Merge branch 'main' into fix_ref_main

docs/docs/deployment/kubernetes.md

@@ -1,11 +1,5 @@
-import Admonition from "@theme/Admonition";
-
 # Kubernetes
 
-<Admonition type="warning" title="warning">
-This page may contain outdated information. It will be updated as soon as possible.
-</Admonition>
-
 This guide will help you get LangFlow up and running in Kubernetes cluster, including the following steps:
 
 - Install [LangFlow as IDE](#langflow-ide) in a Kubernetes cluster (for development)

src/backend/base/langflow/components/embeddings/AstraVectorize.py

@@ -1,6 +1,6 @@
 from typing import Any
 from langflow.custom import Component
-from langflow.inputs.inputs import DictInput, SecretStrInput, MessageTextInput
+from langflow.inputs.inputs import DictInput, SecretStrInput, MessageTextInput, DropdownInput
 from langflow.template.field.base import Output
 
 
@@ -10,32 +10,58 @@ class AstraVectorize(Component):
     documentation: str = "https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html"
     icon = "AstraDB"
 
+    VECTORIZE_PROVIDERS_MAPPING = {
+        "Azure OpenAI": ["azureOpenAI", ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"]],
+        "Hugging Face - Dedicated": ["huggingfaceDedicated", ["endpoint-defined-model"]],
+        "Hugging Face - Serverless": ["huggingface",
+                                      ["sentence-transformers/all-MiniLM-L6-v2", "intfloat/multilingual-e5-large",
+                                       "intfloat/multilingual-e5-large-instruct", "BAAI/bge-small-en-v1.5",
+                                       "BAAI/bge-base-en-v1.5", "BAAI/bge-large-en-v1.5"]],
+        "Jina AI": ["jinaAI", ["jina-embeddings-v2-base-en", "jina-embeddings-v2-base-de", "jina-embeddings-v2-base-es",
+                               "jina-embeddings-v2-base-code", "jina-embeddings-v2-base-zh"]],
+        "Mistral AI": ["mistral", ["mistral-embed"]],
+        "NVIDIA": ["nvidia", ["NV-Embed-QA"]],
+        "OpenAI": ["openai", ["text-embedding-3-small", "text-embedding-3-large", "text-embedding-ada-002"]],
+        "Upstage": ["upstageAI", ["solar-embedding-1-large"]],
+        "Voyage AI": ["voyageAI",
+                      ["voyage-large-2-instruct", "voyage-law-2", "voyage-code-2", "voyage-large-2", "voyage-2"]]
+    }
+    VECTORIZE_MODELS_STR = "\n\n".join([provider + ": " + (', '.join(models[1])) for provider, models in VECTORIZE_PROVIDERS_MAPPING.items()])
+
     inputs = [
-        MessageTextInput(
+        DropdownInput(
             name="provider",
             display_name="Provider name",
-            info="The embedding provider to use.",
+            options=VECTORIZE_PROVIDERS_MAPPING.keys(),
+            value="",
         ),
         MessageTextInput(
             name="model_name",
             display_name="Model name",
-            info="The embedding model to use.",
+            info=f"The embedding model to use for the selected provider. Each provider has a different set of models "
+                 f"available (full list at https://docs.datastax.com/en/astra-db-serverless/databases/embedding-generation.html):\n\n{VECTORIZE_MODELS_STR}",
+            required=True
+        ),
+        MessageTextInput(
+            name="api_key_name",
+            display_name="API Key name",
+            info="The name of the embeddings provider API key stored on Astra. If set, it will override the 'ProviderKey' in the authentication parameters."
         ),
         DictInput(
             name="authentication",
-            display_name="Authentication",
+            display_name="Authentication parameters",
-            info="Authentication parameters. Use the Astra Portal to add the embedding provider integration to your Astra organization.",
             is_list=True,
+            advanced=True,
         ),
         SecretStrInput(
             name="provider_api_key",
             display_name="Provider API Key",
             info="An alternative to the Astra Authentication that let you use directly the API key of the provider.",
+            advanced=True,
         ),
         DictInput(
             name="model_parameters",
             display_name="Model parameters",
-            info="Additional model parameters.",
             advanced=True,
             is_list=True,
         ),
@@ -45,12 +71,17 @@ class AstraVectorize(Component):
     ]
 
     def build_options(self) -> dict[str, Any]:
+        provider_value = self.VECTORIZE_PROVIDERS_MAPPING[self.provider][0]
+        authentication = {**self.authentication}
+        api_key_name = self.api_key_name
+        if api_key_name:
+            authentication["providerKey"] = api_key_name
         return {
             # must match exactly astra CollectionVectorServiceOptions
             "collection_vector_service_options": {
-                "provider": self.provider,
+                "provider": provider_value,
                 "modelName": self.model_name,
-                "authentication": self.authentication,
+                "authentication": authentication,
                 "parameters": self.model_parameters,
             },
             "collection_embedding_api_key": self.provider_api_key,

src/backend/base/langflow/components/langchain_utilities/FirecrawlScrapeApi.py

@@ -2,8 +2,6 @@ from typing import Optional
 from firecrawl.firecrawl import FirecrawlApp
 from langflow.custom import CustomComponent
 from langflow.schema import Data
-from langflow.services.database.models.base import orjson_dumps
-import json
 
 class FirecrawlScrapeApi(CustomComponent):
     display_name: str = "FirecrawlScrapeApi"

src/backend/base/langflow/components/vectorstores/Cassandra.py

@@ -4,6 +4,7 @@ from langchain_community.vectorstores import Cassandra
 
 from langflow.base.vectorstores.model import LCVectorStoreComponent
 from langflow.helpers.data import docs_to_data
+from langflow.inputs import DictInput
 from langflow.io import (
     DataInput,
     DropdownInput,
@@ -23,24 +24,30 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
     icon = "Cassandra"
 
     inputs = [
+        MessageTextInput(name="database_ref",
+                         display_name="Contact Points / Astra Database ID",
+                         info="Contact points for the database (or AstraDB database ID)",
+                         required=True),
+        MessageTextInput(name="username",
+                         display_name="Username",
+                         info="Username for the database (leave empty for AstraDB)."),
         SecretStrInput(
             name="token",
-            display_name="Token",
+            display_name="Password / AstraDB Token",
-            info="Authentication token for accessing Cassandra on Astra DB.",
+            info="User password for the database (or AstraDB token).",
-            required=True,
+            required=True
-        ),
-        MessageTextInput(name="database_id", display_name="Database ID", info="The Astra database ID.", required=True),
-        MessageTextInput(
-            name="table_name",
-            display_name="Table Name",
-            info="The name of the table where vectors will be stored.",
-            required=True,
         ),
         MessageTextInput(
             name="keyspace",
             display_name="Keyspace",
-            info="Optional key space within Astra DB. The keyspace should already be created.",
+            info="Table Keyspace (or AstraDB namespace).",
-            advanced=False,
+            required=True,
+        ),
+        MessageTextInput(
+            name="table_name",
+            display_name="Table Name",
+            info="The name of the table (or AstraDB collection) where vectors will be stored.",
+            required=True,
         ),
         IntInput(
             name="ttl_seconds",
@@ -69,6 +76,13 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
             value="Sync",
             advanced=True,
         ),
+        DictInput(
+            name="cluster_kwargs",
+            display_name="Cluster arguments",
+            info="Optional dictionary of additional keyword arguments for the Cassandra cluster.",
+            advanced=True,
+            is_list=True
+        ),
         MultilineInput(name="search_query", display_name="Search Query"),
         DataInput(
             name="ingest_data",
@@ -96,10 +110,35 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
                 "Could not import cassio integration package. " "Please install it with `pip install cassio`."
             )
 
+        from uuid import UUID
+
+        database_ref = self.database_ref
+
+        try:
+            UUID(self.database_ref)
+            is_astra = True
+        except ValueError:
+            is_astra = False
+            if "," in self.database_ref:
+                # use a copy because we can't change the type of the parameter
+                database_ref = self.database_ref.split(",")
+
+        if is_astra:
             cassio.init(
-            database_id=self.database_id,
+                database_id=database_ref,
                 token=self.token,
+                cluster_kwargs=self.cluster_kwargs,
             )
+        else:
+            cassio.init(
+                contact_points=database_ref,
+                username=self.username,
+                password=self.token,
+                cluster_kwargs=self.cluster_kwargs,
+            )
+
+        if not self.ttl_seconds:
+            self.ttl_seconds = None
 
         documents = []