Vectara Component Update - feature enhancement (#1219)

### Pull Request for Issue #1217 
[feature
request](https://github.com/logspace-ai/langflow/labels/feature%20request)
[python](https://github.com/logspace-ai/langflow/labels/python)

**Description**
This pull request addresses issue #1217 , which concerns the ability to
add files directly to the Vectara vector store using the indexing API's
file upload feature.

**Changes Made**
I have implemented the ability to add files directly to the Vectara
vector store by providing URLs of documents online. The add_files()
method (as well as from_files()) has been added to facilitate this
functionality.

**Files Modified/Added**
Modified: vectara.py

src/backend/langflow/components/vectorstores/Vectara.py

@@ -1,10 +1,14 @@
-from typing import Optional, Union
-
-from langchain.schema import BaseRetriever, Document
-from langchain.vectorstores import Vectara
-from langchain.vectorstores.base import VectorStore
-
+from typing import Optional, Union, List
 from langflow import CustomComponent
+import tempfile
+import urllib.request
+import urllib
+
+from langchain.vectorstores import Vectara
+from langchain.schema import Document
+from langchain.vectorstores.base import VectorStore
+from langchain.schema import BaseRetriever
+from langchain.embeddings import FakeEmbeddings
 
 
 class VectaraComponent(CustomComponent):
@@ -12,13 +16,29 @@ class VectaraComponent(CustomComponent):
     description: str = "Implementation of Vector Store using Vectara"
     documentation = "https://python.langchain.com/docs/integrations/vectorstores/vectara"
     beta = True
-    # api key should be password = True
     field_config = {
-        "vectara_customer_id": {"display_name": "Vectara Customer ID"},
-        "vectara_corpus_id": {"display_name": "Vectara Corpus ID"},
-        "vectara_api_key": {"display_name": "Vectara API Key", "password": True},
+        "vectara_customer_id": {
+            "display_name": "Vectara Customer ID",
+            "required": True,
+        },
+        "vectara_corpus_id": {
+            "display_name": "Vectara Corpus ID",
+            "required": True,
+        },
+        "vectara_api_key": {
+            "display_name": "Vectara API Key",
+            "password": True,
+            "required": True,
+        },
         "code": {"show": False},
-        "documents": {"display_name": "Documents"},
+        "documents": {
+            "display_name": "Documents",
+            "info": "Pass in either for Self Query Retriever or for making a Vectara Object",
+        },
+        "files_url": {
+            "display_name": "Files Url",
+            "info": "Make vectara object using url of files(documents not needed)",
+        },
     }
 
     def build(
@@ -26,21 +46,35 @@ class VectaraComponent(CustomComponent):
         vectara_customer_id: str,
         vectara_corpus_id: str,
         vectara_api_key: str,
+        files_url: Optional[List[str]] = None,
         documents: Optional[Document] = None,
     ) -> Union[VectorStore, BaseRetriever]:
-        # If documents, then we need to create a Vectara instance using .from_documents
         if documents is not None:
             return Vectara.from_documents(
-                documents=documents,  # type: ignore
+                documents=documents,
+                embedding=FakeEmbeddings(size=768),
+                vectara_customer_id=vectara_customer_id,
+                vectara_corpus_id=vectara_corpus_id,
+                vectara_api_key=vectara_api_key,
+            )
+
+        if files_url is not None:
+            files_list = []
+            for url in files_url:
+                name = tempfile.NamedTemporaryFile().name
+                urllib.request.urlretrieve(url, name)
+                files_list.append(name)
+
+            return Vectara.from_files(
+                files=files_list,
+                embedding=FakeEmbeddings(size=768),
                 vectara_customer_id=vectara_customer_id,
                 vectara_corpus_id=vectara_corpus_id,
                 vectara_api_key=vectara_api_key,
-                source="langflow",
             )
 
         return Vectara(
             vectara_customer_id=vectara_customer_id,
             vectara_corpus_id=vectara_corpus_id,
             vectara_api_key=vectara_api_key,
-            source="langflow",
         )

tests/test_endpoints.py

@@ -578,4 +578,4 @@ def test_async_task_processing_vector_store(client, added_vector_store, created_
     # Validate that the task completed successfully and the result is as expected
     assert "result" in task_status_json, task_status_json
     assert "output" in task_status_json["result"], task_status_json["result"]
-    assert "Langflow" in task_status_json["result"]["output"], task_status_json["result"]
+    assert "Langflow" in task_status_json["result"]["output"], task_status_json["result"]