remove slack workspace (#3394)

* remove slack workspace

* update client tokens

* fix up

* clean up docs

* fix up tests

backend/danswer/connectors/factory.py

@@ -41,7 +41,6 @@ from danswer.connectors.salesforce.connector import SalesforceConnector
 from danswer.connectors.sharepoint.connector import SharepointConnector
 from danswer.connectors.slab.connector import SlabConnector
 from danswer.connectors.slack.connector import SlackPollConnector
-from danswer.connectors.slack.load_connector import SlackLoadConnector
 from danswer.connectors.teams.connector import TeamsConnector
 from danswer.connectors.web.connector import WebConnector
 from danswer.connectors.wikipedia.connector import WikipediaConnector
@@ -64,7 +63,6 @@ def identify_connector_class(
         DocumentSource.WEB: WebConnector,
         DocumentSource.FILE: LocalFileConnector,
         DocumentSource.SLACK: {
-            InputType.LOAD_STATE: SlackLoadConnector,
             InputType.POLL: SlackPollConnector,
             InputType.SLIM_RETRIEVAL: SlackPollConnector,
         },

backend/danswer/connectors/slack/connector.py

@@ -134,7 +134,6 @@ def get_latest_message_time(thread: ThreadType) -> datetime:
 
 
 def thread_to_doc(
-    workspace: str,
     channel: ChannelType,
     thread: ThreadType,
     slack_cleaner: SlackTextCleaner,
@@ -179,9 +178,7 @@ def thread_to_doc(
         id=f"{channel_id}__{thread[0]['ts']}",
         sections=[
             Section(
-                link=get_message_link(
+                link=get_message_link(event=m, client=client, channel_id=channel_id),
-                    event=m, workspace=workspace, channel_id=channel_id
-                ),
                 text=slack_cleaner.index_clean(cast(str, m["text"])),
             )
             for m in thread
@@ -265,7 +262,6 @@ def filter_channels(
 
 def _get_all_docs(
     client: WebClient,
-    workspace: str,
     channels: list[str] | None = None,
     channel_name_regex_enabled: bool = False,
     oldest: str | None = None,
@@ -312,7 +308,6 @@ def _get_all_docs(
                 if filtered_thread:
                     channel_docs += 1
                     yield thread_to_doc(
-                        workspace=workspace,
                         channel=channel,
                         thread=filtered_thread,
                         slack_cleaner=slack_cleaner,
@@ -375,14 +370,12 @@ def _get_all_doc_ids(
 class SlackPollConnector(PollConnector, SlimConnector):
     def __init__(
         self,
-        workspace: str,
         channels: list[str] | None = None,
         # if specified, will treat the specified channel strings as
         # regexes, and will only index channels that fully match the regexes
         channel_regex_enabled: bool = False,
         batch_size: int = INDEX_BATCH_SIZE,
     ) -> None:
-        self.workspace = workspace
         self.channels = channels
         self.channel_regex_enabled = channel_regex_enabled
         self.batch_size = batch_size
@@ -416,7 +409,6 @@ class SlackPollConnector(PollConnector, SlimConnector):
         documents: list[Document] = []
         for document in _get_all_docs(
             client=self.client,
-            workspace=self.workspace,
             channels=self.channels,
             channel_name_regex_enabled=self.channel_regex_enabled,
             # NOTE: need to impute to `None` instead of using 0.0, since Slack will
@@ -440,7 +432,6 @@ if __name__ == "__main__":
 
     slack_channel = os.environ.get("SLACK_CHANNEL")
     connector = SlackPollConnector(
-        workspace=os.environ["SLACK_WORKSPACE"],
         channels=[slack_channel] if slack_channel else None,
     )
     connector.load_credentials({"slack_bot_token": os.environ["SLACK_BOT_TOKEN"]})

backend/danswer/connectors/slack/load_connector.py

@@ -1,140 +0,0 @@
-import json
-import os
-from datetime import datetime
-from datetime import timezone
-from pathlib import Path
-from typing import Any
-from typing import cast
-
-from danswer.configs.app_configs import INDEX_BATCH_SIZE
-from danswer.configs.constants import DocumentSource
-from danswer.connectors.interfaces import GenerateDocumentsOutput
-from danswer.connectors.interfaces import LoadConnector
-from danswer.connectors.models import Document
-from danswer.connectors.models import Section
-from danswer.connectors.slack.connector import filter_channels
-from danswer.connectors.slack.utils import get_message_link
-from danswer.utils.logger import setup_logger
-
-
-logger = setup_logger()
-
-
-def get_event_time(event: dict[str, Any]) -> datetime | None:
-    ts = event.get("ts")
-    if not ts:
-        return None
-    return datetime.fromtimestamp(float(ts), tz=timezone.utc)
-
-
-class SlackLoadConnector(LoadConnector):
-    # WARNING: DEPRECATED, DO NOT USE
-    def __init__(
-        self,
-        workspace: str,
-        export_path_str: str,
-        channels: list[str] | None = None,
-        # if specified, will treat the specified channel strings as
-        # regexes, and will only index channels that fully match the regexes
-        channel_regex_enabled: bool = False,
-        batch_size: int = INDEX_BATCH_SIZE,
-    ) -> None:
-        self.workspace = workspace
-        self.channels = channels
-        self.channel_regex_enabled = channel_regex_enabled
-        self.export_path_str = export_path_str
-        self.batch_size = batch_size
-
-    def load_credentials(self, credentials: dict[str, Any]) -> dict[str, Any] | None:
-        if credentials:
-            logger.warning("Unexpected credentials provided for Slack Load Connector")
-        return None
-
-    @staticmethod
-    def _process_batch_event(
-        slack_event: dict[str, Any],
-        channel: dict[str, Any],
-        matching_doc: Document | None,
-        workspace: str,
-    ) -> Document | None:
-        if (
-            slack_event["type"] == "message"
-            and slack_event.get("subtype") != "channel_join"
-        ):
-            if matching_doc:
-                return Document(
-                    id=matching_doc.id,
-                    sections=matching_doc.sections
-                    + [
-                        Section(
-                            link=get_message_link(
-                                event=slack_event,
-                                workspace=workspace,
-                                channel_id=channel["id"],
-                            ),
-                            text=slack_event["text"],
-                        )
-                    ],
-                    source=matching_doc.source,
-                    semantic_identifier=matching_doc.semantic_identifier,
-                    title="",  # slack docs don't really have a "title"
-                    doc_updated_at=get_event_time(slack_event),
-                    metadata=matching_doc.metadata,
-                )
-
-            return Document(
-                id=slack_event["ts"],
-                sections=[
-                    Section(
-                        link=get_message_link(
-                            event=slack_event,
-                            workspace=workspace,
-                            channel_id=channel["id"],
-                        ),
-                        text=slack_event["text"],
-                    )
-                ],
-                source=DocumentSource.SLACK,
-                semantic_identifier=channel["name"],
-                title="",  # slack docs don't really have a "title"
-                doc_updated_at=get_event_time(slack_event),
-                metadata={},
-            )
-
-        return None
-
-    def load_from_state(self) -> GenerateDocumentsOutput:
-        export_path = Path(self.export_path_str)
-
-        with open(export_path / "channels.json") as f:
-            all_channels = json.load(f)
-
-        filtered_channels = filter_channels(
-            all_channels, self.channels, self.channel_regex_enabled
-        )
-
-        document_batch: dict[str, Document] = {}
-        for channel_info in filtered_channels:
-            channel_dir_path = export_path / cast(str, channel_info["name"])
-            channel_file_paths = [
-                channel_dir_path / file_name
-                for file_name in os.listdir(channel_dir_path)
-            ]
-            for path in channel_file_paths:
-                with open(path) as f:
-                    events = cast(list[dict[str, Any]], json.load(f))
-                for slack_event in events:
-                    doc = self._process_batch_event(
-                        slack_event=slack_event,
-                        channel=channel_info,
-                        matching_doc=document_batch.get(
-                            slack_event.get("thread_ts", "")
-                        ),
-                        workspace=self.workspace,
-                    )
-                    if doc:
-                        document_batch[doc.id] = doc
-                        if len(document_batch) >= self.batch_size:
-                            yield list(document_batch.values())
-
-        yield list(document_batch.values())

backend/danswer/connectors/slack/utils.py

@@ -2,6 +2,7 @@ import re
 import time
 from collections.abc import Callable
 from collections.abc import Generator
+from functools import lru_cache
 from functools import wraps
 from typing import Any
 from typing import cast
@@ -21,19 +22,21 @@ basic_retry_wrapper = retry_builder()
 _SLACK_LIMIT = 900
 
 
+@lru_cache()
+def get_base_url(token: str) -> str:
+    """Retrieve and cache the base URL of the Slack workspace based on the client token."""
+    client = WebClient(token=token)
+    return client.auth_test()["url"]
+
+
 def get_message_link(
-    event: dict[str, Any], workspace: str, channel_id: str | None = None
+    event: dict[str, Any], client: WebClient, channel_id: str | None = None
 ) -> str:
-    channel_id = channel_id or cast(
+    channel_id = channel_id or event["channel"]
-        str, event["channel"]
+    message_ts = event["ts"]
-    )  # channel must either be present in the event or passed in
+    response = client.chat_getPermalink(channel=channel_id, message_ts=message_ts)
-    message_ts = cast(str, event["ts"])
+    permalink = response["permalink"]
-    message_ts_without_dot = message_ts.replace(".", "")
+    return permalink
-    thread_ts = cast(str | None, event.get("thread_ts"))
-    return (
-        f"https://{workspace}.slack.com/archives/{channel_id}/p{message_ts_without_dot}"
-        + (f"?thread_ts={thread_ts}" if thread_ts else "")
-    )
 
 
 def _make_slack_api_call_logged(

backend/tests/integration/connector_job_tests/slack/test_permission_sync.py

@@ -67,7 +67,6 @@ def test_slack_permission_sync(
         input_type=InputType.POLL,
         source=DocumentSource.SLACK,
         connector_specific_config={
-            "workspace": "onyx-test-workspace",
             "channels": [public_channel["name"], private_channel["name"]],
         },
         access_type=AccessType.SYNC,
@@ -281,7 +280,6 @@ def test_slack_group_permission_sync(
         input_type=InputType.POLL,
         source=DocumentSource.SLACK,
         connector_specific_config={
-            "workspace": "onyx-test-workspace",
             "channels": [private_channel["name"]],
         },
         access_type=AccessType.SYNC,

backend/tests/integration/connector_job_tests/slack/test_prune.py

@@ -61,7 +61,6 @@ def test_slack_prune(
         input_type=InputType.POLL,
         source=DocumentSource.SLACK,
         connector_specific_config={
-            "workspace": "onyx-test-workspace",
             "channels": [public_channel["name"], private_channel["name"]],
         },
         access_type=AccessType.PUBLIC,

web/src/lib/connectors/connectors.tsx

@@ -546,15 +546,7 @@ Hint: Use the singular form of the object name (e.g., 'Opportunity' instead of '
   },
   slack: {
     description: "Configure Slack connector",
-    values: [
+    values: [],
-      {
-        type: "text",
-        query: "Enter the Slack workspace:",
-        label: "Workspace",
-        name: "workspace",
-        optional: false,
-      },
-    ],
     advanced_values: [
       {
         type: "list",