yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-07-24 17:30:38 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,855 Commits 73 Branches 245 Tags
Commit Graph

83 Commits

Author SHA1 Message Date
Michele Pangrazzi
c192488bf6
Named entity extractor private models (#8658) 
* add 'token' support to NamedEntityExtractor to enable using private models on HF backend

* fix existing error message format

* add release note

* add HF_API_TOKEN to e2e workflow

* add informative comment

* Updated to_dict / from_dict to handle 'token' correctly ; Added tests

* Fix lint

* Revert unwanted change
 2024-12-20 11:15:55 +01:00
David S. Batista
db89b9a2e5
fix: removing unused import (#8636) 2024-12-13 12:35:58 +01:00
David S. Batista
176db5dbf9
initial import (#8635) 2024-12-13 12:12:40 +01:00
David S. Batista
97126eb544
fix: changing default model to gpt-4o-mini on OpenAI API calls (#8360) 
* chaning default model to gpt-4o-mini

* adding release notes

* fixing some missed tests

* fixing some more missed tests

* fixing one last missed test

* fixing linting issues

* making pylint happy about an end2end test

* chaning if test to walruss operator

* fixing azure embedder from ada to text-embedding-ada-002
 2024-09-17 10:36:42 +02:00
David S. Batista
276ff3c104
test evaluation pipeline failing (#7823) 2024-06-07 11:26:18 +02:00
Silvano Cerza
26b263e349
Fix InMemoryDocumentStore not sharing some document stats with other instances (#7792) 2024-06-04 10:15:50 +02:00
Julian Risch
6723dc3801
check for RuntimeError instead of ComponentError in test (#7769) 2024-05-31 08:42:40 +02:00
Massimiliano Pippi
10c675d534
chore: add license header to all modules (#7675) 
* add license header to modules
* check license header at linting time
 2024-05-09 13:40:36 +00:00
Julian Risch
48c7c6ad26
test: Rename responses and use preds instead of ground truth answers in e2e eval test (#7640) 
* rename responses, use preds instead of ground truth answers

* fix typo in component name
 2024-05-03 12:48:42 +02:00
David S. Batista
8d04e530da
test: end2end evaluation tests (#7601) 
* initial import

* wip

* cleaning up tests

* fixing tests

* adding context relevance

* reverting some wrong changes to due PyCharm error in refactoring

* building eval pipeline only once

* handling mypy issues
 2024-04-26 14:07:05 +00:00
Silvano Cerza
d66b5358a1
Remove eval end to end tests (#7093) 2024-02-26 12:27:15 +01:00
Vladimir Blagojevic
d2497d54e8
Update to use the default Secret.from_env_var(OPENAI_API_KEY) approach (#6941) 2024-02-09 14:15:45 +01:00
Ashwin Mathur
393a7993c3
feat: Add Semantic Answer Similarity metric (#6877) 
* Add SAS metric

* Add release notes

* Round similarity scores for precision consistency

* Add tolerance to tests

* Update haystack/evaluation/eval.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>

* Add types for preprocess_text; Add additional types for f1 and em methods

---------

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
 2024-02-02 17:07:52 +01:00
Ashwin Mathur
7217f9d9f0
feat: Add F1 metric (#6822) 
* Add F1 metric

* Add release notes
 2024-01-26 11:04:43 +01:00
Ashwin Mathur
a238c6dd51
feat: Add Exact Match metric (#6696) 
* Add exact match metric

* Add release notes

* Cleanup comments in test_eval_exact_match.py

* Create separate preprocessing function; Add output_key parameter

* Update release note

---------

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
 2024-01-22 09:57:04 +01:00
Madeesh Kannan
6a1514550e
test: Update E2E tests to use Pipeline.dump/load (#6756) 2024-01-17 15:09:27 +01:00
Madeesh Kannan
7376838922
feat!: Framework-agnostic device management (#6748) 
* feat: Framework-agnostic device management

* Add release note

* Linting

* Fix test

* Add `first_device` property, expand release notes, validate `ComponentDevice` state
 2024-01-17 10:41:34 +01:00
Madeesh Kannan
d6cafeaff3
test: Rename RAG E2E test file (#6750) 
Prior to this change, this broke `pytest` workflows in VSCode due to identical test names in this file and the integration/unit test file.
 2024-01-16 13:40:22 +01:00
ZanSara
96c0b59aaa
feat!: Rename model_name_or_path to model in ExtractiveReader (#6736) 
* rename model parameter and internam model attribute in ExtractiveReader

* fix tests for ExtractiveReader

* fix e2e

* reno

* another fix

* review feedback

* Update releasenotes/notes/rename-model-param-reader-b8cbb0d638e3b8c2.yaml
 2024-01-15 14:48:33 +01:00
ZanSara
b236ea49e3
fix: hybrid pipeline e2e test (#6740) 
* fix hybrid pipeline e2e test

* warmup

* write to the right docstore
 2024-01-15 14:20:02 +01:00
ZanSara
288ed150c9
feat!: Rename model_name or model_name_or_path to model in all Embedder classes (#6733) 
* rename model parameter in the openai doc embedder

* fix tests for openai doc embedder

* rename model parameter in the openai text embedder

* fix tests for openai text embedder

* rename model parameter in the st doc embedder

* fix tests for st doc embedder

* rename model parameter in the st backend

* fix tests for st backend

* rename model parameter in the st text embedder

* fix tests for st text embedder

* fix docstring

* fix pipeline utils

* fix e2e

* reno

* fix the indexing pipeline _create_embedder function

* fix e2e eval rag pipeline

* pytest
 2024-01-12 15:30:17 +01:00
ZanSara
3156343dce
fix leftover model_name_or_path param (#6737) 2024-01-12 15:03:06 +01:00
Massimiliano Pippi
e1ec4e5e4d
refact!: Remove symbols under the haystack.document_stores namespace (#6714) 
* remove symbols under the haystack.document_stores namespace

* Update haystack/document_stores/types/protocol.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>

* fix

* same for retrievers

* leftovers

* more leftovers

* add relnote

* leftovers

* one more

* fix examples

---------

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
 2024-01-10 21:20:42 +01:00
Ashwin Mathur
374a937663
feat: Add calculate_metrics and MetricsResult (#6680) 
* Add calculate_metrics, MetricsResult, Exact Match

* Add additional tests for metric calculation

* Add release notes

* Add docstring for Exact Match metric

* Remove Exact Match Implementation

* Update release notes

* Remove unnecessary metrics implementation

* Simplify logic to run supported metrics

* Add some evaluation tests

* Fix linting

---------

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2024-01-10 10:26:44 +01:00
Madeesh Kannan
e6d6ce1c73
feat: Add NamedEntityExtractorcomponent (#6689) 
* feat: Add `NamedEntityExtractor`component

This component accepts a list of `Document`s which it annotates with named entities. The annotations are stored in the `meta` dictionary of each `Document` under a specific key.

The component currently support two backends for the annotation models: Hugging Face `transformers` and spaCy.

* Address comments

* Expand release note

* Add the `[torch]` extra package specifier to the lazy import

* Remove dead code

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2024-01-09 17:56:20 +01:00
Massimiliano Pippi
93b2aaee09
chore: move DocumentJoiner to new joiners package (#6692) 
* move DocumentJoiner to new joiners package

* relnote

* leftovers

* fix docstrings generation

* fix unrelated pydoc misconfiguration

* more unrelated work, yay!

* fix assertions
 2024-01-08 22:06:27 +01:00
Vladimir Blagojevic
506ab81d26
chore: Rename GPT generators, deprecate old names (#6626) 2023-12-22 19:37:29 +01:00
Julian Risch
d90f95be2e
test: Check only top answer in extractive QA e2e test (#6614) 2023-12-22 11:11:24 +01:00
Stefano Fiorucci
7cc6080dfa
chore: replace metadata w meta in tests/examples (#6612) 
* replace metadata w meta in tests/examples

* do not touch already broken e2e tests

* Revert "do not touch already broken e2e tests"

This reverts commit 1f911920d98954b57daacfe8d8ed02fd77d136db.
 2023-12-21 14:09:31 +01:00
Ashwin Mathur
46b395eec3
feat: Add Eval and EvaluationResult (#6505) 
* Add initial implementation for Eval and EvaluationResult

* Add release notes

* Update files with suggestions from review

* Remove serialization

* Add eval e2e tests

* Update eval e2e tests
 2023-12-18 11:29:09 +01:00
Silvano Cerza
18dbce25fc
refacotr: Refactor answer dataclasses (#6523) 
* Refactor answer dataclasses

* Add release notes

* Fix tests

* Fix end to end tests

* Enhance ExtractiveReader
 2023-12-11 18:50:49 +01:00
Silvano Cerza
e6637f5ec2 Fix all tests 2023-11-24 14:48:43 +01:00
Massimiliano Pippi
09e7831f60
clean up 1.x code 
---------

Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
 2023-11-24 11:47:47 +01:00
Silvano Cerza
fd16ec63cb
refactor: Add support for new filters declaration (#6397) 
* Rework filter logic for InMemoryDocumentStore to support new filters
declaration

* Fix legacy filters tests

* Simplify logic and handle dates comparison

* Rework MetadataRouter to support new filters

* Update docstrings

* Add release notes

* Fix linting

* Avoid duplicating filters specifications

* Handle corner case

* Simplify docstring

* Fix filters logic and tests

* Fix Document Store testing legacy filters tests
 2023-11-24 11:22:46 +01:00
Julian Risch
67780a62d5
test: Add end-to-end test for dense doc search 2.0 (#6102) 
* draft e2e test for dense doc search

* fix import path

* add DocumentJoiner

* update converter import; fix getting filled doc store

* add text embedder

* add sample txt and pdf for preview e2e tests

* run the query pipeline before serializing

* define samples path

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>
 2023-11-23 16:59:02 +01:00
Vladimir Blagojevic
cfff0d5212
Rename file_converters to converters (#6390) 2023-11-23 10:28:40 +01:00
Julian Risch
4ef2a680bb
feat: Add DocumentJoiner component 2.0 (#6105) 
* draft DocumentJoiner

* implement merge and rrf

* draft end-to-end test with DocumentJoiner in hybrid doc search pipeline

* adjust for variadics Canals PR #122

* fix text_embedder input

* adapt to the new Document class

* adapt to new doc id

* specify documents input as Variadic in run method

* compare doc ids instead of full docs

* rename text_file_converter input to sources

* update docstring

* Update haystack/preview/components/routers/document_joiner.py

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

* Apply suggestions from docstring review

Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>

* capitalize Documents and Retrievers in docstrings

* fix log message in test

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Agnieszka Marzec <97166305+agnieszka-m@users.noreply.github.com>
 2023-11-20 10:56:56 +01:00
ZanSara
dfc1d452bb
feat: upgrade canals to 0.10.1 (#6309) 
* upgrade canals

* reno

* trigger preview e2e

* bump canals

* fix decorator

* fix test

* test factory

* tests inmemory

* tests writer

* test audio

* tests builders

* tests caching

* tests embedders

* tests converters

* tests generators

* tests rankers

* tests retrievers

* fix pipeline and telemetry tests

* remove trigger
 2023-11-17 14:46:23 +01:00
Julian Risch
1c85e44156
test: Add langdetect installation to e2e tests (#6327) 
* Add langdetect installation to e2e tests

* compare doc content and id only
 2023-11-17 10:12:05 +01:00
Julian Risch
8b092a90c0
test: Add MetadataRouter to preprocessing pipeline in e2e test (#6321) 
* add MetadataRouter to preprocessing pipeline

* replace mimetype check with language check
 2023-11-16 11:22:37 +01:00
Vladimir Blagojevic
5497ca2a45
feat: Adapt GPTGenerator to use str input/output format in Haystack 2.x (#6214) 
* Adapt GPTGenerator to string input/output

* Finishing touches

* punctuation upd

* PR feedback

* Small naming fixes

* Update haystack/preview/components/generators/openai.py

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>

* Update class pydoc with a printed response

---------

Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
 2023-11-07 18:00:43 +01:00
Stefano Fiorucci
982ac3df01
fix: fix failing e2e test (after moving classifiers) (#6243) 
* mv classifiers

* release note

* fix e2e test
 2023-11-06 17:08:20 +01:00
Stefano Fiorucci
063d27c522
refactor!: rename TextDocumentSplitter to DocumentSplitter (#6223) 
* rename TextDocumentSplitter to DocumentSplitter

* reno

* fix init
 2023-11-03 11:33:20 +01:00
Julian Risch
29b1fefaa4
feat: Add DocumentLanguageClassifier 2.0 (#6037) 
* add DocumentLanguageClassifier and tests

* reno

* fix import, rename DocumentCleaner

* mark example usage as python code

* add assertions to e2e test

* use deserialized document_store

* Apply suggestions from code review

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>

* remove from/to_dict

* use renamed InMemoryDocumentStore

* adapt to Document refactoring

* improve docstring

* fix test for new Document

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Stefano Fiorucci <44616784+anakin87@users.noreply.github.com>
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
 2023-10-31 15:35:05 +01:00
Silvano Cerza
7287657f0e
refactor: Rename Document's text field to content (#6181) 
* Rework Document serialisation

Make Document backward compatible

Fix InMemoryDocumentStore filters

Fix InMemoryDocumentStore.bm25_retrieval

Add release notes

Fix pylint failures

Enhance Document kwargs handling and docstrings

Rename Document's text field to content

Fix e2e tests

Fix SimilarityRanker tests

Fix typo in release notes

Rename Document's metadata field to meta (#6183)

* fix bugs

* make linters happy

* fix

* more fix

* match regex

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2023-10-31 12:44:04 +01:00
Nripesh Niketan
708d33a657
feat: add apple silicon GPU acceleration (#6151) 
* feat: add apple silicon GPU acceleration

* add release notes

* small fix

* Update utils.py

* Update utils.py

* ci fix mps

* Revert "ci fix mps"

This reverts commit 783ae503940d9ff8270a970a321549fb9e69dce7.

* mps fix

* Update experiment_tracking.py

* try removing upper watermark limit

* disable mps CI

* Use xl runner

* initialise env

* small fix

* black linting

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2023-10-30 11:26:46 +01:00
Stefano Fiorucci
4e4af99a5e
refactor!: rename MemoryDocumentStore and related Retrievers (#6076) 
* rename doc store and retrievers

* release note

* fix patch
 2023-10-17 16:15:16 +02:00
ZanSara
71f2430fd1
test: enhance e2e tests to also draw and serialize/deserialize the test pipelines (#5910) 
* add draw and serialization/deserialization to e2e pipeline examples

* add comment about json serialization

* fix a small gptgenerator bug and move indexing in tests

* to json

* review feedback
 2023-10-09 13:54:17 +02:00
Stefano Fiorucci
c8398eeb6d
test: e2e test for Extractive QA Pipeline (#5879) 
* e2e test for e. qa pipeline
 2023-09-26 15:44:34 +02:00
Silvano Cerza
cf7f0ebc22
Add Pipelines async run (#5864) 
* Add Pipeline.arun()

* Sleeper node

* Fix async running

* Add e2e tests

To run a Pipeline that doesn't have any async node in async mode:

    pytest e2e/pipelines/test_standard_pipelines.py::test_query_and_indexing_pipeline

To run a Pipeline that has a single async node in concurrent mode:

    pytest e2e/pipelines/test_standard_pipelines.py::test_async_concurrent_complex_pipeline

To run a Pipeline that has a single async node in sequential mode:

    pytest e2e/pipelines/test_standard_pipelines.py::test_async_sequential_complex_pipeline

* Remove unused _adispatch_run method

* Make Pipeline.run work with async nodes

* Revert "Make Pipeline.run work with async nodes"

This reverts commit 22d7a94e4d41aca1b59dad18c0b366fbb6e8f431.

* Rename Pipeline.arun to Pipeline._arun

* Enhance docstring

* Add Sleeper docstring

* Add release notes

* ignore typing across the node

* make pylint happy

* skip pylint on needed unused import

* fix

* if a node has an arun method, use it

---------

Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
 2023-09-26 15:37:27 +02:00