FAQ Pipeline via REST API #4127

shahid-cloud · 2023-02-09T23:03:41Z

shahid-cloud
Feb 9, 2023

I have deployed the FAQ style question answering per the totorial here:
https://haystack.deepset.ai/tutorials/04_faq_style_qa

Next, I would like to expose FAQ style QA using the REST API. However, I am not sure on how to define the FAQPipeline inside the pipelines configuration yaml file.

Looking for guidance on how best to implement this capability using REST

mayankjobanputra · 2023-02-10T13:38:38Z

mayankjobanputra
Feb 10, 2023

Hey @shahid-cloud,

Once you have your pipeline ready, you can use the following code snippet to generate the YAML automatically.
pipe.pipeline.save_to_yaml("faq.yaml")

Once you have this YAML ready, I suggest you follow another tutorial on using REST API with Haystack. Please feel free to come back with more questions if you get stuck or need more help :)

3 replies

shahid-cloud Feb 14, 2023
Author

Thanks @mayankjobanputra for the quick reply. I followed the instructions and created faq.yaml but the haystack container fails to load with the following error:

Traceback (most recent call last):
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/haystack/pipelines/base.py", line 2009, in _load_or_get_component
slack-faq-haystack-api-1 | cls._load_or_get_component(name=value, definitions=definitions, components=components)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/haystack/pipelines/base.py", line 2026, in _load_or_get_component
slack-faq-haystack-api-1 | raise PipelineConfigError(
slack-faq-haystack-api-1 | haystack.errors.PipelineConfigError: Failed loading pipeline component 'ElasticsearchDocumentStore'. See the stacktrace above for more informations.
slack-faq-haystack-api-1 |
slack-faq-haystack-api-1 | The above exception was the direct cause of the following exception:
slack-faq-haystack-api-1 |
slack-faq-haystack-api-1 | Traceback (most recent call last):
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/arbiter.py", line 589, in spawn_worker
slack-faq-haystack-api-1 | worker.init_process()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/uvicorn/workers.py", line 66, in init_process
slack-faq-haystack-api-1 | super(UvicornWorker, self).init_process()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/workers/base.py", line 134, in init_process
slack-faq-haystack-api-1 | self.load_wsgi()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/workers/base.py", line 146, in load_wsgi
slack-faq-haystack-api-1 | self.wsgi = self.app.wsgi()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/app/base.py", line 67, in wsgi
slack-faq-haystack-api-1 | self.callable = self.load()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/app/wsgiapp.py", line 58, in load
slack-faq-haystack-api-1 | return self.load_wsgiapp()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/app/wsgiapp.py", line 48, in load_wsgiapp
slack-faq-haystack-api-1 | return util.import_app(self.app_uri)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/gunicorn/util.py", line 359, in import_app
slack-faq-haystack-api-1 | mod = importlib.import_module(module)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/importlib/init.py", line 126, in import_module
slack-faq-haystack-api-1 | return _bootstrap._gcd_import(name[level:], package, level)
slack-faq-haystack-api-1 | File "", line 1050, in _gcd_import
slack-faq-haystack-api-1 | File "", line 1027, in _find_and_load
slack-faq-haystack-api-1 | File "", line 1006, in _find_and_load_unlocked
slack-faq-haystack-api-1 | File "", line 688, in _load_unlocked
slack-faq-haystack-api-1 | File "", line 883, in exec_module
slack-faq-haystack-api-1 | File "", line 241, in _call_with_frames_removed
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/rest_api/application.py", line 13, in
slack-faq-haystack-api-1 | app = get_app()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/rest_api/utils.py", line 28, in get_app
slack-faq-haystack-api-1 | from rest_api.controller import file_upload, search, feedback, document, health
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/rest_api/controller/file_upload.py", line 20, in
slack-faq-haystack-api-1 | indexing_pipeline: Pipeline = get_pipelines().get("indexing_pipeline", None)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/rest_api/utils.py", line 59, in get_pipelines
slack-faq-haystack-api-1 | pipelines = setup_pipelines()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/rest_api/pipeline/init.py", line 28, in setup_pipelines
slack-faq-haystack-api-1 | query_pipeline = Pipeline.load_from_yaml(Path(config.PIPELINE_YAML_PATH), pipeline_name=config.QUERY_PIPELINE_NAME)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/haystack/pipelines/base.py", line 1908, in load_from_yaml
slack-faq-haystack-api-1 | return cls.load_from_config(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/haystack/pipelines/base.py", line 1978, in load_from_config
slack-faq-haystack-api-1 | component = cls._load_or_get_component(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/haystack/pipelines/base.py", line 2026, in _load_or_get_component
slack-faq-haystack-api-1 | raise PipelineConfigError(
slack-faq-haystack-api-1 | haystack.errors.PipelineConfigError: Failed loading pipeline component 'Retriever'. See the stacktrace above for more informations.
slack-faq-haystack-api-1 | [2023-02-13 21:07:13 +0000] [7] [INFO] Worker exiting (pid: 7)`

The faq.yaml for reference:

components:
- name: ElasticsearchDocumentStore
  params:
    embedding_dim: 384
    embedding_field: question_emb
    excluded_meta_data:
    - question_emb
    similarity: cosine
  type: ElasticsearchDocumentStore
- name: Retriever
  params:
    document_store: ElasticsearchDocumentStore
    embedding_model: sentence-transformers/all-MiniLM-L6-v2
    scale_score: false
    use_gpu: false
  type: EmbeddingRetriever
- name: Docs2Answers
  params: {}
  type: Docs2Answers
pipelines:
- name: query
  nodes:
  - inputs:
    - Query
    name: Retriever
  - inputs:
    - Retriever
    name: Docs2Answers
version: 1.12.2

mayankjobanputra Feb 15, 2023

@shahid-cloud Can you confirm if the ElasticSearch container running on this machine?

shahid-cloud Feb 15, 2023
Author

@mayankjobanputra Looks like elasticsearch startsup after recovering from an error and then haystack is unable to connect with it.

slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,529Z", "level": "ERROR", "component": "o.e.i.g.GeoIpDownloader", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "exception during geoip databases update", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" ,
slack-faq-elasticsearch-1 | "stacktrace": ["org.elasticsearch.ElasticsearchException: not all primary shards of [.geoip_databases] index are active",
slack-faq-elasticsearch-1 | "at org.elasticsearch.ingest.geoip.GeoIpDownloader.updateDatabases(GeoIpDownloader.java:137) ~[ingest-geoip-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.ingest.geoip.GeoIpDownloader.runDownloader(GeoIpDownloader.java:284) [ingest-geoip-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.ingest.geoip.GeoIpDownloaderTaskExecutor.nodeOperation(GeoIpDownloaderTaskExecutor.java:100) [ingest-geoip-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.ingest.geoip.GeoIpDownloaderTaskExecutor.nodeOperation(GeoIpDownloaderTaskExecutor.java:46) [ingest-geoip-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.persistent.NodePersistentTasksExecutor$1.doRun(NodePersistentTasksExecutor.java:42) [elasticsearch-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.common.util.concurrent.ThreadContext$ContextPreservingAbstractRunnable.doRun(ThreadContext.java:777) [elasticsearch-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at org.elasticsearch.common.util.concurrent.AbstractRunnable.run(AbstractRunnable.java:26) [elasticsearch-7.17.6.jar:7.17.6]",
slack-faq-elasticsearch-1 | "at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) [?:?]",
slack-faq-elasticsearch-1 | "at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) [?:?]",
slack-faq-elasticsearch-1 | "at java.lang.Thread.run(Thread.java:833) [?:?]"] }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,546Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "retrieve geoip database [GeoLite2-Country.mmdb] from [.geoip_databases] to [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-Country.mmdb.tmp.gz]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,547Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "retrieve geoip database [GeoLite2-ASN.mmdb] from [.geoip_databases] to [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-ASN.mmdb.tmp.gz]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,547Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "retrieve geoip database [GeoLite2-City.mmdb] from [.geoip_databases] to [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-City.mmdb.tmp.gz]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,590Z", "level": "INFO", "component": "o.e.c.r.a.AllocationService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "Cluster health status changed from [RED] to [YELLOW] (reason: [shards started [[.ds-.logs-deprecation.elasticsearch-default-2023.02.07-000001][0]]]).", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,696Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "successfully reloaded changed geoip database file [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-Country.mmdb]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:23,726Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "successfully reloaded changed geoip database file [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-ASN.mmdb]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-elasticsearch-1 | {"type": "server", "timestamp": "2023-02-15T01:02:24,220Z", "level": "INFO", "component": "o.e.i.g.DatabaseNodeService", "cluster.name": "docker-cluster", "node.name": "6f1295e6d07a", "message": "successfully reloaded changed geoip database file [/tmp/elasticsearch-14361917457217680089/geoip-databases/gDJsoxWwRp2jm22iu1jk1A/GeoLite2-City.mmdb]", "cluster.uuid": "lo3LtkkGQJCiDiqfqE1SLA", "node.id": "gDJsoxWwRp2jm22iu1jk1A" }
slack-faq-haystack-api-1 | [2023-02-15 01:02:27 +0000] [1] [INFO] Starting gunicorn 20.1.0
slack-faq-haystack-api-1 | [2023-02-15 01:02:27 +0000] [1] [INFO] Listening at: http://0.0.0.0:8000 (1)
slack-faq-haystack-api-1 | [2023-02-15 01:02:27 +0000] [1] [INFO] Using worker: uvicorn.workers.UvicornWorker
slack-faq-haystack-api-1 | [2023-02-15 01:02:27 +0000] [7] [INFO] Booting worker with pid: 7
slack-faq-haystack-api-1 | WARNING:elasticsearch:HEAD http://localhost:9200/ [status:N/A request:0.000s]
slack-faq-haystack-api-1 | Traceback (most recent call last):
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connection.py", line 174, in _new_conn
slack-faq-haystack-api-1 | conn = connection.create_connection(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 95, in create_connection
slack-faq-haystack-api-1 | raise err
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/util/connection.py", line 85, in create_connection
slack-faq-haystack-api-1 | sock.connect(sa)
slack-faq-haystack-api-1 | ConnectionRefusedError: [Errno 111] Connection refused
slack-faq-haystack-api-1 |
slack-faq-haystack-api-1 | During handling of the above exception, another exception occurred:
slack-faq-haystack-api-1 |
slack-faq-haystack-api-1 | Traceback (most recent call last):
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/elasticsearch/connection/http_urllib3.py", line 245, in perform_request
slack-faq-haystack-api-1 | response = self.pool.urlopen(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 787, in urlopen
slack-faq-haystack-api-1 | retries = retries.increment(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/util/retry.py", line 525, in increment
slack-faq-haystack-api-1 | raise six.reraise(type(error), error, _stacktrace)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/packages/six.py", line 770, in reraise
slack-faq-haystack-api-1 | raise value
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 703, in urlopen
slack-faq-haystack-api-1 | httplib_response = self._make_request(
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connectionpool.py", line 398, in _make_request
slack-faq-haystack-api-1 | conn.request(method, url, **httplib_request_kw)
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connection.py", line 239, in request
slack-faq-haystack-api-1 | super(HTTPConnection, self).request(method, url, body=body, headers=headers)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/http/client.py", line 1282, in request
slack-faq-haystack-api-1 | self._send_request(method, url, body, headers, encode_chunked)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/http/client.py", line 1328, in _send_request
slack-faq-haystack-api-1 | self.endheaders(body, encode_chunked=encode_chunked)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/http/client.py", line 1277, in endheaders
slack-faq-haystack-api-1 | self._send_output(message_body, encode_chunked=encode_chunked)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/http/client.py", line 1037, in _send_output
slack-faq-haystack-api-1 | self.send(msg)
slack-faq-haystack-api-1 | File "/usr/local/lib/python3.10/http/client.py", line 975, in send
slack-faq-haystack-api-1 | self.connect()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connection.py", line 205, in connect
slack-faq-haystack-api-1 | conn = self._new_conn()
slack-faq-haystack-api-1 | File "/opt/venv/lib/python3.10/site-packages/urllib3/connection.py", line 186, in _new_conn
slack-faq-haystack-api-1 | raise NewConnectionError(
slack-faq-haystack-api-1 | urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0xffff4a63ca00>: Failed to establish a new connection: [Errno 111] Connection refused

mayankjobanputra · 2023-02-17T14:46:29Z

mayankjobanputra
Feb 17, 2023

Hi @shahid-cloud,
Can you share the steps and the dockerfile that you're using here? I am unable to reproduce this locally.

0 replies

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

FAQ Pipeline via REST API #4127

Uh oh!

{{title}}

Uh oh!

Replies: 2 comments 3 replies

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{editor}}'s edit

{{editor}}'s edit

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{title}}

Uh oh!

Uh oh!

{{editor}}'s edit

{{editor}}'s edit

Uh oh!

Uh oh!

{{title}}

Uh oh!

Select a reply

Uh oh!

FAQ Pipeline via REST API #4127

Uh oh!

shahid-cloud Feb 9, 2023

Replies: 2 comments · 3 replies

Uh oh!

mayankjobanputra Feb 10, 2023

Uh oh!

Uh oh!

shahid-cloud Feb 14, 2023 Author

Uh oh!

mayankjobanputra Feb 15, 2023

Uh oh!

Uh oh!

shahid-cloud Feb 15, 2023 Author

Uh oh!

mayankjobanputra Feb 17, 2023

shahid-cloud
Feb 9, 2023

Replies: 2 comments 3 replies

mayankjobanputra
Feb 10, 2023

shahid-cloud Feb 14, 2023
Author

shahid-cloud Feb 15, 2023
Author

mayankjobanputra
Feb 17, 2023