Release 0.15.0

.github/workflows/black.yml

@@ -6,6 +6,6 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
-      - uses: psf/black@stable
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+      - uses: psf/black@stable

deployment/task_defs/dev.json

@@ -43,11 +43,11 @@
           "name": "GH_CLIENT_SECRET"
         },
         {
-          "valueFrom": "PEPHUB_GH_REDIRECT_URI",
+          "valueFrom": "PEPHUB_DEV_GH_REDIRECT_URI",
           "name": "REDIRECT_URI"
         },
         {
-          "valueFrom": "PEPHUB_BASE_URI",
+          "valueFrom": "PEPHUB_DEV_BASE_URI",
           "name": "BASE_URI"
         },
         {

deployment/task_defs/primary.json

@@ -7,7 +7,7 @@
   "containerDefinitions": [
     {
       "name": "pephub-container",
-      "cpu": 512,
+      "cpu": 128,
       "memory": 6096,
       "memoryReservation": 512,
       "portMappings": [

launch_docker.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 
-docker run -p 80:80 \
+docker run -p 8000:80 \
     --env POSTGRES_HOST=$POSTGRES_HOST \
     --env POSTGRES_DB=$POSTGRES_DB \
     --env POSTGRES_USER=$POSTGRES_USER \
@@ -9,8 +9,7 @@ docker run -p 80:80 \
     --env QDRANT_PORT=$QDRANT_PORT \
     --env QDRANT_ENABLED=$QDRANT_ENABLED \
     --env QDRANT_API_KEY=$QDRANT_API_KEY \
-    --env HF_MODEL=$HF_MODEL \
     --env GH_CLIENT_ID=$GH_CLIENT_ID \
     --env GH_CLIENT_SECRET=$GH_CLIENT_SECRET \
     --env BASE_URI=$BASE_URI \
-    pephub
+    databio/pephub:dev

pephub/_version.py

@@ -1 +1 @@
-__version__ = "0.14.4"
+__version__ = "0.15.0"

pephub/dependencies.py

@@ -157,7 +157,7 @@ def read_authorization_header(authorization: str = Header(None)) -> Union[dict,
 
 
 def get_organizations_from_session_info(
-    session_info: Union[dict, None] = Depends(read_authorization_header)
+    session_info: Union[dict, None] = Depends(read_authorization_header),
 ) -> List[str]:
     organizations = []
     if session_info:
@@ -168,7 +168,7 @@ def get_organizations_from_session_info(
 
 
 def get_user_from_session_info(
-    session_info: Union[dict, None] = Depends(read_authorization_header)
+    session_info: Union[dict, None] = Depends(read_authorization_header),
 ) -> Union[str, None]:
     user = None
     if session_info:
@@ -405,8 +405,16 @@ def get_namespace_info(
 
 
 @cached(TTLCache(maxsize=100, ttl=5 * 60))
-def get_pepdb_namespace_info(limit: int = 10) -> ListOfNamespaceInfo:
+def get_pepdb_namespace_info(
+    page: int = 0,
+    page_size: int = 10,
+    order_by: str = "number_of_projects",
+) -> ListOfNamespaceInfo:
     """
     Get the information on the biggest namespaces in the database.
     """
-    return agent.namespace.info(limit=limit)
+    return agent.namespace.info(
+        page=page,
+        page_size=page_size,
+        order_by=order_by,
+    )

pephub/helpers.py

@@ -6,6 +6,7 @@
 import jwt
 import pandas as pd
 import yaml
+import json
 from fastapi import Response, UploadFile
 from fastapi.exceptions import HTTPException
 from peppy.const import (
@@ -119,6 +120,28 @@ def download_yaml(content: dict, file_name: str = "unnamed.yaml") -> Response:
     )
 
 
+def download_json(content: dict, file_name: str = "unnamed.json") -> Response:
+    """
+    Convert json/dict to downloading io format
+
+    :param content: content of the file
+    :param file_name: name of the file
+    return Response: response object
+    """
+
+    json_string = json.dumps(content)
+
+    json_bytes = io.BytesIO()
+    json_bytes.write(json_string.encode("utf-8"))
+    json_bytes.seek(0)
+
+    return Response(
+        json_bytes.getvalue(),
+        media_type="application/json",
+        headers={"Content-Disposition": f"attachment; filename={file_name}"},
+    )
+
+
 def build_authorization_url(
     client_id: str,
     redirect_uri: str,

pephub/main.py

@@ -79,8 +79,8 @@
 
 # build routes
 app.include_router(api_base)
-app.include_router(api_namespace)
 app.include_router(api_namespaces)
+app.include_router(api_namespace)
 app.include_router(api_project)
 app.include_router(api_projects)
 app.include_router(api_search)

pephub/routers/api/v1/namespace.py

@@ -5,7 +5,7 @@
 
 import peppy
 from dotenv import load_dotenv
-from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile
+from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile, Request
 from fastapi.responses import JSONResponse
 from pepdbagent import PEPDatabaseAgent
 from pepdbagent.const import DEFAULT_LIMIT_INFO
@@ -18,7 +18,6 @@
 )
 from pepdbagent.models import (
     AnnotationList,
-    ListOfNamespaceInfo,
     Namespace,
     NamespaceStats,
     TarNamespaceModelReturn,
@@ -40,7 +39,12 @@
     get_pepdb_namespace_info,
 )
 from ....helpers import parse_user_file_upload, split_upload_files_on_init_file
-from ...models import FavoriteRequest, ProjectJsonRequest, ProjectRawModel
+from ...models import (
+    FavoriteRequest,
+    ProjectJsonRequest,
+    ProjectRawModel,
+    NamespaceInfoReturnModel,
+)
 
 # from bedms.const import AVAILABLE_SCHEMAS
 
@@ -379,14 +383,27 @@ async def remove_from_stars(
 
 
 @namespaces.get(
-    "/info",
+    "",
     summary="Get information list of biggest namespaces",
-    response_model=ListOfNamespaceInfo,
+    response_model=NamespaceInfoReturnModel,
 )
 async def get_namespace_information(
-    limit: Optional[int] = DEFAULT_LIMIT_INFO,
-) -> ListOfNamespaceInfo:
-    return get_pepdb_namespace_info(limit)
+    request: Request,
+    page: int = 0,
+    page_size: int = DEFAULT_LIMIT_INFO,
+    order_by: Literal[
+        "number_of_projects",
+        "number_of_schemas",
+    ] = "number_of_projects",
+) -> NamespaceInfoReturnModel:
+    results = get_pepdb_namespace_info(
+        page=page,
+        page_size=page_size,
+        order_by=order_by,
+    )
+    return NamespaceInfoReturnModel(
+        **results.model_dump(), server=f"{str(request.base_url)}api/v1/schemas"
+    )
 
 
 @namespaces.get(

pephub/routers/api/v1/project.py

@@ -1,5 +1,5 @@
 import logging
-from typing import Annotated, Any, Callable, Dict, List, Optional, Union
+from typing import Annotated, Any, Literal, Dict, List, Optional, Union
 
 import eido
 import numpy as np
@@ -29,7 +29,7 @@
     ProjectViews,
     HistoryAnnotationModel,
 )
-from peppy.const import SAMPLE_DF_KEY, SAMPLE_RAW_DICT_KEY
+from peppy.const import SAMPLE_RAW_DICT_KEY
 
 # from ....const import SAMPLE_CONVERSION_FUNCTIONS
 from ....dependencies import (
@@ -53,12 +53,9 @@
     ProjectHistoryResponse,
     SamplesResponseModel,
     ConfigResponseModel,
-    StandardizerResponse,
 )
 from ....const import (
     MAX_PROCESSED_PROJECT_SIZE,
-    BEDMS_REPO_URL,
-    MAX_STANDARDIZED_PROJECT_SIZE,
 )
 from .helpers import verify_updated_project
 
@@ -237,7 +234,7 @@ async def delete_a_pep(
 @project.get("/samples", response_model=Union[SamplesResponseModel, str, list, dict])
 async def get_pep_samples(
     proj: dict = Depends(get_project),
-    format: Optional[str] = None,
+    format: Optional[Union[Literal["basic", "csv", "yaml", "json"], None]] = None,
     raw: Optional[bool] = True,
 ):
     """
@@ -277,9 +274,11 @@ async def get_pep_samples(
                 "samples": [sample.to_dict() for sample in proj.samples],
             }
         elif format == "csv":
-            return eido.convert_project(proj, "csv")["samples"]
+            return PlainTextResponse(eido.convert_project(proj, "csv")["samples"])
         elif format == "yaml":
-            return eido.convert_project(proj, "yaml-samples")["samples"]
+            return PlainTextResponse(
+                eido.convert_project(proj, "yaml-samples")["samples"]
+            )
         elif format == "basic":
             return eido.convert_project(proj, "basic")