v1.15.0-rc2

v1.15.0-rc2

v1.15.0-rc1

v1.15.0-rc1

v1.14.0

⭐ 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

• feat: add frontmatter to meta in MarkdownConverter by @TuanaCelik in #3953
• fix: removing code block in MarkdownConverter by @TuanaCelik in #3960
• feat: Add page range support to PDF converters. by @danielbichuetti in #3965
• fix: Update telemetry to not serialize Pipeline if disabled. by @sjrl in #4000
• feat: add Shaper by @ZanSara in #3880
• fix: Event sending for RayPipeline crashing Haystack by @zoltan-fedor in #3971
• fix: document retrieval metrics for non-document_id document_relevance_criteria by @tstadel in #3885
• fix: make the crawler more robust on Windows by @anakin87 in #4049
• fix: use correct count of outgoing edges in RayPipeline by @zoltan-fedor in #4066
• feat: Allow all training options for training a SentenceTransformers EmbeddingRetriever by @sjrl in #4026
• refactor: replace mutable default arguments by @julian-risch in #4070
• feat: Support multiple RayPipelines by @zoltan-fedor in #4078
• Remove double batching in retrieve_batch by @sjrl in #4014
• style: Update black by @silvanocerza in #4101
• fix: Fix TableTextRetriever for input consisting of tables only by @jackapbutler in #4048
• fix: Deduplicate same Documents in isolated evaluation of Reader by @bogdankostic in #4114
• Docs: Fix code block formatting by @agnieszka-m in #4162
• refactor: Remove the pin from the espnet module and fix the audio node tests. by @danielbichuetti in #4128
• fix: change tiktoken fallback mechanism to support Windows amd64 by @danielbichuetti in #4175
• feat: Add OpenAIError to retry mechanism by @sjrl in #4178

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
• feat: Implement run_batch for PromptNode by @sjrl in #4072

Other Changes

• fix: add option to not override results by Shaper #4231
• fix: Shaper store all outputs from function #4223
• fix: allowing file-upload api to write files to disk #4221
• fix: Fix bug in prompt template check of OpenAIAnswerGenerator #4220
• feat: add top_k to PromptNode #4159
• feat: Add JsonConverter node #4130
• feat: adding secure loading of models by default for haystack by @mayankjobanputra in #3901
• fix: add tiktoken fallback mechanism. by @danielbichuetti in #3929
• fix: change model in distillation test by @ZanSara in #3944
• feat: Expose output_variable in PromptNode result, adjust unit tests by @vblagoje in #3892
• fix: Fix type in FARMReader's save_to_remote by @bogdankostic in #3952
• refactor: Remove PromptNode hash and equality functions by @vblagoje in #3923
• ci: Remove mypy deps install step in python_cache action by @silvanocerza in #3956
• fix: overwrite params with environment variables even if there are no params in the pipeline definition; make mypy ignore REST API tests by @anakin87 in #3930
• Docs: Update ImageToText docstrings by @agnieszka-m in #3963
• Docs: Add TransformersImageToText API doc by @agnieszka-m in #3966
• ci: Add Docker images testing by @silvanocerza in #3943
• feat: Allow users to set a timeout for remote APIs by @danielbichuetti in #3949
• ci: Fix docker image testing on release by @silvanocerza in #3976
• Fix: Fix quotation marks by @agnieszka-m in #3973
• fix: PromptNode doesn't have run_batch support (yet) by @vblagoje in #3972
• chore: increased timeout for loading pipelines through API by @mayankjobanputra in #3977
• Missing import for TransformersImageToText by @ZanSara in #3984
• test: CI on py3.8 by @ZanSara in #3926
• Simplifies and fix docker images tests on release by @silvanocerza in #3982
• feat: Add use_prefiltering parameter to DeepsetCloudDocumentStore by @bogdankostic in #3969
• ci: Delete Docker images after testing to prevent workflow failure by @silvanocerza in #4004
• fix: Add a verbose option to PromptNode to let users understand the prompts being used #2 by @zoltan-fedor in #3898
• fix: prevent posthog from sending errors to stderr by @julian-risch in #4008
• fix: extend schema for prompt node results by @tstadel in #3891
• proposal: TableCell by @sjrl in #3875
• refactor: In PromptNode reuse tokenizer instead of loading new one for stop words by @sjrl in #4016
• ci: Automate release on PyPi by @silvanocerza in https://github.co...

v1.14.0rc2

What's Changed

• fix: add option to not override results by Shaper #4231
• fix: Shaper store all outputs from function #4223
• fix: allowing file-upload api to write files to disk #4221
• fix: Fix bug in prompt template check of OpenAIAnswerGenerator #4220
• feat: add top_k to PromptNode #4159
• feat: Add JsonConverter node #4130

v1.14.0rc1

⭐ 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

• feat: add frontmatter to meta in MarkdownConverter by @TuanaCelik in #3953
• fix: removing code block in MarkdownConverter by @TuanaCelik in #3960
• feat: Add page range support to PDF converters. by @danielbichuetti in #3965
• fix: Update telemetry to not serialize Pipeline if disabled. by @sjrl in #4000
• feat: add Shaper by @ZanSara in #3880
• fix: Event sending for RayPipeline crashing Haystack by @zoltan-fedor in #3971
• fix: document retrieval metrics for non-document_id document_relevance_criteria by @tstadel in #3885
• fix: make the crawler more robust on Windows by @anakin87 in #4049
• fix: use correct count of outgoing edges in RayPipeline by @zoltan-fedor in #4066
• feat: Allow all training options for training a SentenceTransformers EmbeddingRetriever by @sjrl in #4026
• refactor: replace mutable default arguments by @julian-risch in #4070
• feat: Support multiple RayPipelines by @zoltan-fedor in #4078
• Remove double batching in retrieve_batch by @sjrl in #4014
• style: Update black by @silvanocerza in #4101
• fix: Fix TableTextRetriever for input consisting of tables only by @jackapbutler in #4048
• fix: Deduplicate same Documents in isolated evaluation of Reader by @bogdankostic in #4114
• Docs: Fix code block formatting by @agnieszka-m in #4162
• refactor: Remove the pin from the espnet module and fix the audio node tests. by @danielbichuetti in #4128
• fix: change tiktoken fallback mechanism to support Windows amd64 by @danielbichuetti in #4175
• feat: Add OpenAIError to retry mechanism by @sjrl in #4178

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

• feat: adding secure loading of models by default for haystack by @mayankjobanputra in #3901
• fix: add tiktoken fallback mechanism. by @danielbichuetti in #3929
• fix: change model in distillation test by @ZanSara in #3944
• feat: Expose output_variable in PromptNode result, adjust unit tests by @vblagoje in #3892
• fix: Fix type in FARMReader's save_to_remote by @bogdankostic in #3952
• refactor: Remove PromptNode hash and equality functions by @vblagoje in #3923
• ci: Remove mypy deps install step in python_cache action by @silvanocerza in #3956
• fix: overwrite params with environment variables even if there are no params in the pipeline definition; make mypy ignore REST API tests by @anakin87 in #3930
• Docs: Update ImageToText docstrings by @agnieszka-m in #3963
• Docs: Add TransformersImageToText API doc by @agnieszka-m in #3966
• ci: Add Docker images testing by @silvanocerza in #3943
• feat: Allow users to set a timeout for remote APIs by @danielbichuetti in #3949
• ci: Fix docker image testing on release by @silvanocerza in #3976
• Fix: Fix quotation marks by @agnieszka-m in #3973
• fix: PromptNode doesn't have run_batch support (yet) by @vblagoje in #3972
• chore: increased timeout for loading pipelines through API by @mayankjobanputra in #3977
• Missing import for TransformersImageToText by @ZanSara in #3984
• test: CI on py3.8 by @ZanSara in #3926
• Simplifies and fix docker images tests on release by @silvanocerza in #3982
• feat: Add use_prefiltering parameter to DeepsetCloudDocumentStore by @bogdankostic in #3969
• ci: Delete Docker images after testing to prevent workflow failure by @silvanocerza in #4004
• fix: Add a verbose option to PromptNode to let users understand the prompts being used #2 by @zoltan-fedor in #3898
• fix: prevent posthog from sending errors to stderr by @julian-risch in #4008
• fix: extend schema for prompt node results by @tstadel in #3891
• proposal: TableCell by @sjrl in #3875
• refactor: In PromptNode reuse tokenizer instead of loading new one for stop words by @sjrl in #4016
• ci: Automate release on PyPi by @silvanocerza in #4015
• ci: Fix PyPi release workflow by @silvanocerza in #4029
• ci: Bump act10ns/slack from v1 to v2 by @silvanocerza in #4031
• ci: latest version of pylint is failing, ignore new errors by @masci in https://github.com/deep...

v1.13.2

What's Changed

Pipelines

• fix: fix torchaudio version by @mayankjobanputra in #4102
• feat: Add use_prefiltering parameter to DeepsetCloudDocumentStore by @bogdankostic in #3969

Documentation

• Add shaper api by @agnieszka-m in #4082
• Update imgtotext api by @agnieszka-m in #4074

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

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

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

• fix: adjust max token size for openai ADA-v2 embeddings by @LeoGitGuy in #3793
• feat: make new sklearn models default in QueryClassifier by @julian-risch in #3777

DocumentStores

• Fixing broken BM25 support with Weaviate - fixes #3720 by @zoltan-fedor in #3723
• feat: make score_script first class citizen via knn_engine param by @tstadel in #3284
• bug: skip validating empty embeddings by @julian-risch in #3774
• fix: Despite return_embedding=False SearchEngineDocumentStore.query retrieves embedding_field by @tstadel in #3662
• fix: upgrade launch_es() to the version used in CI by @ZanSara in #3858
• Adding condition to pinecone object. by @AI-Ahmed in #3768
• fix: Allowing InMemStore and FAISSDocStore for indexing using single worker by @mayankjobanputra in #3868
• fix: authenticate with aws4auth if set in OpenSearchDocumentStore by @FabianHertwig in #3741
• Fixing the query_batch method of the deepsetcloud document store - … by @zoltan-fedor in #3724
• feat: add HA support for Weaviate by @zoltan-fedor in #3764

UI / Demo

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

...

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

v1.12.2rc1

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