Add darwin assistant

backend/alembic/versions/792d1af3dc44_create_table_user_slack_persona.py

@@ -0,0 +1,32 @@
+"""Create table user_slack_persona
+
+Revision ID: 792d1af3dc44
+Revises: 3a7802814195
+Create Date: 2025-01-24 04:26:02.844951
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "792d1af3dc44"
+down_revision = "3a7802814195"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "user_slack_persona",
+        sa.Column("sender_id", sa.String(), nullable=False),
+        sa.Column("persona_id", sa.Integer(), nullable=True),
+        sa.ForeignKeyConstraint(
+            ["persona_id"],
+            ["persona.id"],
+        ),
+        sa.PrimaryKeyConstraint("sender_id"),
+    )
+
+
+def downgrade() -> None:
+    op.drop_table("user_slack_persona")

backend/danswer/auth/api_key.py

@@ -0,0 +1,31 @@
+from fastapi import Depends
+from fastapi import HTTPException
+from fastapi import Request
+from sqlalchemy import select
+from sqlalchemy.orm import Session
+
+from danswer.db.engine import get_session
+from danswer.db.models import ApiKey
+from danswer.utils.logger import setup_logger
+
+
+logger = setup_logger()
+
+_API_KEY_HEADER = "X-API-Key"
+
+
+def validate_api_key(request: Request, db_session: Session = Depends(get_session)):
+    if _API_KEY_HEADER not in request.headers:
+        return None
+
+    api_key_value = request.headers.get(_API_KEY_HEADER)
+    if not api_key_value:
+        raise HTTPException(status_code=401, detail="Missing API key")
+
+    api_key = db_session.scalar(
+        select(ApiKey).where(ApiKey.hashed_api_key == api_key_value)
+    )
+    if not api_key:
+        raise HTTPException(status_code=401, detail="Invalid API key")
+
+    return None

backend/danswer/chat/chat_utils.py

@@ -114,27 +114,29 @@ def combine_message_chain(
     return "\n\n".join(message_strs)
 
 
-def reorganize_citations(
-    answer: str, citations: list[CitationInfo]
-) -> tuple[str, list[CitationInfo]]:
-    """For a complete, citation-aware response, we want to reorganize the citations so that
+def reorganize_citations(answer: str, citations: list) -> tuple[str, list]:
+    """
+    For a complete, citation-aware response, we want to reorganize the citations so that
     they are in the order of the documents that were used in the response. This just looks nicer / avoids
-    confusion ("Why is there [7] when only 2 documents are cited?")."""
+    confusion ("Why is there [7] when only 2 documents are cited?").
 
-    # Regular expression to find all instances of [[x]](LINK)
-    pattern = r"\[\[(.*?)\]\]\((.*?)\)"
+    Now also handles citations in the format [number] in addition to [[number]](LINK).
+    """
+
+    pattern = r"\[\[(\d+)\]\]\((.*?)\)|\[(\d+)\]"
 
     all_citation_matches = re.findall(pattern, answer)
 
     new_citation_info: dict[int, CitationInfo] = {}
     for citation_match in all_citation_matches:
         try:
-            citation_num = int(citation_match[0])
+            citation_str = citation_match[0] if citation_match[0] else citation_match[2]
+            citation_num = int(citation_str)
             if citation_num in new_citation_info:
                 continue
 
             matching_citation = next(
-                iter([c for c in citations if c.citation_num == int(citation_num)]),
+                (c for c in citations if c.citation_num == citation_num),
                 None,
             )
             if matching_citation is None:
@@ -149,16 +151,28 @@ def reorganize_citations(
 
     # Function to replace citations with their new number
     def slack_link_format(match: re.Match) -> str:
-        link_text = match.group(1)
-        try:
-            citation_num = int(link_text)
-            if citation_num in new_citation_info:
-                link_text = new_citation_info[citation_num].citation_num
-        except Exception:
-            pass
-
-        link_url = match.group(2)
-        return f"[[{link_text}]]({link_url})"
+        # Case 1: Linked citation ([[number]](LINK))
+        if match.group(1):
+            link_text = match.group(1)
+            try:
+                citation_num = int(link_text)
+                if citation_num in new_citation_info:
+                    link_text = new_citation_info[citation_num].citation_num
+            except Exception:
+                pass
+            link_url = match.group(2)
+            return f"[[{link_text}]]({link_url})"
+        # Case 2: Non-linked citation ([number])
+        elif match.group(3):
+            try:
+                citation_num = int(match.group(3))
+                if citation_num in new_citation_info:
+                    citation_num = new_citation_info[citation_num].citation_num
+            except Exception:
+                pass
+            return f"[{citation_num}]"
+        else:
+            return match.group(0)
 
     # Substitute all matches in the input text
     new_answer = re.sub(pattern, slack_link_format, answer)

backend/danswer/configs/app_configs.py

@@ -198,6 +198,10 @@
     for ignored_tag in os.environ.get("JIRA_CONNECTOR_LABELS_TO_SKIP", "").split(",")
     if ignored_tag
 ]
+# Maximum size for Jira tickets in bytes (default: 100KB)
+JIRA_CONNECTOR_MAX_TICKET_SIZE = int(
+    os.environ.get("JIRA_CONNECTOR_MAX_TICKET_SIZE", 100 * 1024)
+)
 
 GONG_CONNECTOR_START_TIME = os.environ.get("GONG_CONNECTOR_START_TIME")
 

backend/danswer/configs/constants.py

@@ -95,6 +95,7 @@ class DocumentSource(str, Enum):
     SHAREPOINT = "sharepoint"
     TEAMS = "teams"
     SALESFORCE = "salesforce"
+    SFKBARTICLES = "sfkbarticles"
     DISCOURSE = "discourse"
     AXERO = "axero"
     CLICKUP = "clickup"