jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/dev' into saveComponent

Browse source
This commit is contained in:
anovazzi1 2023-10-16 17:09:42 -03:00
commit 4f50425807
15 changed files with 195 additions and 75 deletions
Download patch file Download diff file Expand all files Collapse all files

6
src/backend/langflow/components/llms/HuggingFaceEndpoints.py
View file

@ -1,6 +1,6 @@
from typing import Optional
from langflow import CustomComponent
from langchain.llms import HuggingFaceEndpoint
from langchain.llms.huggingface_endpoint import HuggingFaceEndpoint
from langchain.llms.base import BaseLLM
@ -13,7 +13,6 @@ class HuggingFaceEndpointsComponent(CustomComponent):
"endpoint_url": {"display_name": "Endpoint URL", "password": True},
"task": {
"display_name": "Task",
"type": "select",
"options": ["text2text-generation", "text-generation", "summarization"],
},
"huggingfacehub_api_token": {"display_name": "API token", "password": True},
@ -27,7 +26,7 @@ class HuggingFaceEndpointsComponent(CustomComponent):
def build(
self,
endpoint_url: str,
task="text2text-generation",
task: str = "text2text-generation",
huggingfacehub_api_token: Optional[str] = None,
model_kwargs: Optional[dict] = None,
) -> BaseLLM:
@ -36,6 +35,7 @@ class HuggingFaceEndpointsComponent(CustomComponent):
endpoint_url=endpoint_url,
task=task,
huggingfacehub_api_token=huggingfacehub_api_token,
model_kwargs=model_kwargs,
)
except Exception as e:
raise ValueError("Could not connect to HuggingFace Endpoints API.") from e

54
src/backend/langflow/field_typing/__init__.py
View file

@ -1,3 +1,53 @@
from .base import NestedDict
# LANGCHAIN_BASE_TYPES = {
# "Chain": Chain,
# "AgentExecutor": AgentExecutor,
# "Tool": Tool,
# "BaseLLM": BaseLLM,
# "PromptTemplate": PromptTemplate,
# "BaseLoader": BaseLoader,
# "Document": Document,
# "TextSplitter": TextSplitter,
# "VectorStore": VectorStore,
# "Embeddings": Embeddings,
# "BaseRetriever": BaseRetriever,
# "BaseOutputParser": BaseOutputParser,
# "BaseMemory": BaseMemory,
# "BaseChatMemory": BaseChatMemory,
# }
from .constants import (
Tool,
PromptTemplate,
Chain,
BaseChatMemory,
BaseLLM,
BaseLoader,
BaseMemory,
BaseOutputParser,
BaseRetriever,
VectorStore,
Embeddings,
TextSplitter,
Document,
AgentExecutor,
NestedDict,
Data,
)
__all__ = ["NestedDict"]
__all__ = [
"NestedDict",
"Data",
"Tool",
"PromptTemplate",
"Chain",
"BaseChatMemory",
"BaseLLM",
"BaseLoader",
"BaseMemory",
"BaseOutputParser",
"BaseRetriever",
"VectorStore",
"Embeddings",
"TextSplitter",
"Document",
"AgentExecutor",
]

4
src/backend/langflow/field_typing/base.py
View file

@ -1,4 +0,0 @@
from typing import Union, Dict
# Type alias for more complex dicts
NestedDict = Dict[str, Union[str, Dict]]

50
src/backend/langflow/field_typing/constants.py Normal file
View file

@ -0,0 +1,50 @@
from langchain.agents.agent import AgentExecutor
from langchain.chains.base import Chain
from langchain.document_loaders.base import BaseLoader
from langchain.llms.base import BaseLLM
from langchain.memory.chat_memory import BaseChatMemory
from langchain.prompts import PromptTemplate
from langchain.schema import BaseOutputParser, BaseRetriever, Document
from langchain.schema.embeddings import Embeddings
from langchain.schema.memory import BaseMemory
from langchain.text_splitter import TextSplitter
from langchain.tools import Tool
from langchain.vectorstores.base import VectorStore
from typing import Union, Dict
# Type alias for more complex dicts
NestedDict = Dict[str, Union[str, Dict]]
class Data:
pass
LANGCHAIN_BASE_TYPES = {
"Chain": Chain,
"AgentExecutor": AgentExecutor,
"Tool": Tool,
"BaseLLM": BaseLLM,
"PromptTemplate": PromptTemplate,
"BaseLoader": BaseLoader,
"Document": Document,
"TextSplitter": TextSplitter,
"VectorStore": VectorStore,
"Embeddings": Embeddings,
"BaseRetriever": BaseRetriever,
"BaseOutputParser": BaseOutputParser,
"BaseMemory": BaseMemory,
"BaseChatMemory": BaseChatMemory,
}
# Langchain base types plus Python base types
CUSTOM_COMPONENT_SUPPORTED_TYPES = {
**LANGCHAIN_BASE_TYPES,
"str": str,
"int": int,
"float": float,
"bool": bool,
"list": list,
"dict": dict,
"NestedDict": NestedDict,
"Data": Data,
}

10
src/backend/langflow/graph/vertex/base.py
View file

@ -216,6 +216,16 @@ class Vertex:
}
elif isinstance(_value, dict):
params[key] = _value
elif value.get("type") == "int" and value.get("value") is not None:
try:
params[key] = int(value.get("value"))
except ValueError:
params[key] = value.get("value")
elif value.get("type") == "float" and value.get("value") is not None:
try:
params[key] = float(value.get("value"))
except ValueError:
params[key] = value.get("value")
else:
params[key] = value.get("value")

78
src/backend/langflow/interface/custom/constants.py
View file

@ -1,65 +1,33 @@
from langchain.prompts import PromptTemplate
from langchain.chains.base import Chain
from langchain.document_loaders.base import BaseLoader
from langchain.schema.embeddings import Embeddings
from langchain.llms.base import BaseLLM
from langchain.schema import BaseRetriever, Document
from langchain.text_splitter import TextSplitter
from langchain.tools import Tool
from langchain.vectorstores.base import VectorStore
from langchain.schema import BaseOutputParser
from langchain.schema.memory import BaseMemory
from langchain.memory.chat_memory import BaseChatMemory
from langchain.agents.agent import AgentExecutor
LANGCHAIN_BASE_TYPES = {
"Chain": Chain,
"AgentExecutor": AgentExecutor,
"Tool": Tool,
"BaseLLM": BaseLLM,
"PromptTemplate": PromptTemplate,
"BaseLoader": BaseLoader,
"Document": Document,
"TextSplitter": TextSplitter,
"VectorStore": VectorStore,
"Embeddings": Embeddings,
"BaseRetriever": BaseRetriever,
"BaseOutputParser": BaseOutputParser,
"BaseMemory": BaseMemory,
"BaseChatMemory": BaseChatMemory,
}
# Langchain base types plus Python base types
CUSTOM_COMPONENT_SUPPORTED_TYPES = {
**LANGCHAIN_BASE_TYPES,
"str": str,
"int": int,
"float": float,
"bool": bool,
"list": list,
"dict": dict,
}
DEFAULT_CUSTOM_COMPONENT_CODE = """from langflow import CustomComponent
from langchain.llms.base import BaseLLM
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.schema import Document
from langflow.field_typing import (
Tool,
PromptTemplate,
Chain,
BaseChatMemory,
BaseLLM,
BaseLoader,
BaseMemory,
BaseOutputParser,
BaseRetriever,
VectorStore,
Embeddings,
TextSplitter,
Document,
AgentExecutor,
NestedDict,
Data,
)
import requests
class YourComponent(CustomComponent):
class Component(CustomComponent):
display_name: str = "Custom Component"
description: str = "Create any custom component you want!"
def build_config(self):
return { "url": { "multiline": True, "required": True } }
return {"param": {"display_name": "Parameter"}}
def build(self, param: Data) -> Data:
return param
def build(self, url: str, llm: BaseLLM, prompt: PromptTemplate) -> Document:
response = requests.get(url)
chain = LLMChain(llm=llm, prompt=prompt)
result = chain.run(response.text[:300])
return Document(page_content=str(result))
"""

5
src/backend/langflow/interface/custom/custom_component.py
View file

@ -1,7 +1,7 @@
from typing import Any, Callable, List, Optional, Union
from uuid import UUID
from fastapi import HTTPException
from langflow.interface.custom.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.field_typing.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.interface.custom.component import Component
from langflow.interface.custom.directory_reader import DirectoryReader
from langflow.services.getters import get_db_service
@ -108,6 +108,9 @@ class CustomComponent(Component, extra=Extra.allow):
),
},
)
elif not arg.get("type"):
# Set the type to Data
arg["type"] = "Data"
return args
@property

23
src/backend/langflow/interface/types.py
View file

@ -4,7 +4,7 @@ from typing import Any, List
from langflow.api.utils import get_new_key
from langflow.interface.agents.base import agent_creator
from langflow.interface.chains.base import chain_creator
from langflow.interface.custom.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.field_typing.constants import CUSTOM_COMPONENT_SUPPORTED_TYPES
from langflow.interface.custom.utils import extract_inner_type
from langflow.interface.document_loaders.base import documentloader_creator
from langflow.interface.embeddings.base import embedding_creator
@ -288,6 +288,24 @@ def add_base_classes(frontend_node, return_types: List[str]):
frontend_node.get("base_classes").append(base_class)
def add_output_types(frontend_node, return_types: List[str]):
"""Add output types to the frontend node"""
for return_type in return_types:
if return_type not in CUSTOM_COMPONENT_SUPPORTED_TYPES or return_type is None:
raise HTTPException(
status_code=400,
detail={
"error": (
"Invalid return type should be one of: "
f"{list(CUSTOM_COMPONENT_SUPPORTED_TYPES.keys())}"
),
"traceback": traceback.format_exc(),
},
)
frontend_node.get("output_types").append(return_type)
def build_langchain_template_custom_component(custom_component: CustomComponent):
"""Build a custom component template for the langchain"""
try:
@ -314,6 +332,9 @@ def build_langchain_template_custom_component(custom_component: CustomComponent)
add_base_classes(
frontend_node, custom_component.get_function_entrypoint_return_type
)
add_output_types(
frontend_node, custom_component.get_function_entrypoint_return_type
)
logger.debug("Added base classes")
return frontend_node
except Exception as exc:

4
src/backend/langflow/processing/base.py
View file

@ -34,7 +34,9 @@ def get_langfuse_callback(trace_id):
if langfuse := LangfuseInstance.get():
logger.debug("Langfuse credentials found")
try:
trace = langfuse.trace(CreateTrace(id=trace_id))
trace = langfuse.trace(
CreateTrace(name="langflow-" + trace_id, id=trace_id)
)
return trace.getNewHandler()
except Exception as exc:
logger.error(f"Error initializing langfuse callback: {exc}")

3
src/backend/langflow/template/frontend_node/custom_components.py
View file

@ -2,6 +2,7 @@ from langflow.template.field.base import TemplateField
from langflow.template.frontend_node.base import FrontendNode
from langflow.template.template.base import Template
from langflow.interface.custom.constants import DEFAULT_CUSTOM_COMPONENT_CODE
from typing import Optional
class CustomComponentFrontendNode(FrontendNode):
@ -24,7 +25,7 @@ class CustomComponentFrontendNode(FrontendNode):
)
],
)
description: str = "Create any custom component you want!"
description: Optional[str] = None
base_classes: list[str] = []
def to_dict(self):

4
src/backend/langflow/utils/util.py
View file

@ -191,7 +191,9 @@ def get_base_classes(cls):
"""Get the base classes of a class.
These are used to determine the output of the nodes.
"""
if bases := cls.__bases__:
if hasattr(cls, "__bases__") and cls.__bases__:
bases = cls.__bases__
result = []
for base in bases:
if any(type in base.__module__ for type in ["pydantic", "abc"]):

3
src/frontend/src/contexts/tabsContext.tsx
View file

@ -260,9 +260,6 @@ export function TabsProvider({ children }: { children: ReactNode }) {
// simulate a click on the link element to trigger the download
link.click();
setNoticeData({
title: "Warning: Critical data, JSON file may include API keys.",
});
}
function downloadFlows() {

17
src/frontend/src/modals/exportModal/index.tsx
View file

@ -4,6 +4,7 @@ import IconComponent from "../../components/genericIconComponent";
import { Button } from "../../components/ui/button";
import { Checkbox } from "../../components/ui/checkbox";
import { EXPORT_DIALOG_SUBTITLE } from "../../constants/constants";
import { alertContext } from "../../contexts/alertContext";
import { TabsContext } from "../../contexts/tabsContext";
import { removeApiKeys } from "../../utils/reactflowUtils";
import BaseModal from "../baseModal";
@ -11,7 +12,8 @@ import BaseModal from "../baseModal";
const ExportModal = forwardRef(
(props: { children: ReactNode }, ref): JSX.Element => {
const { flows, tabId, downloadFlow } = useContext(TabsContext);
const [checked, setChecked] = useState(false);
const { setNoticeData } = useContext(alertContext);
const [checked, setChecked] = useState(true);
const flow = flows.find((f) => f.id === tabId);
useEffect(() => {
setName(flow!.name);
@ -44,6 +46,7 @@ const ExportModal = forwardRef(
<div className="mt-3 flex items-center space-x-2">
<Checkbox
id="terms"
checked={checked}
onCheckedChange={(event: boolean) => {
setChecked(event);
}}
@ -52,18 +55,26 @@ const ExportModal = forwardRef(
Save with my API keys
</label>
</div>
<span className="text-xs text-destructive">
Caution: Uncheck this box only removes API keys from fields
specifically designated for API keys.
</span>
</BaseModal.Content>
<BaseModal.Footer>
<Button
onClick={() => {
if (checked)
if (checked) {
downloadFlow(
flows.find((flow) => flow.id === tabId)!,
name!,
description
);
else
setNoticeData({
title:
"Warning: Critical data, JSON file may include API keys.",
});
} else
downloadFlow(
removeApiKeys(flows.find((flow) => flow.id === tabId)!),
name!,