Merge branch 'dev' into migrate_message_table

src/backend/base/langflow/api/v1/files.py

@@ -131,8 +131,8 @@ async def list_profile_pictures(storage_service: StorageService = Depends(get_st
         people = await storage_service.list_files(flow_id=people_path)  # type: ignore
         space = await storage_service.list_files(flow_id=space_path)  # type: ignore
 
-        files = [Path("People") / i for i in people]
-        files += [Path("Space") / i for i in space]
+        files = [f"People/{i}" for i in people]
+        files += [f"Space/{i}" for i in space]
 
         return {"files": files}
 

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 +10,77 @@ 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",
-            info="Authentication parameters. Use the Astra Portal to add the embedding provider integration to your Astra organization.",
+            display_name="Authentication parameters",
             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 +90,17 @@ 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/FirecrawlCrawlApi.py

@@ -0,0 +1,89 @@
+import uuid
+from typing import Optional
+
+from langflow.custom import CustomComponent
+from langflow.schema import Data
+
+
+class FirecrawlCrawlApi(CustomComponent):
+    display_name: str = "FirecrawlCrawlApi"
+    description: str = "Firecrawl Crawl API."
+    output_types: list[str] = ["Document"]
+    documentation: str = "https://docs.firecrawl.dev/api-reference/endpoint/crawl"
+    field_config = {
+        "api_key": {
+            "display_name": "API Key",
+            "field_type": "str",
+            "required": True,
+            "password": True,
+            "info": "The API key to use Firecrawl API.",
+        },
+        "url": {
+            "display_name": "URL",
+            "field_type": "str",
+            "required": True,
+            "info": "The base URL to start crawling from.",
+        },
+        "timeout": {
+            "display_name": "Timeout",
+            "field_type": "int",
+            "info": "The timeout in milliseconds.",
+        },
+        "crawlerOptions": {
+            "display_name": "Crawler Options",
+            "info": "Options for the crawler behavior.",
+        },
+        "pageOptions": {
+            "display_name": "Page Options",
+            "info": "The page options to send with the request.",
+        },
+        "idempotency_key": {
+            "display_name": "Idempotency Key",
+            "field_type": "str",
+            "info": "Optional idempotency key to ensure unique requests.",
+        },
+    }
+
+    def build(
+        self,
+        api_key: str,
+        url: str,
+        timeout: int = 30000,
+        crawlerOptions: Optional[Data] = None,
+        pageOptions: Optional[Data] = None,
+        idempotency_key: Optional[str] = None,
+    ) -> Data:
+        try:
+            from firecrawl.firecrawl import FirecrawlApp  # type: ignore
+        except ImportError:
+            raise ImportError(
+                "Could not import firecrawl integration package. " "Please install it with `pip install firecrawl-py`."
+            )
+
+        if crawlerOptions:
+            crawler_options_dict = crawlerOptions.__dict__["data"]["text"]
+        else:
+            crawler_options_dict = {}
+
+        if pageOptions:
+            page_options_dict = pageOptions.__dict__["data"]["text"]
+        else:
+            page_options_dict = {}
+
+        if not idempotency_key:
+            idempotency_key = str(uuid.uuid4())
+
+        app = FirecrawlApp(api_key=api_key)
+        crawl_result = app.crawl_url(
+            url,
+            {
+                "crawlerOptions": crawler_options_dict,
+                "pageOptions": page_options_dict,
+            },
+            True,
+            int(timeout / 1000),
+            idempotency_key,
+        )
+
+        records = Data(data={"results": crawl_result})
+        return records

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

@@ -0,0 +1,77 @@
+from typing import Optional
+
+from langflow.custom import CustomComponent
+from langflow.schema import Data
+
+
+class FirecrawlScrapeApi(CustomComponent):
+    display_name: str = "FirecrawlScrapeApi"
+    description: str = "Firecrawl Scrape API."
+    output_types: list[str] = ["Document"]
+    documentation: str = "https://docs.firecrawl.dev/api-reference/endpoint/scrape"
+    field_config = {
+        "api_key": {
+            "display_name": "API Key",
+            "field_type": "str",
+            "required": True,
+            "password": True,
+            "info": "The API key to use Firecrawl API.",
+        },
+        "url": {
+            "display_name": "URL",
+            "field_type": "str",
+            "required": True,
+            "info": "The URL to scrape.",
+        },
+        "timeout": {
+            "display_name": "Timeout",
+            "info": "Timeout in milliseconds for the request.",
+            "field_type": "int",
+            "default_value": 10000,
+        },
+        "pageOptions": {
+            "display_name": "Page Options",
+            "info": "The page options to send with the request.",
+        },
+        "extractorOptions": {
+            "display_name": "Extractor Options",
+            "info": "The extractor options to send with the request.",
+        },
+    }
+
+    def build(
+        self,
+        api_key: str,
+        url: str,
+        timeout: Optional[int] = 10000,
+        pageOptions: Optional[Data] = None,
+        extractorOptions: Optional[Data] = None,
+    ) -> Data:
+        try:
+            from firecrawl.firecrawl import FirecrawlApp  # type: ignore
+        except ImportError:
+            raise ImportError(
+                "Could not import firecrawl integration package. " "Please install it with `pip install firecrawl-py`."
+            )
+        if extractorOptions:
+            extractor_options_dict = extractorOptions.__dict__["data"]["text"]
+        else:
+            extractor_options_dict = {}
+
+        if pageOptions:
+            page_options_dict = pageOptions.__dict__["data"]["text"]
+        else:
+            page_options_dict = {}
+
+        app = FirecrawlApp(api_key=api_key)
+        results = app.scrape_url(
+            url,
+            {
+                "timeout": str(timeout),
+                "extractorOptions": extractor_options_dict,
+                "pageOptions": page_options_dict,
+            },
+        )
+
+        record = Data(data=results)
+        return record

src/backend/base/langflow/components/models/OpenAIModel.py

@@ -34,6 +34,12 @@ class OpenAIModelComponent(LCModelComponent):
             info="The maximum number of tokens to generate. Set to 0 for unlimited tokens.",
         ),
         DictInput(name="model_kwargs", display_name="Model Kwargs", advanced=True),
+        BoolInput(
+            name="json_mode",
+            display_name="JSON Mode",
+            advanced=True,
+            info="If True, it will output JSON regardless of passing a schema.",
+        ),
         DictInput(
             name="output_schema",
             is_list=True,
@@ -84,7 +90,7 @@ class OpenAIModelComponent(LCModelComponent):
         max_tokens = self.max_tokens
         model_kwargs = self.model_kwargs or {}
         openai_api_base = self.openai_api_base or "https://api.openai.com/v1"
-        json_mode = bool(output_schema_dict)
+        json_mode = bool(output_schema_dict) or self.json_mode
         seed = self.seed
         model_kwargs["seed"] = seed
 
@@ -101,7 +107,10 @@ class OpenAIModelComponent(LCModelComponent):
             temperature=temperature or 0.1,
         )
         if json_mode:
-            output = output.with_structured_output(schema=output_schema_dict, method="json_mode")  # type: ignore
+            if output_schema_dict:
+                output = output.with_structured_output(schema=output_schema_dict, method="json_mode")  # type: ignore
+            else:
+                output = output.bind(response_format={"type": "json_object"})  # type: ignore
 
         return output
 

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 +24,32 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
     icon = "Cassandra"
 
     inputs = [
-        SecretStrInput(
-            name="token",
-            display_name="Token",
-            info="Authentication token for accessing Cassandra on Astra DB.",
+        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="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.",
+            name="username", display_name="Username", info="Username for the database (leave empty for AstraDB)."
+        ),
+        SecretStrInput(
+            name="token",
+            display_name="Password / AstraDB Token",
+            info="User password for the database (or AstraDB token).",
             required=True,
         ),
         MessageTextInput(
             name="keyspace",
             display_name="Keyspace",
-            info="Optional key space within Astra DB. The keyspace should already be created.",
-            advanced=False,
+            info="Table Keyspace (or AstraDB namespace).",
+            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 +78,13 @@ 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 +112,35 @@ class CassandraVectorStoreComponent(LCVectorStoreComponent):
                 "Could not import cassio integration package. " "Please install it with `pip install cassio`."
             )
 
-        cassio.init(
-            database_id=self.database_id,
-            token=self.token,
-        )
+        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=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:  # type: ignore
+            self.ttl_seconds = None
 
         documents = []
 

src/backend/base/langflow/graph/graph/base.py

@@ -343,10 +343,10 @@ class Graph:
         except Exception as exc:
             logger.exception(exc)
             tb = traceback.format_exc()
-            await self.end_all_traces(error=f"{exc.__class__.__name__}: {exc}\n\n{tb}")
+            asyncio.create_task(self.end_all_traces(error=f"{exc.__class__.__name__}: {exc}\n\n{tb}"))
             raise ValueError(f"Error running graph: {exc}") from exc
         finally:
-            await self.end_all_traces()
+            asyncio.create_task(self.end_all_traces())
         # Get the outputs
         vertex_outputs = []
         for vertex in self.vertices:
@@ -1444,7 +1444,7 @@ class Graph:
 
     def is_vertex_runnable(self, vertex_id: str) -> bool:
         """Returns whether a vertex is runnable."""
-        return self.run_manager.is_vertex_runnable(vertex_id)
+        return self.run_manager.is_vertex_runnable(vertex_id, self.inactivated_vertices)
 
     def build_run_map(self):
         """
@@ -1464,7 +1464,7 @@ class Graph:
         This checks the direct predecessors of each successor to identify any that are
         immediately runnable, expanding the search to ensure progress can be made.
         """
-        return self.run_manager.find_runnable_predecessors_for_successors(vertex_id)
+        return self.run_manager.find_runnable_predecessors_for_successors(vertex_id, self.inactivated_vertices)
 
     def remove_from_predecessors(self, vertex_id: str):
         self.run_manager.remove_from_predecessors(vertex_id)

src/backend/base/langflow/graph/graph/runnable_vertices_manager.py

@@ -1,6 +1,6 @@
 import asyncio
 from collections import defaultdict
-from typing import TYPE_CHECKING, Callable, List, Coroutine
+from typing import TYPE_CHECKING, Callable, Coroutine, List
 
 if TYPE_CHECKING:
     from langflow.graph.graph.base import Graph
@@ -40,19 +40,23 @@ class RunnableVerticesManager:
         self.run_predecessors = state["run_predecessors"]
         self.vertices_to_run = state["vertices_to_run"]
 
-    def is_vertex_runnable(self, vertex_id: str) -> bool:
+    def is_vertex_runnable(self, vertex_id: str, inactivated_vertices: set[str]) -> bool:
         """Determines if a vertex is runnable."""
 
-        return vertex_id in self.vertices_to_run and not self.run_predecessors.get(vertex_id)
+        return (
+            vertex_id in self.vertices_to_run
+            and not self.run_predecessors.get(vertex_id)
+            and vertex_id not in inactivated_vertices
+        )
 
-    def find_runnable_predecessors_for_successors(self, vertex_id: str) -> List[str]:
+    def find_runnable_predecessors_for_successors(self, vertex_id: str, inactivated_vertices: set[str]) -> List[str]:
         """Finds runnable predecessors for the successors of a given vertex."""
         runnable_vertices = []
         visited = set()
 
         for successor_id in self.run_map.get(vertex_id, []):
             for predecessor_id in self.run_predecessors.get(successor_id, []):
-                if predecessor_id not in visited and self.is_vertex_runnable(predecessor_id):
+                if predecessor_id not in visited and self.is_vertex_runnable(predecessor_id, inactivated_vertices):
                     runnable_vertices.append(predecessor_id)
                     visited.add(predecessor_id)
         return runnable_vertices
@@ -104,10 +108,14 @@ class RunnableVerticesManager:
         """
         async with lock:
             self.remove_from_predecessors(vertex.id)
-            direct_successors_ready = [v for v in vertex.successors_ids if self.is_vertex_runnable(v)]
+            direct_successors_ready = [
+                v for v in vertex.successors_ids if self.is_vertex_runnable(v, graph.inactivated_vertices)
+            ]
             if not direct_successors_ready:
                 # No direct successors ready, look for runnable predecessors of successors
-                next_runnable_vertices = self.find_runnable_predecessors_for_successors(vertex.id)
+                next_runnable_vertices = self.find_runnable_predecessors_for_successors(
+                    vertex.id, graph.inactivated_vertices
+                )
             else:
                 next_runnable_vertices = direct_successors_ready
 

src/backend/base/poetry.lock

@@ -112,13 +112,13 @@ frozenlist = ">=1.1.0"
 
 [[package]]
 name = "alembic"
-version = "1.13.1"
+version = "1.13.2"
 description = "A database migration tool for SQLAlchemy."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "alembic-1.13.1-py3-none-any.whl", hash = "sha256:2edcc97bed0bd3272611ce3a98d98279e9c209e7186e43e75bbb1b2bdfdbcc43"},
-    {file = "alembic-1.13.1.tar.gz", hash = "sha256:4932c8558bf68f2ee92b9bbcb8218671c627064d5b08939437af6d77dc05e595"},
+    {file = "alembic-1.13.2-py3-none-any.whl", hash = "sha256:6b8733129a6224a9a711e17c99b08462dbf7cc9670ba8f2e2ae9af860ceb1953"},
+    {file = "alembic-1.13.2.tar.gz", hash = "sha256:1ff0ae32975f4fd96028c39ed9bb3c867fe3af956bd7bb37343b54c9fe7445ef"},
 ]
 
 [package.dependencies]
@@ -739,6 +739,20 @@ typer = ">=0.12.3"
 [package.extras]
 standard = ["fastapi", "uvicorn[standard] (>=0.15.0)"]
 
+[[package]]
+name = "firecrawl-py"
+version = "0.0.16"
+description = "Python SDK for Firecrawl API"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "firecrawl_py-0.0.16-py3-none-any.whl", hash = "sha256:9024f483b501852a6b9c4e6cdfc9e8dde452d922afac357080bb278a0c9c2a26"},
+    {file = "firecrawl_py-0.0.16.tar.gz", hash = "sha256:6c662fa0a549bc7f5c0acb704baba6731869ca0451094034264dfc1b4eb086e4"},
+]
+
+[package.dependencies]
+requests = "*"
+
 [[package]]
 name = "frozenlist"
 version = "1.4.1"
@@ -1158,19 +1172,19 @@ files = [
 
 [[package]]
 name = "langchain"
-version = "0.2.5"
+version = "0.2.6"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain-0.2.5-py3-none-any.whl", hash = "sha256:9aded9a65348254e1c93dcdaacffe4d1b6a5e7f74ef80c160c88ff78ad299228"},
-    {file = "langchain-0.2.5.tar.gz", hash = "sha256:ffdbf4fcea46a10d461bcbda2402220fcfd72a0c70e9f4161ae0510067b9b3bd"},
+    {file = "langchain-0.2.6-py3-none-any.whl", hash = "sha256:f86e8a7afd3e56f8eb5ba47f01dd00144fb9fc2f1db9873bd197347be2857aa4"},
+    {file = "langchain-0.2.6.tar.gz", hash = "sha256:867f6add370c1e3911b0e87d3dd0e36aec1e8f513bf06131340fe8f151d89dc5"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 async-timeout = {version = ">=4.0.0,<5.0.0", markers = "python_version < \"3.11\""}
-langchain-core = ">=0.2.7,<0.3.0"
+langchain-core = ">=0.2.10,<0.3.0"
 langchain-text-splitters = ">=0.2.0,<0.3.0"
 langsmith = ">=0.1.17,<0.2.0"
 numpy = [
@@ -1181,24 +1195,24 @@ pydantic = ">=1,<3"
 PyYAML = ">=5.3"
 requests = ">=2,<3"
 SQLAlchemy = ">=1.4,<3"
-tenacity = ">=8.1.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-community"
-version = "0.2.5"
+version = "0.2.6"
 description = "Community contributed LangChain integrations."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_community-0.2.5-py3-none-any.whl", hash = "sha256:bf37a334952e42c7676d083cf2d2c4cbfbb7de1949c4149fe19913e2b06c485f"},
-    {file = "langchain_community-0.2.5.tar.gz", hash = "sha256:476787b8c8c213b67e7b0eceb53346e787f00fbae12d8e680985bd4f93b0bf64"},
+    {file = "langchain_community-0.2.6-py3-none-any.whl", hash = "sha256:758cc800acfe5dd396bf8ba1b57c4792639ead0eab48ed0367f0732ec6ee1f68"},
+    {file = "langchain_community-0.2.6.tar.gz", hash = "sha256:40ce09a50ed798aa651ddb34c8978200fa8589b9813c7a28ce8af027bbf249f0"},
 ]
 
 [package.dependencies]
 aiohttp = ">=3.8.3,<4.0.0"
 dataclasses-json = ">=0.5.7,<0.7"
-langchain = ">=0.2.5,<0.3.0"
-langchain-core = ">=0.2.7,<0.3.0"
+langchain = ">=0.2.6,<0.3.0"
+langchain-core = ">=0.2.10,<0.3.0"
 langsmith = ">=0.1.0,<0.2.0"
 numpy = [
     {version = ">=1,<2", markers = "python_version < \"3.12\""},
@@ -1207,17 +1221,17 @@ numpy = [
 PyYAML = ">=5.3"
 requests = ">=2,<3"
 SQLAlchemy = ">=1.4,<3"
-tenacity = ">=8.1.0,<9.0.0"
+tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-core"
-version = "0.2.9"
+version = "0.2.10"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_core-0.2.9-py3-none-any.whl", hash = "sha256:426a5a4fea95a5db995ba5ab560b76edd4998fb6fe52ccc28ac987092a4cbfcd"},
-    {file = "langchain_core-0.2.9.tar.gz", hash = "sha256:f1c59082642921727844e1cd0eb36d451edd1872c20e193aa3142aac03495986"},
+    {file = "langchain_core-0.2.10-py3-none-any.whl", hash = "sha256:6eb72086b6bc86db9812da98f79e507c2209a15c0112aefd214a04182ada8586"},
+    {file = "langchain_core-0.2.10.tar.gz", hash = "sha256:33d1fc234ab58c80476eb5bbde2107ef522a2ce8f46bdf47d9e1bd21e054208f"},
 ]
 
 [package.dependencies]
@@ -1233,35 +1247,32 @@ tenacity = ">=8.1.0,<8.4.0 || >8.4.0,<9.0.0"
 
 [[package]]
 name = "langchain-experimental"
-version = "0.0.61"
+version = "0.0.62"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_experimental-0.0.61-py3-none-any.whl", hash = "sha256:f9c516f528f55919743bd56fe1689a53bf74ae7f8902d64b9d8aebc61249cbe2"},
-    {file = "langchain_experimental-0.0.61.tar.gz", hash = "sha256:e9538efb994be5db3045cc582cddb9787c8299c86ffeee9d3779b7f58eef2226"},
+    {file = "langchain_experimental-0.0.62-py3-none-any.whl", hash = "sha256:9240f9e3490e819976f20a37863970036e7baacb7104b9eb6833d19ab6d518c9"},
+    {file = "langchain_experimental-0.0.62.tar.gz", hash = "sha256:9737fbc8429d24457ea4d368e3c9ba9ed1cace0564fb5f1a96a3027a588bd0ac"},
 ]
 
 [package.dependencies]
-langchain-community = ">=0.2.5,<0.3.0"
-langchain-core = ">=0.2.7,<0.3.0"
+langchain-community = ">=0.2.6,<0.3.0"
+langchain-core = ">=0.2.10,<0.3.0"
 
 [[package]]
 name = "langchain-text-splitters"
-version = "0.2.1"
+version = "0.2.2"
 description = "LangChain text splitting utilities"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_text_splitters-0.2.1-py3-none-any.whl", hash = "sha256:c2774a85f17189eaca50339629d2316d13130d4a8d9f1a1a96f3a03670c4a138"},
-    {file = "langchain_text_splitters-0.2.1.tar.gz", hash = "sha256:06853d17d7241ecf5c97c7b6ef01f600f9b0fb953dd997838142a527a4f32ea4"},
+    {file = "langchain_text_splitters-0.2.2-py3-none-any.whl", hash = "sha256:1c80d4b11b55e2995f02d2a326c0323ee1eeff24507329bb22924e420c782dff"},
+    {file = "langchain_text_splitters-0.2.2.tar.gz", hash = "sha256:a1e45de10919fa6fb080ef0525deab56557e9552083600455cb9fa4238076140"},
 ]
 
 [package.dependencies]
-langchain-core = ">=0.2.0,<0.3.0"
-
-[package.extras]
-extended-testing = ["beautifulsoup4 (>=4.12.3,<5.0.0)", "lxml (>=4.9.3,<6.0)"]
+langchain-core = ">=0.2.10,<0.3.0"
 
 [[package]]
 name = "langchainhub"
@@ -2468,13 +2479,13 @@ pyasn1 = ">=0.1.3"
 
 [[package]]
 name = "sentry-sdk"
-version = "2.6.0"
+version = "2.7.0"
 description = "Python client for Sentry (https://sentry.io)"
 optional = false
 python-versions = ">=3.6"
 files = [
-    {file = "sentry_sdk-2.6.0-py2.py3-none-any.whl", hash = "sha256:422b91cb49378b97e7e8d0e8d5a1069df23689d45262b86f54988a7db264e874"},
-    {file = "sentry_sdk-2.6.0.tar.gz", hash = "sha256:65cc07e9c6995c5e316109f138570b32da3bd7ff8d0d0ee4aaf2628c3dd8127d"},
+    {file = "sentry_sdk-2.7.0-py2.py3-none-any.whl", hash = "sha256:db9594c27a4d21c1ebad09908b1f0dc808ef65c2b89c1c8e7e455143262e37c1"},
+    {file = "sentry_sdk-2.7.0.tar.gz", hash = "sha256:d846a211d4a0378b289ced3c434480945f110d0ede00450ba631fc2852e7a0d4"},
 ]
 
 [package.dependencies]
@@ -2506,7 +2517,7 @@ langchain = ["langchain (>=0.0.210)"]
 loguru = ["loguru (>=0.5)"]
 openai = ["openai (>=1.0.0)", "tiktoken (>=0.3.0)"]
 opentelemetry = ["opentelemetry-distro (>=0.35b0)"]
-opentelemetry-experimental = ["opentelemetry-distro (>=0.40b0,<1.0)", "opentelemetry-instrumentation-aiohttp-client (>=0.40b0,<1.0)", "opentelemetry-instrumentation-django (>=0.40b0,<1.0)", "opentelemetry-instrumentation-fastapi (>=0.40b0,<1.0)", "opentelemetry-instrumentation-flask (>=0.40b0,<1.0)", "opentelemetry-instrumentation-requests (>=0.40b0,<1.0)", "opentelemetry-instrumentation-sqlite3 (>=0.40b0,<1.0)", "opentelemetry-instrumentation-urllib (>=0.40b0,<1.0)"]
+opentelemetry-experimental = ["opentelemetry-instrumentation-aio-pika (==0.46b0)", "opentelemetry-instrumentation-aiohttp-client (==0.46b0)", "opentelemetry-instrumentation-aiopg (==0.46b0)", "opentelemetry-instrumentation-asgi (==0.46b0)", "opentelemetry-instrumentation-asyncio (==0.46b0)", "opentelemetry-instrumentation-asyncpg (==0.46b0)", "opentelemetry-instrumentation-aws-lambda (==0.46b0)", "opentelemetry-instrumentation-boto (==0.46b0)", "opentelemetry-instrumentation-boto3sqs (==0.46b0)", "opentelemetry-instrumentation-botocore (==0.46b0)", "opentelemetry-instrumentation-cassandra (==0.46b0)", "opentelemetry-instrumentation-celery (==0.46b0)", "opentelemetry-instrumentation-confluent-kafka (==0.46b0)", "opentelemetry-instrumentation-dbapi (==0.46b0)", "opentelemetry-instrumentation-django (==0.46b0)", "opentelemetry-instrumentation-elasticsearch (==0.46b0)", "opentelemetry-instrumentation-falcon (==0.46b0)", "opentelemetry-instrumentation-fastapi (==0.46b0)", "opentelemetry-instrumentation-flask (==0.46b0)", "opentelemetry-instrumentation-grpc (==0.46b0)", "opentelemetry-instrumentation-httpx (==0.46b0)", "opentelemetry-instrumentation-jinja2 (==0.46b0)", "opentelemetry-instrumentation-kafka-python (==0.46b0)", "opentelemetry-instrumentation-logging (==0.46b0)", "opentelemetry-instrumentation-mysql (==0.46b0)", "opentelemetry-instrumentation-mysqlclient (==0.46b0)", "opentelemetry-instrumentation-pika (==0.46b0)", "opentelemetry-instrumentation-psycopg (==0.46b0)", "opentelemetry-instrumentation-psycopg2 (==0.46b0)", "opentelemetry-instrumentation-pymemcache (==0.46b0)", "opentelemetry-instrumentation-pymongo (==0.46b0)", "opentelemetry-instrumentation-pymysql (==0.46b0)", "opentelemetry-instrumentation-pyramid (==0.46b0)", "opentelemetry-instrumentation-redis (==0.46b0)", "opentelemetry-instrumentation-remoulade (==0.46b0)", "opentelemetry-instrumentation-requests (==0.46b0)", "opentelemetry-instrumentation-sklearn (==0.46b0)", "opentelemetry-instrumentation-sqlalchemy (==0.46b0)", "opentelemetry-instrumentation-sqlite3 (==0.46b0)", "opentelemetry-instrumentation-starlette (==0.46b0)", "opentelemetry-instrumentation-system-metrics (==0.46b0)", "opentelemetry-instrumentation-threading (==0.46b0)", "opentelemetry-instrumentation-tornado (==0.46b0)", "opentelemetry-instrumentation-tortoiseorm (==0.46b0)", "opentelemetry-instrumentation-urllib (==0.46b0)", "opentelemetry-instrumentation-urllib3 (==0.46b0)", "opentelemetry-instrumentation-wsgi (==0.46b0)"]
 pure-eval = ["asttokens", "executing", "pure-eval"]
 pymongo = ["pymongo (>=3.1)"]
 pyspark = ["pyspark (>=2.4.4)"]
@@ -3235,4 +3246,4 @@ local = []
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<3.13"
-content-hash = "4f566531a8539ddc81cb91a7e7f9b723c84679f0af5bb8619f7b02f9ffc6cfaa"
+content-hash = "7e46144d27c633214f00e73e496c0e4d56db1fb47032a21861677ec275b79d86"

src/backend/base/pyproject.toml

@@ -64,6 +64,7 @@ pyperclip = "^1.8.2"
 uncurl = "^0.0.11"
 sentry-sdk = {extras = ["fastapi", "loguru"], version = "^2.5.1"}
 chardet = "^5.2.0"
+firecrawl-py = "^0.0.16"
 
 
 [tool.poetry.extras]