by @masci in #3337

Documentation

Other Changes

  • refactor: make TransformersDocumentClassifier output consistent between different types of classification by @anakin87 in #3224
  • Classify pipeline's type based on its components by @vblagoje in #3132
  • docs: sync Haystack API with Readme by @brandenchan in #3223
  • fix: MostSimilarDocumentsPipeline doesn't have pipeline property by @vblagoje in #3265
  • bug: make ElasticSearchDocumentStore use batch_size in get_documents_by_id by @anakin87 in #3166
  • refactor: better tests for TransformersDocumentClassifier by @anakin87 in #3270
  • fix: AttributeError in TranslationWrapperPipeline by @nickchomey in #3290
  • refactor: remove Inferencer multiprocessing by @vblagoje in #3283
  • fix: opensearch script score with filters by @tstadel in #3321
  • feat: Adding filters param to MostSimilarDocumentsPipeline run and run_batch by @JacdDev in #3301
  • feat: add multi-platform Docker images by @masci in #3354
  • fix: Added checks for DataParallel and WrappedDataParallel by @sjrl in #3366
  • fix: QuestionGenerator generates wrong document questions for non-default num_queries_per_doc parameter by @vblagoje in #3381
  • bug: Adds better way of checking query in BaseRetriever and Pipeline.run() by @ugm2 in #3304
  • feat: Updated EntityExtractor to handle long texts and added better postprocessing by @sjrl in #3154
  • docs: Add comment about the generation of no-answer samples in FARMReader training by @brandenchan in #3404
  • feat: Speed up integration tests (nodes) by @sjrl in #3408
  • fix: Fix the error of wrong page numbers when documents contain empty pages. by @brunnurs in #3330
  • bug: change type of split_by to Literal including None by @julian-risch in #3389
  • feat: Add exponential backoff decorator; apply it to OpenAI requests by @vblagoje in #3398

New Contributors

Full Changelog: v1.9.1...v1.10.0rc1

Contributors

masci, tanertopal, and 13 other contributors
Assets 2
Loading

v1.10.0rc1

20 Oct 15:37
@masci masci
v1.10.0rc1
0405d70
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.10.0rc1 Pre-release
Pre-release

⭐ Highlights

Expanding Haystack's LLM support with the new OpenAIEmbeddingEncoder (#3356)

Now you can easily create document and query embeddings using large language models: if you have an OpenAI account, all you have to do is set the name of one of the supported models (ada, babbage, davinci or curie) and add your API key to the EmbeddedRetriver component in your pipelines.

Multimodal retrieval is here! (#2891)

Multimodality with Haystack just made a big leap forward with the addition of MultiModalRetriever: a Retriever that can handle different modalities for query and documents independently. Take it for a spin and experiment with new Document formats, like images. You can now use the same Retriever for text-to-image, text-to-table, and text-to-text retrieval but also image similarity, table similarity, and more! Feed your favorite multimodal model to MultiModalRetriever and see it in action.

retriever = MultiModalRetriever(
    document_store=InMemoryDocumentStore(embedding_dim=512),
    query_embedding_model = "sentence-transformers/clip-ViT-B-32",
    query_type="text",
    document_embedding_models = {"image": "sentence-transformers/clip-ViT-B-32"}
)

Multi-platform Docker images

Starting with 1.10, we're making the deepset/haystack images available for linux/amd64 and linux/arm64.

⚠️ Breaking change in embed_queries method (#3252)

We've changed the text argument in the embed_queries method for DensePassageRetriever and EmbeddingRetriever to queries.

What's Changed

Breaking Changes

Pipeline

  • fix: ONNX FARMReader model conversion is broken by @vblagoje in #3211
  • bug: JoinDocuments nodes produce incorrect results if preceded by another JoinDocuments node by @JeffRisberg in #3170
  • fix: eval() with add_isolated_node_eval=True breaks if no node supports it by @tstadel in #3347
  • feat: extract label aggregation by @tstadel in #3363
  • feat: Add OpenAIEmbeddingEncoder to EmbeddingRetriever by @vblagoje in #3356
  • fix: stable YAML schema generation by @ZanSara in #3388
  • fix: Update how schema is ordered by @sjrl in #3399
  • feat: MultiModalRetriever by @ZanSara in #2891

DocumentStores

  • feat: FAISS in OpenSearch: Support HNSW for cosine by @tstadel in #3217
  • feat: add support for Elasticsearch 7.16.2 by @masci in #3318
  • refactor: remove dead code from FAISSDocumentStore by @anakin87 in #3372
  • fix: allow same vector_id in different indexes for SQL-based Document stores by @anakin87 in #3383

UI / Demo

  • fix: demo won't start through Docker compose on Apple M1 by @masci in #3337

Documentation

Other Changes

  • refactor: make TransformersDocumentClassifier output consistent between different types of classification by @anakin87 in #3224
  • Classify pipeline's type based on its components by @vblagoje in #3132
  • docs: sync Haystack API with Readme by @brandenchan in #3223
  • fix: MostSimilarDocumentsPipeline doesn't have pipeline property by @vblagoje in #3265
  • bug: make ElasticSearchDocumentStore use batch_size in get_documents_by_id by @anakin87 in #3166
  • refactor: better tests for TransformersDocumentClassifier by @anakin87 in #3270
  • fix: AttributeError in TranslationWrapperPipeline by @nickchomey in #3290
  • refactor: remove Inferencer multiprocessing by @vblagoje in #3283
  • fix: opensearch script score with filters by @tstadel in #3321
  • feat: Adding filters param to MostSimilarDocumentsPipeline run and run_batch by @JacdDev in #3301
  • feat: add multi-platform Docker images by @masci in #3354
  • fix: Added checks for DataParallel and WrappedDataParallel by @sjrl in #3366
  • fix: QuestionGenerator generates wrong document questions for non-default num_queries_per_doc parameter by @vblagoje in #3381
  • bug: Adds better way of checking query in BaseRetriever and Pipeline.run() by @ugm2 in #3304
  • feat: Updated EntityExtractor to handle long texts and added better postprocessing by @sjrl in #3154
  • docs: Add comment about the generation of no-answer samples in FARMReader training by @brandenchan in #3404
  • feat: Speed up integration tests (nodes) by @sjrl in #3408
  • fix: Fix the error of wrong page numbers when documents contain empty pages. by @brunnurs in #3330
  • bug: change type of split_by to Literal including None by @julian-risch in #3389
  • feat: Add exponential backoff decorator; apply it to OpenAI requests by @vblagoje in #3398

New Contributors

Full Changelog: v1.9.1...v1.10.0rc1

Contributors

masci, tanertopal, and 13 other contributors
Assets 2
Loading

v1.9.1

10 Oct 13:16
@masci masci
v1.9.1
c1e8d14
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.1

What's Changed

  • fix: Allow less restrictive values for parameters in Pipeline configurations by @bogdankostic in #3345

Full Changelog: v1.9.0...v1.9.1rc1

Contributors

bogdankostic
Assets 2
Loading

v1.9.1rc1

10 Oct 12:37
@masci masci
v1.9.1rc1
256321d
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.1rc1 Pre-release
Pre-release

What's Changed

  • fix: Allow less restrictive values for parameters in Pipeline configurations by @bogdankostic in #3345

Full Changelog: v1.9.0...v1.9.1rc1

Contributors

bogdankostic
Assets 2
Loading

v1.9.0

21 Sep 11:23
@masci masci
v1.9.0
ce36be8
This commit was signed with the committer’s verified signature.
masci Massimiliano Pippi
GPG key ID: C69551A629D71A65
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.9.0

⭐ Highlights

Haystack 1.9 comes with nice performance improvements and two important pieces of news about its ecosystem. Let's see it in more detail!

Logging speed set to ludicrous (#3212)

This feature alone makes Haystack 1.9 worth testing out, just sayin'... We switched from f-strings to the string formatting operator when composing a log message, observing an astonishing speed of up to 120% in some pipelines.

Tutorials moved out! (#3244)

They grow up so fast! Tutorials now have their own git repository, CI, and release cycle, making it easier than ever to contribute ideas, fixes, and bug reports. Have a look at the tutorials repo, Star it, and open an issue if you have an idea for a new tutorial!

Docker pull deepset/haystack (#3162)

A new Docker image is ready to be pulled shipping Haystack 1.9, providing different flavors and versions that you can specify with the proper Docker tag - have a look at the README.
On this occasion, we also revamped the build process so that it's now using bake, while the older images are deprecated (see below).

⚠️ Deprecation notice

With the release of the new Docker image deepset/haystack, the following images are now deprecated and won't be updated any more starting with Haystack 1.10:

New Documentation Site and Haystack Website Revamp:

The Haystack website is going through a make-over to become a developer portal that surrounds Haystack and NLP topics beyond pure documentation. With that, we've published our new documentation site. From now on, content surrounding pure developer documentation will live under Haystack Documentation, while the Haystack website becomes a place for the community with tutorials, learning material and soon, a place where the community can share their own content too.

What's Changed

Pipeline

  • feat: standardize devices parameter and device initialization by @vblagoje in #3062
  • fix: Reduce GPU to CPU copies at inference by @sjrl in #3127
  • test: lower low boundary for accuracy in test_calculate_context_similarity_on_non_matching_contexts by @ZanSara in #3199
  • bug: fix pdftotext installation verification by @banjocustard in #3233
  • chore: remove f-strings from logs for performance reasons by @ZanSara in #3212
  • bug: reactivate benchmarks with quick fixes by @tholor in #2766

Models

  • fix: Replace multiprocessing tokenization with batched fast tokenization by @vblagoje in #3089

DocumentStores

  • bug: OpensearchDocumentStore.custom_mapping should accept JSON strings at validation by @ZanSara in #3065
  • feat: Add warnings to PineconeDocumentStore about indexing metadata if filters return no documents by @Namoush in #3086
  • bug: validate custom_mapping as an object by @ZanSara in #3189

Tutorials

  • docs: Fix the word length splitting; should be set to 100 not 1,000 by @stevenhaley in #3133
  • chore: remove tutorials from the repo by @masci in #3244

Other Changes

  • chore: Upgrade and pin transformers to 4.21.2 by @vblagoje in #3098
  • bug: adapt UI random question for streamlit 1.12 and pin to streamlit>=1.9.0 by @anakin87 in #3121
  • build: pin pydantic to 1.9.2 by @masci in #3126
  • fix: document FARMReader.train() evaluation report log level by @brandenchan in #3129
  • feat: add a security policy for Haystack by @masci in #3130
  • refactor: update dependencies and remove pins by @danielbichuetti in #3147
  • refactor: update package strategy in rest_api by @masci in #3148
  • fix: give default index for torch.device('cuda') in initialize_device_settings by @sjrl in #3161
  • fix: add type hints to all component init constructor parameters by @vblagoje in #3152
  • fix: Add 15 min timeout for downloading cached HF models by @vblagoje in #3179
  • fix: replace torch.device("cuda") with torch.device("cuda:0") in devices initialization by @vblagoje in #3184
  • feat: add health check endpoint to rest api by @danielbichuetti in #3168
  • refactor: improve support for dataclasses by @danielbichuetti in #3142
  • feat: Updates docs and types for language param in PreProcessor by @sjrl in #3186
  • feat: Add option to use MultipleNegativesRankingLoss for EmbeddingRetriever training with sentence-transformers by @bglearning in #3164
  • refactoring: reimplement Docker strategy by @masci in #3162
  • refactor: remove pre haystack-1.0 import paths support by @ZanSara in #3204
  • feat: exponential backoff with exp decreasing batch size for opensearch and elasticsearch client by @ArzelaAscoIi in #3194
  • feat: add public layout-base extraction support on PDFToTextConverter by @danielbichuetti in #3137
  • bug: fix embedding_dim mismatch in DocumentStore by @kalki7 in #3183
  • fix: update rest_api Docker Compose yamls for recent refactoring of rest_api by @nickchomey in #3197
  • chore: fix Windows CI by @masci in #3222
  • fix: type of temperature param and adjust defaults for OpenAIAnswerGenerator by @tholor in #3073
  • fix: handle Documents containing dataframes in Multilabel constructor by @masci in #3237
  • fix: make pydoc-markdown hook correctly resolve paths relative to repo root by @masci in #3238
  • fix: proper retrieval of answers for batch eval by @vblagoje in #3245
  • chore: updating colab links in older docs versions by @TuanaCelik in #3250
  • docs: establish API docs sync between v1.9.x and Readme by @brandenchan in #3266

New Contributors

Full Changelog: v1.8.0...v1.9.0

Contributors

masci, vblagoje, and 14 other contributors
Assets 2
Loading