yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-09-26 08:33:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add create_index and similarity metric to api config (#493)

Browse Source 
* make creation of label index optional

* add params for rest api

* reset tutorial flag
This commit is contained in:
Malte Pietsch 2020-10-15 18:41:36 +02:00 committed by GitHub
parent ceb5c87da0
commit bdbd1b323b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 7 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
rest_api/config.py
View File

@ -25,6 +25,8 @@ SEARCH_FIELD_NAME = os.getenv("SEARCH_FIELD_NAME", "text")
FAQ_QUESTION_FIELD_NAME = os.getenv("FAQ_QUESTION_FIELD_NAME", "question")
EMBEDDING_FIELD_NAME = os.getenv("EMBEDDING_FIELD_NAME", None)
EMBEDDING_DIM = os.getenv("EMBEDDING_DIM", None)
VECTOR_SIMILARITY_METRIC = os.getenv("VECTOR_SIMILARITY_METRIC", "dot_product")
CREATE_INDEX = os.getenv("CREATE_INDEX", "True").lower() == "true"
# Reader
READER_MODEL_PATH = os.getenv("READER_MODEL_PATH", "deepset/roberta-base-squad2")

6
rest_api/controller/search.py
View File

@ -14,7 +14,9 @@ from rest_api.config import DB_HOST, DB_PORT, DB_USER, DB_PW, DB_INDEX, ES_CONN_
EMBEDDING_DIM, EMBEDDING_FIELD_NAME, EXCLUDE_META_DATA_FIELDS, RETRIEVER_TYPE, EMBEDDING_MODEL_PATH, USE_GPU, READER_MODEL_PATH, \
BATCHSIZE, CONTEXT_WINDOW_SIZE, TOP_K_PER_CANDIDATE, NO_ANS_BOOST, MAX_PROCESSES, MAX_SEQ_LEN, DOC_STRIDE, \
DEFAULT_TOP_K_READER, DEFAULT_TOP_K_RETRIEVER, CONCURRENT_REQUEST_PER_WORKER, FAQ_QUESTION_FIELD_NAME, \
EMBEDDING_MODEL_FORMAT, READER_TYPE, READER_TOKENIZER, GPU_NUMBER, NAME_FIELD_NAME
EMBEDDING_MODEL_FORMAT, READER_TYPE, READER_TOKENIZER, GPU_NUMBER, NAME_FIELD_NAME, VECTOR_SIMILARITY_METRIC, \
CREATE_INDEX
from rest_api.controller.utils import RequestLimiter
from haystack.document_store.elasticsearch import ElasticsearchDocumentStore
from haystack.reader.farm import FARMReader
@ -43,6 +45,8 @@ document_store = ElasticsearchDocumentStore(
embedding_field=EMBEDDING_FIELD_NAME,
excluded_meta_data=EXCLUDE_META_DATA_FIELDS, # type: ignore
faq_question_field=FAQ_QUESTION_FIELD_NAME,
create_index=CREATE_INDEX,
similarity=VECTOR_SIMILARITY_METRIC
)

1
tutorials/Tutorial1_Basic_QA_Pipeline.py
View File

@ -86,7 +86,6 @@ else:
logger.warning("Since we already have a running ES instance we should not index the same documents again. \n"
"If you still want to do this call: document_store.write_documents(dicts) manually ")
# ## Initalize Retriever, Reader, & Finder
#
# ### Retriever