feat: Add new Atlassian Confluence Component for document loading and vector database integration (#2718)

* feat: Add Gemma 2 to Groq model list (#2586)

Add gemma2 to groq_constants.py

* Adds new ConfluenceComponent module with lazy loading support

- Implements ConfluenceComponent to load documents from the Confluence platform.
- Adds necessary inputs, including URL, username, API key, space_key, and more.
- Supports configuration of max_pages for pagination control.
- Implements lazy loading in the load_documents method for incremental document processing.
- Allows immediate processing of documents as they are loaded.

This new module facilitates integration with the Confluence platform and enables efficient handling of large volumes of data.

* Adds new ConfluenceComponent module

- Implements ConfluenceComponent to load documents from the Confluence platform.
- Adds necessary inputs, including URL, username, API key, space key, and more.
- Supports configuration of max_pages for pagination control.

This new module facilitates integration with the Confluence platform.

* Updated load_documents method to use Data.from_document

- Changed load_documents method to convert documents using Data..from_document instead of docs_to_data for better integration with Data module.
- Updated trace_type to "tool" because the LangSmith API only supports one of the following types: ["tool", "chain", "llm", "retriever", "embedding", "prompt", "parser"].

* [autofix.ci] apply automated fixes

---------

Co-authored-by: Gordon Stein <7331488+gsteinLTU@users.noreply.github.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>

src/backend/base/langflow/components/documentloaders/Confluence.py

@@ -0,0 +1,85 @@
+from typing import List
+from langflow.custom import Component
+from langflow.io import StrInput, SecretStrInput, BoolInput, DropdownInput, Output, IntInput
+from langflow.schema import Data
+from langchain_community.document_loaders import ConfluenceLoader
+from langchain_community.document_loaders.confluence import ContentFormat
+
+
+class ConfluenceComponent(Component):
+    display_name = "Confluence"
+    description = "Confluence wiki collaboration platform"
+    documentation = "https://python.langchain.com/v0.2/docs/integrations/document_loaders/confluence/"
+    trace_type = "tool"
+    icon = "Confluence"
+    name = "Confluence"
+
+    inputs = [
+        StrInput(
+            name="url",
+            display_name="Site URL",
+            required=True,
+            info="The base URL of the Confluence Space. Example: https://<company>.atlassian.net/wiki.",
+        ),
+        StrInput(
+            name="username",
+            display_name="Username",
+            required=True,
+            info="Atlassian User E-mail. Example: email@example.com",
+        ),
+        SecretStrInput(
+            name="api_key",
+            display_name="API Key",
+            required=True,
+            info="Atlassian Key. Create at: https://id.atlassian.com/manage-profile/security/api-tokens",
+        ),
+        StrInput(name="space_key", display_name="Space Key", required=True),
+        BoolInput(name="cloud", display_name="Use Cloud?", required=True, value=True, advanced=True),
+        DropdownInput(
+            name="content_format",
+            display_name="Content Format",
+            options=[
+                ContentFormat.EDITOR.value,
+                ContentFormat.EXPORT_VIEW.value,
+                ContentFormat.ANONYMOUS_EXPORT_VIEW.value,
+                ContentFormat.STORAGE.value,
+                ContentFormat.VIEW.value,
+            ],
+            value=ContentFormat.STORAGE.value,
+            required=True,
+            advanced=True,
+            info="Specify content format, defaults to ContentFormat.STORAGE",
+        ),
+        IntInput(
+            name="max_pages",
+            display_name="Max Pages",
+            required=False,
+            value=1000,
+            advanced=True,
+            info="Maximum number of pages to retrieve in total, defaults 1000",
+        ),
+    ]
+
+    outputs = [
+        Output(name="data", display_name="Data", method="load_documents"),
+    ]
+
+    def build_confluence(self) -> ConfluenceLoader:
+        content_format = ContentFormat(self.content_format)
+        loader = ConfluenceLoader(
+            url=self.url,
+            username=self.username,
+            api_key=self.api_key,
+            cloud=self.cloud,
+            space_key=self.space_key,
+            content_format=content_format,
+            max_pages=self.max_pages,
+        )
+        return loader
+
+    def load_documents(self) -> List[Data]:
+        confluence = self.build_confluence()
+        documents = confluence.load()
+        data = [Data.from_document(doc) for doc in documents]  # Using the from_document method of Data
+        self.status = data
+        return data

src/backend/base/langflow/components/documentloaders/__init__.py

@@ -0,0 +1,3 @@
+from .Confluence import ConfluenceComponent
+
+__all__ = ["ConfluenceComponent"]