Skip to content

Releases: deepset-ai/haystack

v1.14.0rc1

20 Feb 19:02
@vblagoje vblagoje
v1.14.0rc1
a5ef5b4
Compare
Choose a tag to compare
v1.14.0rc1 Pre-release
Pre-release

⭐ Highlights

PromptNode enhancements

PromptNode just rolled out prompt logging (pipeline debug), run_batch, and model_kwargs support. More updates to PromptNode and PromptTemplates coming soon!

Shaper

We're introducing the Shaper, PromptNode's helper. Shaper unlocks the full potential of PromptNode and ensures its seamless integration with Haystack. But Shaper's scope and functionality are not limited to PromptNode; you can also use it independently, opening up a whole new world of possibilities.

IVF and Product Quantization support for OpenSearchDocumentStore

We've added support for IVF and IVF with Product Quantization to OpenSearchDocumentStore. You can train the IVF index by calling train_index method (same as in FAISSDocumentStore) or by setting ivf_train_size when initializing OpenSearchDocumentStore and take your search to the next level.

What's Changed

Breaking Changes

  • refactor: Updated rest_api schema for tables to be consistent with Document.to_dict by @sjrl in #3872
  • feat: Support multiple document_ids in Answer object (for generative QA) by @tstadel in #4062
  • feat: Update OpenAIAnswerGenerator defaults and with learnings from PromptNode by @sjrl in #4038
  • build: cache nltk models into the docker image by @mayankjobanputra in #4118
  • feat: Add IVF and Product Quantization support for OpenSearchDocumentStore by @bogdankostic in #3850

Pipeline

DocumentStores

  • refactor: use weaviate client to build BM25 query by @hsm207 in #3939
  • fix: fixed InMemoryDocumentStore.get_embedding_count to return correct number by @sjrl in #3980
  • fix: Add inner query for mysql compatibility by @julian-risch in #4068
  • feat: add support for custom headers by @hsm207 in #4040
  • feat: Add BM25 support for tables in InMemoryDocumentStore by @bogdankostic in #4090
  • refactor: InMemoryDocumentStore - manage documents without embedding & fix mypy errors by @anakin87 in #4113
  • refactor: complete the document stores test refactoring by @masci in #4125
  • feat: include testing facilities into haystack package by @masci in #4182

Documentation

  • Align with the docs install guide + correct lg by @agnieszka-m in #3950
  • docs: Update Crawler docstring for correct usage in Google colab by @silvanocerza in #3979
  • Docs: Update docstrings by @agnieszka-m in #4119
  • docs: Update Annotation Tool README.md by @bogdankostic in #4123
  • feat: Add model_kwargs option to PromptNode by @sjrl in #4151
  • fix: Remove logging statement of setting ID manually in Document by @bogdankostic in #4129
  • chore: Fixing PromptNode .prompt() docstring to include the PromptTemplate object as an option by @TuanaCelik in #4135
  • chore: de-couple the telemetry events for each tutorial from the dataset on AWS that is used by @TuanaCelik in #4155
  • Prompt node/run batch by @sjrl in #4072

Other Changes

Read more

Contributors

masci, vblagoje, and 16 other contributors
Assets 2
Loading

v1.13.2

09 Feb 19:06
@ZanSara ZanSara
v1.13.2
d69e409
Compare
Choose a tag to compare
v1.13.2

What's Changed

Pipelines

Documentation

Full Changelog: v1.13.1...v1.13.2

Contributors

mayankjobanputra, bogdankostic, and agnieszka-m
Assets 2
Loading

v1.13.1

02 Feb 20:03
@ZanSara ZanSara
v1.13.1
5578a0c
Compare
Choose a tag to compare
v1.13.1

What's Changed

  • fix: document retrieval metrics for non-document_id document_relevance_criteria (#3885)
  • Update pyproject.toml (#4035)
  • feat: add Shaper (#3880)
  • fix: extend schema for prompt node results (#3891)
  • fix: removing code block in MarkdownConverter (#3960)
  • feat: add frontmatter to meta in MarkdownConverter (#3953)

Full Changelog: v1.13.0...v1.13.1

Assets 2
Loading

v1.13.0

27 Jan 13:43
@ZanSara ZanSara
v1.13.0
cae33b1
Compare
Choose a tag to compare
v1.13.0

⭐ Highlights

Stop words for PromptNode

Implements stop words on the level of the PromptNode (for all models). Users can specify ‘stop_words’ as PromptNode list parameter, and thus stop LLM text generation once any of the stop words is encountered. Stop words will not be included in the response.

A dedicated Github repository for Haystack demo(s)

The source code for Haystack' Explore the World demo has been moved to a dedicated repository: https://github.com/deepset-ai/haystack-demos. Use this repository to check out the code, run it locally, fork, customize, and contribute!

New nodes: ImageToText and CsvTextConverter

This release sees two new nodes, both contributed by community members!

The first one is ImageToText (courtesy of our well-known @anakin87): an image captioning node that can generate description of image files and create Haystack documents from them.

The second one is CsvTextConverter, from @Benvii: a small utility node that can load a CSV of FAQ question-answer pairs and correctly send them to your DocumentStore, making it super handy for FAQ matching pipelines.

Check out the docs to know more about them and try them out!

Faster tokenization for GPT models with tiktoken

Haystack now supports faster tokenization with OpenAI's tiktoken library, which can dramatically improve tokenization speed for GPT models. For unsupported architectures (Py < 3.8, arm64 and MacOS) fallbacks are in place and regular HuggingFace tokenizers are used. Thanks to @danielbichuetti for yet another amazing contribution!

What's Changed

Breaking Changes

  • Migrating to use native Pytorch AMP by @sjrl in #2827
  • bug: consistent batch_size parameter names in distillation by @julian-risch in #3811
  • refactor: Move invocation_context from meta to own pipeline variable by @vblagoje in #3888

Pipeline

  • feat: Update cohere embedding models by @vblagoje in #3704
  • feat: add index parameter to TfidfRetriever by @anakin87 in #3666
  • feat: Use torch.inference_mode() for TableQA by @sjrl in #3731
  • feat: Enable text-embedding-ada-002 for EmbeddingRetriever by @vblagoje in #3721
  • refactor: improve monkey patch for SklearnQueryClassifier by @anakin87 in #3732
  • refactor: remove unused code in TfidfRetriever by @anakin87 in #3733
  • refactor: Remove duplicate code in TableReader by @sjrl in #3708
  • fix: Make InferenceProcessor thread safe by @bogdankostic in #3709
  • chore: adding template for prompt node by @TuanaCelik in #3738
  • fix: Fixed local reader model loading by @mayankjobanputra in #3663
  • fix: Fix predict_batch in TransformersReader for single nested Document list by @bogdankostic in #3748
  • feat: change PipelineConfigError to DocumentStoreError with more details by @julian-risch in #3783
  • bug: skip empty documents in reader by @julian-risch in #3773
  • fix: linefeeds in custom_query by @tstadel in #3813
  • fix: Convert table cells to strings for compatibility with TableReader by @sjrl in #3762
  • fix: Ensure eval mode for TableReader model for predictions by @sjrl in #3743
  • fix: gracefully handle FileExistsError during Preprocessor resource download by @wochinge in #3816
  • fix: make the crawler runnable and testable on Windows by @anakin87 in #3830
  • fix: ignore non-serializable params when hashing pipeline objects by @masci in #3842
  • feat: preprocessor raises warning when doc length exceeds threshold by @ZanSara in #3837
  • fix: remove string validation in YAML by @ZanSara in #3854
  • feat: Use truncate option for Cohere.embed by @sjrl in #3865
  • feat: ImageToText (caption generator) by @anakin87 in #3859
  • fix: Remove double super class init from ParsrConverter init by @silvanocerza in #3896
  • feat: store id_hash_keys in Document objects to make documents clonable by @ZanSara in #3697
  • feat: adding the ability to use Ray Serve async functionality by @zoltan-fedor in #3769
  • feat: support cl100k_base tokenization and increase performance for GPT2 by @danielbichuetti in #3897
  • fix: Fix number of concurrent requests in RequestLimiter by @bogdankostic in #3705
  • feat: Run commands inside docker container as a non root user by @vblagoje in #3702
  • fix: Removed overlooked torch scatter references by @sjrl in #3719
  • build: upgrade torch and let transformers pick the version by @julian-risch in #3727
  • feat: Expand LLM support with PromptModel, PromptNode, and PromptTemplate by @vblagoje in #3667
  • refactor: remove deprecated parameters from Summarizer by @anakin87 in #3740
  • refactor: Using with open() to read files by @sjrl in #3787
  • feat: Bump python to 3.10 for gpu docker image, use nvidia/cuda by @vblagoje in #3701
  • fix: pin protobuf version by @masci in #3789
  • fix(docker): Use IMAGE_NAME in api image by @FabianHertwig in #3786
  • bug: Fix launch_milvus() by cd'ing to milvus_dir by @t0r0id in #3795
  • refactor: Change PromptNode registered templates from per class to per instance by @vblagoje in #3810
  • bug: The PromptNode handles all parameters as lists without checking if they are in fact lists by @zoltan-fedor in #3820
  • feat: update the docker image for haystack-api service by @bilgeyucel in #3835
  • refactor: Simplify PromptTemplate substitution in PromptNode by @vblagoje in #3876
  • feat: PromptNode - implement stop words by @vblagoje in #3884
  • feat: Add retry with exponential back-off to PromptNode's OpenAI models by @vblagoje in #3886
  • chore: Add timeouts to external requests calls by @silvanocerza in #3895
  • feat: Add CsvTextConverter by @Benvii in #3587
  • refactor: Improve stop_words handling, add unit test cases by @vblagoje in #3918
  • refactor: Updated rest_api schema for tables to be consistent with Document.to_dict #3872

Models

DocumentStores

UI / Demo

  • refactor: remove haystack demo along with deprecated Dockerfiles by @masci in #3829

...

Read more

Contributors

masci, askainet, and 20 other contributors
Assets 2
Loading

v1.12.2

22 Dec 13:15
@bogdankostic bogdankostic
v1.12.2
ef1fa09
Compare
Choose a tag to compare
v1.12.2

What's Changed

  • Fixing the query_batch method of the deepsetcloud document store by @zoltan-fedor in #3724
  • build: upgrade torch and let transformers pick the version by @julian-risch in #3727
  • fix: Removed overlooked torch scatter references by @sjrl in #3719

Full Changelog: v1.12.1...v1.12.2

Contributors

zoltan-fedor, julian-risch, and sjrl
Assets 2
Loading

v1.12.2rc1

22 Dec 11:24
@bogdankostic bogdankostic
v1.12.2rc1
7dbb7e4
Compare
Choose a tag to compare
v1.12.2rc1 Pre-release
Pre-release

What's Changed

  • Fixing the query_batch method of the deepsetcloud document store by @zoltan-fedor in #3724
  • build: upgrade torch and let transformers pick the version by @julian-risch in #3727
  • fix: Removed overlooked torch scatter references by @sjrl in #3719

Full Changelog: v1.12.1...v1.12.2rc1

Contributors

zoltan-fedor, julian-risch, and sjrl
Assets 2
Loading

v1.12.1

21 Dec 20:12
@bogdankostic bogdankostic
v1.12.1
cde10a7
Compare
Choose a tag to compare
v1.12.1

⭐ 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
  • feat: Expand LLM support with PromptModel, PromptNode, and PromptTemplate by @vblagoje in #3667

DocumentStores

Documentation

Contributors to Tutorials

Other Changes

New Contributors

Full Changelog: v1.11.1...v1.12.1

Contributors

masci, vblagoje, and 12 other contributors
Assets 2
Loading

v1.12.0

21 Dec 16:51
@bogdankostic bogdankostic
v1.12.0
71de1ca
Compare
Choose a tag to compare
v1.12.0 
v1.12.0
Assets 2
Loading

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