matching code with latest upstream

Signed-off-by: Alex Co <alex.tuan@mindvalley.com>

backend/Dockerfile

@@ -9,7 +9,8 @@ founders@danswer.ai for more information. Please visit https://github.com/danswe
 
 # Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
 ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
 
 RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 # Install system dependencies

backend/Dockerfile.model_server

@@ -8,7 +8,10 @@ visit https://github.com/danswer-ai/danswer."
 
 # Default DANSWER_VERSION, typically overriden during builds by GitHub Actions.
 ARG DANSWER_VERSION=0.3-dev
-ENV DANSWER_VERSION=${DANSWER_VERSION}
+ENV DANSWER_VERSION=${DANSWER_VERSION} \
+    DANSWER_RUNNING_IN_DOCKER="true"
+
+
 RUN echo "DANSWER_VERSION: ${DANSWER_VERSION}"
 
 COPY ./requirements/model_server.txt /tmp/requirements.txt
@@ -21,16 +24,15 @@ RUN apt-get remove -y --allow-remove-essential perl-base && \
 # Download tokenizers, distilbert for the Danswer model
 # Download model weights
 # Run Nomic to pull in the custom architecture and have it cached locally
-# RUN python -c "from transformers import AutoTokenizer; \
-# from huggingface_hub import snapshot_download; \
-# snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
-# snapshot_download('nomic-ai/nomic-embed-text-v1'); \
-# from sentence_transformers import SentenceTransformer; \
-# SentenceTransformer(model_name_or_path='nomic-ai/nomic-embed-text-v1', trust_remote_code=True);"
+RUN python -c "from transformers import AutoTokenizer; \
+AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
+from huggingface_hub import snapshot_download; \
+snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
+snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1');"
 
 # In case the user has volumes mounted to /root/.cache/huggingface that they've downloaded while
 # running Danswer, don't overwrite it with the built in cache folder
-# RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
+RUN mv /root/.cache/huggingface /root/.cache/temp_huggingface
 
 WORKDIR /app
 

backend/alembic/versions/1f60f60c3401_embedding_model_search_settings.py

@@ -30,7 +30,7 @@ def upgrade() -> None:
     op.add_column(
         "search_settings",
         sa.Column(
-            "multipass_indexing", sa.Boolean(), nullable=False, server_default="true"
+            "multipass_indexing", sa.Boolean(), nullable=False, server_default="false"
         ),
     )
     op.add_column(

backend/alembic/versions/35e6853a51d5_server_default_chosen_assistants.py

@@ -0,0 +1,38 @@
+"""server default chosen assistants
+
+Revision ID: 35e6853a51d5
+Revises: c99d76fcd298
+Create Date: 2024-09-13 13:20:32.885317
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = "35e6853a51d5"
+down_revision = "c99d76fcd298"
+branch_labels = None
+depends_on = None
+
+DEFAULT_ASSISTANTS = [-2, -1, 0]
+
+
+def upgrade() -> None:
+    op.alter_column(
+        "user",
+        "chosen_assistants",
+        type_=postgresql.JSONB(astext_type=sa.Text()),
+        nullable=False,
+        server_default=sa.text(f"'{DEFAULT_ASSISTANTS}'::jsonb"),
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "user",
+        "chosen_assistants",
+        type_=postgresql.JSONB(astext_type=sa.Text()),
+        nullable=True,
+        server_default=None,
+    )

backend/alembic/versions/401c1ac29467_add_tables_for_ui_based_llm_.py

@@ -5,7 +5,6 @@
 Create Date: 2024-04-13 18:07:29.153817
 
 """
-
 from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql

backend/alembic/versions/5c7fdadae813_match_any_keywords_flag_for_standard_.py

@@ -0,0 +1,35 @@
+"""match_any_keywords flag for standard answers
+
+Revision ID: 5c7fdadae813
+Revises: efb35676026c
+Create Date: 2024-09-13 18:52:59.256478
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "5c7fdadae813"
+down_revision = "efb35676026c"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        "standard_answer",
+        sa.Column(
+            "match_any_keywords",
+            sa.Boolean(),
+            nullable=False,
+            server_default=sa.false(),
+        ),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("standard_answer", "match_any_keywords")
+    # ### end Alembic commands ###

backend/alembic/versions/703313b75876_add_tokenratelimit_tables.py

@@ -5,7 +5,6 @@
 Create Date: 2024-04-15 01:36:02.952809
 
 """
-
 import json
 from typing import cast
 from alembic import op

backend/alembic/versions/c99d76fcd298_add_nullable_to_persona_id_in_chat_.py

@@ -0,0 +1,31 @@
+"""add nullable to persona id in Chat Session
+
+Revision ID: c99d76fcd298
+Revises: 5c7fdadae813
+Create Date: 2024-07-09 19:27:01.579697
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "c99d76fcd298"
+down_revision = "5c7fdadae813"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.alter_column(
+        "chat_session", "persona_id", existing_type=sa.INTEGER(), nullable=True
+    )
+
+
+def downgrade() -> None:
+    op.alter_column(
+        "chat_session",
+        "persona_id",
+        existing_type=sa.INTEGER(),
+        nullable=False,
+    )

backend/alembic/versions/ef7da92f7213_add_files_to_chatmessage.py

@@ -5,7 +5,6 @@
 Create Date: 2024-04-28 16:59:33.199153
 
 """
-
 from alembic import op
 import sqlalchemy as sa
 from sqlalchemy.dialects import postgresql

backend/alembic/versions/efb35676026c_standard_answer_match_regex_flag.py

@@ -0,0 +1,32 @@
+"""standard answer match_regex flag
+
+Revision ID: efb35676026c
+Revises: 52a219fb5233
+Create Date: 2024-09-11 13:55:46.101149
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "efb35676026c"
+down_revision = "0ebb1d516877"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column(
+        "standard_answer",
+        sa.Column(
+            "match_regex", sa.Boolean(), nullable=False, server_default=sa.false()
+        ),
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column("standard_answer", "match_regex")
+    # ### end Alembic commands ###

backend/alembic/versions/fad14119fb92_delete_tags_with_wrong_enum.py

@@ -5,7 +5,6 @@
 Create Date: 2024-04-25 17:05:09.695703
 
 """
-
 from alembic import op
 
 # revision identifiers, used by Alembic.

backend/danswer/auth/users.py

@@ -231,6 +231,7 @@ async def oauth_callback(
         associate_by_email: bool = False,
         is_verified_by_default: bool = False,
     ) -> models.UOAP:
+        verify_email_in_whitelist(account_email)
         verify_email_domain(account_email)
 
         user = await super().oauth_callback(  # type: ignore
@@ -267,6 +268,7 @@ async def oauth_callback(
             )
             user.is_verified = is_verified_by_default
             user.has_web_login = True
+
         return user
 
     async def on_after_register(
@@ -413,6 +415,7 @@ async def optional_user(
 async def double_check_user(
     user: User | None,
     optional: bool = DISABLE_AUTH,
+    include_expired: bool = False,
 ) -> User | None:
     if optional:
         return None
@@ -429,7 +432,11 @@ async def double_check_user(
             detail="Access denied. User is not verified.",
         )
 
-    if user.oidc_expiry and user.oidc_expiry < datetime.now(timezone.utc):
+    if (
+        user.oidc_expiry
+        and user.oidc_expiry < datetime.now(timezone.utc)
+        and not include_expired
+    ):
         raise HTTPException(
             status_code=status.HTTP_403_FORBIDDEN,
             detail="Access denied. User's OIDC token has expired.",
@@ -438,6 +445,12 @@ async def double_check_user(
     return user
 
 
+async def current_user_with_expired_token(
+    user: User | None = Depends(optional_user),
+) -> User | None:
+    return await double_check_user(user, include_expired=True)
+
+
 async def current_user(
     user: User | None = Depends(optional_user),
 ) -> User | None: