1077 Commits

Author SHA1 Message Date
Tanay Soni
912e98cd40
Fix id for documents returned by the TfidfRetriever (#232) 2020-07-15 14:55:07 +02:00
Tanay Soni
4e10a1520d
Remove mutation of documents in write_documents() (#231) 2020-07-15 13:10:52 +02:00
Tanay Soni
e1d64c2c68
Fix print_answers to not delete keys from passed results object (#230) 2020-07-15 12:49:14 +02:00
Malte Pietsch
99a6a34047
Upgrade to new FARM / Transformers / PyTorch versions (#212) 2020-07-14 18:53:15 +02:00
Malte Pietsch
17c1b84c21
Fix API links in readme 2020-07-14 17:42:06 +02:00
Anirban Saha
6b217732f5
Add basic support for Docx Files (#225) 2020-07-14 12:28:19 +02:00
Tanay Soni
b886e054a3
Move document_name attribute to meta (#217) 2020-07-14 09:53:31 +02:00
Tanay Soni
4c21556a79
Fix embedding method for Retriever (#220) 2020-07-13 12:38:01 +02:00
Malte Pietsch
5023fde2be Update issue templates 2020-07-13 10:45:58 +02:00
Malte Pietsch
d2b26a99ff
Add more tests (#213) 2020-07-10 10:54:56 +02:00
Malte Pietsch
549f3a1285
Harmonize meta data handling across doc stores (#214) 2020-07-09 15:25:48 +02:00
Guillim
c45d54959f
Fix Dockerfile to build successfully without models directory (#210) 2020-07-08 17:12:20 +02:00
antoniolanza1996
4b9954c4a6
Update docstring for embedding_field and embedding_dim (#208)
'embedding_field' and 'embedding_dim' are useful not only for EmbeddingRetriever but also for DensePassageRetriever. Hence, could be good if you generalise it as "dense retriever".
2020-07-08 13:36:49 +02:00
Malte Pietsch
bda333dca4 Update code snippet for readme 2020-07-08 11:43:43 +02:00
Guillim
9733e0bd1b
Fix naming of offset in answers of TransformersReader (for consistency with FARMReader) (#204) 2020-07-07 19:29:12 +02:00
Guillim
b4f4388e09
gitignore fix (#203) 2020-07-07 19:24:48 +02:00
Guillim
8a616dae75
Adjust Docker and REST API to allow TransformsReader Class (#180) 2020-07-07 16:25:36 +02:00
Malte Pietsch
fe33a481ad
Update tutorials (#200)
* fix link in readme. update installation in tutorials

* update haystack version to latest master

* add basic documentation for input to write_documents()

* add docstring for sqldocumentstore

* comment out docker in notebook
2020-07-07 14:59:01 +02:00
Tanay Soni
ff7e35581b
Add response time in logs (#201) 2020-07-07 12:28:41 +02:00
Tanay Soni
68d604d82b
Add response for successful file upload (#195) 2020-07-06 17:35:47 +02:00
Tanay Soni
0eb8a29da9
Adjust PDF conversion subprocess for Python v3.6 (#194) 2020-07-06 16:56:10 +02:00
Malte Pietsch
7ada5a91cd
Update README.rst 2020-07-03 16:08:26 +02:00
Malte Pietsch
c36f8c991e Update Tutorial 6 2020-07-03 16:06:46 +02:00
Malte Pietsch
8a9f97fad3
Tutorial for Dense Passage Retriever (#186) 2020-07-03 15:53:58 +02:00
Malte Pietsch
84a25c73b3
Update README.rst 2020-07-02 09:15:03 +02:00
Malte Pietsch
07ecfb60b9
Dense Passage Retriever (Inference) (#167) 2020-06-30 19:05:45 +02:00
Guillim
27b8c98227
Fix rest api in Docker image after refactoring (#178) 2020-06-26 17:52:46 +02:00
Guillim
b3858a07eb
Update tutorial link in readme from .py to .ipynb (#177)
for more consitency between all the link formats
2020-06-26 17:29:02 +02:00
Timo Moeller
c53aaddb78
Fix document id missing in farm inference output (#174) 2020-06-26 11:01:10 +02:00
Tanay Soni
44f89c94ab
Upgrade FARM version (#172) 2020-06-24 15:14:09 +02:00
Tanay Soni
587b2fe749
Add check if sequences empty when detecing header/footer (#165) 2020-06-24 15:05:52 +02:00
Tanay Soni
0e070d0d7c
Create file upload dir if not exists (#166) 2020-06-24 15:05:30 +02:00
Timo Moeller
5852cbd306
Adjust to farm handling of no answer (#170)
* Adjust to farm handling of no answer

* Add check for answer type returned from farm
2020-06-23 16:49:32 +02:00
Tanay Soni
ec433a5ed6
Move out REST API from PyPI package (#160) 2020-06-22 12:07:12 +02:00
Tanay Soni
03acb1ee32
Add ONNXRuntime support (#157) 2020-06-18 17:47:16 +02:00
Tanay Soni
54e85e586e
Fix for installing PyTorch on Windows OS (#159) 2020-06-18 17:43:38 +02:00
Tanay Soni
a349eef0db
Add API endpoint to upload files (#154) 2020-06-17 16:28:26 +02:00
Tanay Soni
8bcc4b26a1
Remove Literal type hint (#156) 2020-06-17 16:26:21 +02:00
Tanay Soni
af5fc79dce
Add EMBEDDING_MODEL_FORMAT in API config (#152) 2020-06-16 13:58:30 +02:00
Tanay Soni
42f56672b4
Remove PyMuPDF dependency (#148) 2020-06-12 11:53:18 +02:00
Tanay Soni
997aafcf62 Remove hard-coded question field for FAQs 2020-06-11 14:29:32 +02:00
Tanay Soni
4c2726f7ab
Make FAQ question field customizable (#146) 2020-06-11 12:36:19 +02:00
Jonas
f3492a3f12
Typo fixes (#145)
* Fix model spelling typo in readme

* fix wrong function name in error log message
2020-06-11 12:02:26 +02:00
Tanay Soni
08779007eb
Add mypy badge 2020-06-10 17:26:13 +02:00
Tanay Soni
98f1a3f9a7
Add type hints and mypy checks (#138) 2020-06-10 17:22:37 +02:00
Tanay Soni
180dc8cbd6
Start Elasticsearch with a Github Action (#142) 2020-06-09 12:46:15 +02:00
Tanay Soni
2e4d2e792b
Delete .travis.yml 2020-06-09 12:00:13 +02:00
Tanay Soni
160345f3d5 Update build workflow 2020-06-09 11:45:25 +02:00
Tanay Soni
c4592c1b9a
Create ci.yml 2020-06-09 11:36:27 +02:00
Arthur Barros
394ddab734
Add Elasticsearch PORT and SCHEME in API config (#134) 2020-06-09 09:56:56 +02:00