update to external knowledge api

api/controllers/console/datasets/test_external.py

@@ -39,4 +39,4 @@ class TestExternalApi(Resource):
         return result, 200
 
 
-api.add_resource(TestExternalApi, "/dify/external-knowledge/retrieval-documents")
+api.add_resource(TestExternalApi, "/retrieval")

api/poetry.lock

@@ -6641,19 +6641,6 @@ files = [
     {file = "pyarrow-17.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:392bc9feabc647338e6c89267635e111d71edad5fcffba204425a7c8d13610d7"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:af5ff82a04b2171415f1410cff7ebb79861afc5dae50be73ce06d6e870615204"},
     {file = "pyarrow-17.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:edca18eaca89cd6382dfbcff3dd2d87633433043650c07375d095cd3517561d8"},
-    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7c7916bff914ac5d4a8fe25b7a25e432ff921e72f6f2b7547d1e325c1ad9d155"},
-    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f553ca691b9e94b202ff741bdd40f6ccb70cdd5fbf65c187af132f1317de6145"},
-    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:0cdb0e627c86c373205a2f94a510ac4376fdc523f8bb36beab2e7f204416163c"},
-    {file = "pyarrow-17.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d7d192305d9d8bc9082d10f361fc70a73590a4c65cf31c3e6926cd72b76bc35c"},
-    {file = "pyarrow-17.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:02dae06ce212d8b3244dd3e7d12d9c4d3046945a5933d28026598e9dbbda1fca"},
-    {file = "pyarrow-17.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:13d7a460b412f31e4c0efa1148e1d29bdf18ad1411eb6757d38f8fbdcc8645fb"},
-    {file = "pyarrow-17.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9b564a51fbccfab5a04a80453e5ac6c9954a9c5ef2890d1bcf63741909c3f8df"},
-    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:32503827abbc5aadedfa235f5ece8c4f8f8b0a3cf01066bc8d29de7539532687"},
-    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a155acc7f154b9ffcc85497509bcd0d43efb80d6f733b0dc3bb14e281f131c8b"},
-    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:dec8d129254d0188a49f8a1fc99e0560dc1b85f60af729f47de4046015f9b0a5"},
-    {file = "pyarrow-17.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:a48ddf5c3c6a6c505904545c25a4ae13646ae1f8ba703c4df4a1bfe4f4006bda"},
-    {file = "pyarrow-17.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:42bf93249a083aca230ba7e2786c5f673507fa97bbd9725a1e2754715151a204"},
-    {file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
 ]
 
 [package.dependencies]
@@ -10498,4 +10485,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "17c4108d92c415d987f8b437ea3e0484c5601a05bfe175339a8546c93c159bc5"
+content-hash = "1f9d36b61528276a0761d87ef4f9fa787b5c1b49ae85b238c86626fa1110e2e8"

api/pyproject.toml

@@ -220,6 +220,7 @@ volcengine-python-sdk = {extras = ["ark"], version = "^1.0.98"}
 oci = "^2.133.0"
 tos = "^2.7.1"
 nomic = "^3.1.2"
+validators = "0.21.0"
 [tool.poetry.group.indriect.dependencies]
 kaleido = "0.2.1"
 rank-bm25 = "~0.2.2"

api/services/external_knowledge_service.py

@@ -7,6 +7,7 @@ from typing import Any, Optional, Union
 
 import boto3
 import httpx
+import validators
 
 # from tasks.external_document_indexing_task import external_document_indexing_task
 from configs import dify_config
@@ -21,7 +22,7 @@ from models.dataset import (
 from models.model import UploadFile
 from services.entities.external_knowledge_entities.external_knowledge_entities import ExternalKnowledgeApiSetting, Authorization
 from services.errors.dataset import DatasetNameDuplicateError
-
+from urllib.parse import urlparse
 
 class ExternalDatasetService:
     @staticmethod
@@ -47,6 +48,7 @@ class ExternalDatasetService:
 
     @staticmethod
     def create_external_knowledge_api(tenant_id: str, user_id: str, args: dict) -> ExternalKnowledgeApis:
+        ExternalDatasetService.check_endpoint_and_api_key(args.get("settings"))
         external_knowledge_api = ExternalKnowledgeApis(
             tenant_id=tenant_id,
             created_by=user_id,
@@ -59,6 +61,28 @@ class ExternalDatasetService:
         db.session.add(external_knowledge_api)
         db.session.commit()
         return external_knowledge_api
+    
+    @staticmethod
+    def check_endpoint_and_api_key(settings: dict):
+        if "endpoint" not in settings or not settings["endpoint"]:
+            raise ValueError("endpoint is required")
+        if "api_key" not in settings or not settings["api_key"]:
+            raise ValueError("api_key is required")
+        
+        endpoint = f"{settings['endpoint']}/retrieval"
+        api_key = settings["api_key"]
+        if not validators.url(endpoint):
+            raise ValueError(f"invalid endpoint: {endpoint}")
+        try:
+            response = httpx.post(endpoint, headers={"Authorization": f"Bearer {api_key}"})
+        except Exception as e:
+            raise ValueError(f"failed to connect to the endpoint: {endpoint}")
+        if response.status_code == 502:
+            raise ValueError(f"Bad Gateway: failed to connect to the endpoint: {endpoint}")
+        if response.status_code == 404:
+            raise ValueError(f"Not Found: failed to connect to the endpoint: {endpoint}")
+        if response.status_code == 403:
+            raise ValueError(f"Forbidden: Authorization failed with api_key: {api_key}")
 
     @staticmethod
     def get_external_knowledge_api(external_knowledge_api_id: str) -> ExternalKnowledgeApis: