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

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

Browse source
This commit is contained in:
Gabriel Luiz Freitas Almeida 2024-02-28 12:57:53 -03:00
commit 225b09650e
30 changed files with 66 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/components/embeddings.mdx
View file

@ -98,9 +98,9 @@ Used to load [OpenAI’s](https://openai.com/) embedding models.
Wrapper around [Google Vertex AI](https://cloud.google.com/vertex-ai) [Embeddings API](https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings).
:::info
<Admonition type="info">
Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP). It provides access, management, and development of applications and services through global data centers. To use Vertex AI PaLM, you need to have the [google-cloud-aiplatform](https://pypi.org/project/google-cloud-aiplatform/) Python package installed and credentials configured for your environment.
:::
</Admonition>
- **credentials:** The default custom credentials (google.auth.credentials.Credentials) to use.
- **location:** The default location to use when making API calls – defaults to `us-central1`.

21
docs/docs/components/llms.mdx
View file

@ -40,9 +40,10 @@ Wrapper around Anthropic's large language model used for chat-based interactions
The `CTransformers` component provides access to the Transformer models implemented in C/C++ using the [GGML](https://github.com/ggerganov/ggml) library.
:::info
<Admonition type="info">
Make sure to have the `ctransformers` python package installed. Learn more about installation, supported models, and usage [here](https://github.com/marella/ctransformers).
:::
</Admonition>
**config:** Configuration for the Transformer models. Check out [config](https://github.com/marella/ctransformers#config). Defaults to:
@ -115,9 +116,9 @@ Wrapper around [Cohere's](https://cohere.com) large language models.
Wrapper around [HuggingFace](https://www.huggingface.co/models) models.
:::info
<Admonition type="info">
The HuggingFace Hub is an online platform that hosts over 120k models, 20k datasets, and 50k demo apps, all of which are open-source and publicly available. Discover more at [HuggingFace](http://www.huggingface.co).
:::
</Admonition>
- **huggingfacehub_api_token:** Token needed to authenticate the API.
- **model_kwargs:** Keyword arguments to pass to the model.
@ -130,9 +131,9 @@ The HuggingFace Hub is an online platform that hosts over 120k models, 20k datas
The `LlamaCpp` component provides access to the `llama.cpp` models.
:::info
<Admonition type="info">
Make sure to have the `llama.cpp` python package installed. Learn more about installation, supported models, and usage [here](https://github.com/ggerganov/llama.cpp).
:::
</Admonition>
- **echo:** Whether to echo the prompt – defaults to `False`.
- **f16_kv:** Use half-precision for key/value cache – defaults to `True`.
@ -181,9 +182,9 @@ Wrapper around [OpenAI's](https://openai.com) large language models.
Wrapper around [Google Vertex AI](https://cloud.google.com/vertex-ai) large language models.
:::info
<Admonition type="info">
Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP). It provides access, management, and development of applications and services through global data centers. To use Vertex AI PaLM, you need to have the [google-cloud-aiplatform](https://pypi.org/project/google-cloud-aiplatform/) Python package installed and credentials configured for your environment.
:::
</Admonition>
- **credentials:** The default custom credentials (google.auth.credentials.Credentials) to use.
- **location:** The default location to use when making API calls – defaults to `us-central1`.
@ -203,9 +204,9 @@ Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP).
Wrapper around [Google Vertex AI](https://cloud.google.com/vertex-ai) large language models.
:::info
<Admonition type="info">
Vertex AI is a cloud computing platform offered by Google Cloud Platform (GCP). It provides access, management, and development of applications and services through global data centers. To use Vertex AI PaLM, you need to have the [google-cloud-aiplatform](https://pypi.org/project/google-cloud-aiplatform/) Python package installed and credentials configured for your environment.
:::
</Admonition>
- **credentials:** The default custom credentials (google.auth.credentials.Credentials) to use.
- **location:** The default location to use when making API calls – defaults to `us-central1`.

5
docs/docs/deployment/gcp-deployment.md
View file

@ -4,9 +4,8 @@
This guide will help you set up a Langflow development VM in a Google Cloud Platform project using Google Cloud Shell.
:::note
When Cloud Shell opens, be sure to select **Trust repo**. Some `gcloud` commands might not run in an ephemeral Cloud Shell environment.
:::
> Note: When Cloud Shell opens, be sure to select **Trust repo**. Some `gcloud` commands might not run in an ephemeral Cloud Shell environment.
## Standard VM

1
docs/docs/examples/buffer-memory.mdx
View file

@ -14,6 +14,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/buffer-memory.png",
dark: "img/buffer-memory.png",
}}
/>

1
docs/docs/examples/conversation-chain.mdx
View file

@ -20,6 +20,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/basic-chat.png",
dark: "img/basic-chat.png",
}}
/>

9
docs/docs/examples/csv-loader.mdx
View file

@ -32,6 +32,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/csv-loader.png",
dark: "img/csv-loader.png",
}}
/>
@ -39,12 +40,12 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`CSVLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/csv)
- [`CSVLoader`](https://python.langchain.com/docs/integrations/document_loaders/csv)
- [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter)
- [`OpenAIEmbedding`](https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/openai)
- [`Chroma`](https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/chroma)
- [`OpenAIEmbedding`](https://python.langchain.com/docs/integrations/text_embedding/openai)
- [`Chroma`](https://python.langchain.com/docs/integrations/vectorstores/chroma)
- [`VectorStoreInfo`](https://python.langchain.com/docs/modules/data_connection/vectorstores/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`VectorStoreAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
- [`VectorStoreAgent`](https://js.langchain.com/docs/modules/agents/tools/how_to/agents_with_vectorstores)
</Admonition>

3
docs/docs/examples/flow-runner.mdx
View file

@ -14,6 +14,7 @@ The CustomComponent class allows us to create components that interact with Lang
alt="Document Processor Component"
sources={{
light: "img/flow_runner.png",
dark: "img/flow_runner.png",
}}
style={{
width: "30%",
@ -339,6 +340,7 @@ Done! This is what our script and custom component looks like:
alt="Document Processor Code"
sources={{
light: "img/flow_runner_code.png",
dark: "img/flow_runner_code.png",
}}
style={{
maxWidth: "100%",
@ -353,6 +355,7 @@ Done! This is what our script and custom component looks like:
alt="Document Processor Component"
sources={{
light: "img/flow_runner.png",
dark: "img/flow_runner.png",
}}
style={{
width: "40%",

1
docs/docs/examples/how-upload-examples.mdx
View file

@ -12,6 +12,7 @@ Langflow Examples is a repository on [GitHub](https://github.com/logspace-ai/lan
alt="Docusaurus themed image"
sources={{
light: "img/community-examples.png",
dark: "img/community-examples.png",
}}
style={{ width: "100%" }}
/>

3
docs/docs/examples/midjourney-prompt-chain.mdx
View file

@ -32,6 +32,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/midjourney-prompt-chain.png",
dark: "img/midjourney-prompt-chain.png",
}}
/>
@ -40,6 +41,6 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`ConversationSummaryMemory`](https://python.langchain.com/docs/modules/memory/how_to/summary)
- [`ConversationSummaryMemory`](https://python.langchain.com/docs/modules/memory/types/summary)
</Admonition>

15
docs/docs/examples/multiple-vectorstores.mdx
View file

@ -24,7 +24,7 @@ https://pt.wikipedia.org/wiki/Harry_Potter
<Admonition type="info">
Learn more about Multiple Vector Stores
[here](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore?highlight=Multiple%20Vector%20Stores#multiple-vectorstores).
[here](https://python.langchain.com/docs/modules/data_connection/vectorstores/).
</Admonition>
## ⛓️ Langflow Example
@ -37,6 +37,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/multiple-vectorstores.png",
dark: "img/multiple-vectorstores.png",
}}
/>
@ -44,14 +45,14 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`WebBaseLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/web_base)
- [`TextLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/integrations/unstructured_file)
- [`WebBaseLoader`](https://python.langchain.com/docs/integrations/document_loaders/web_base)
- [`TextLoader`](https://python.langchain.com/docs/modules/data_connection/document_loaders/)
- [`CharacterTextSplitter`](https://python.langchain.com/docs/modules/data_connection/document_transformers/text_splitters/character_text_splitter)
- [`OpenAIEmbedding`](https://python.langchain.com/docs/modules/data_connection/text_embedding/integrations/openai)
- [`Chroma`](https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/chroma)
- [`OpenAIEmbedding`](https://python.langchain.com/docs/integrations/text_embedding/openai)
- [`Chroma`](https://python.langchain.com/docs/integrations/vectorstores/chroma)
- [`VectorStoreInfo`](https://python.langchain.com/docs/modules/data_connection/vectorstores/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`VectorStoreRouterToolkit`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
- [`VectorStoreRouterAgent`](https://python.langchain.com/docs/modules/agents/toolkits/vectorstore)
- [`VectorStoreRouterToolkit`](https://js.langchain.com/docs/modules/agents/tools/how_to/agents_with_vectorstores)
- [`VectorStoreRouterAgent`](https://js.langchain.com/docs/modules/agents/tools/how_to/agents_with_vectorstores)
</Admonition>

5
docs/docs/examples/python-function.mdx
View file

@ -28,7 +28,7 @@ The `AgentInitializer` component is a quick way to construct an agent from the m
<Admonition type="info">
The `PythonFunction` is a custom component that uses the LangChain 🦜🔗 tool
decorator. Learn more about it
[here](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools).
[here](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
</Admonition>
## ⛓️ Langflow Example
@ -41,6 +41,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/python-function.png",
dark: "img/python-function.png",
}}
/>
@ -48,7 +49,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
<Admonition type="note" title="LangChain Components 🦜🔗">
- [`PythonFunctionTool`](https://python.langchain.com/docs/modules/agents/tools/how_to/custom_tools)
- [`PythonFunctionTool`](https://python.langchain.com/docs/modules/agents/tools/custom_tools)
- [`ChatOpenAI`](https://python.langchain.com/docs/modules/model_io/models/chat/integrations/openai)
- [`AgentInitializer`](https://python.langchain.com/docs/modules/agents/)

5
docs/docs/examples/serp-api-tool.mdx
View file

@ -22,7 +22,7 @@ The `ZeroShotAgent` takes the `LLMChain` and the `Search` tool as inputs, using
<Admonition type="info">
Learn more about the Serp API
[here](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi).
[here](https://python.langchain.com/docs/integrations/providers/serpapi ).
</Admonition>
## ⛓️ Langflow Example
@ -35,6 +35,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/serp-api-tool.png",
dark: "img/serp-api-tool.png",
}}
/>
@ -45,7 +46,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
- [`ZeroShotPrompt`](https://python.langchain.com/docs/modules/model_io/prompts/prompt_templates/)
- [`OpenAI`](https://python.langchain.com/docs/modules/model_io/models/llms/integrations/openai)
- [`LLMChain`](https://python.langchain.com/docs/modules/chains/foundational/llm_chain)
- [`Search`](https://python.langchain.com/docs/modules/agents/tools/integrations/serpapi)
- [`Search`](https://python.langchain.com/docs/integrations/providers/serpapi)
- [`ZeroShotAgent`](https://python.langchain.com/docs/modules/agents/how_to/custom_mrkl_agent)
</Admonition>

1
docs/docs/getting-started/creating-flows.mdx
View file

@ -13,6 +13,7 @@ Creating flows with Langflow is easy. Drag sidebar components onto the canvas an
alt="Docusaurus themed image"
sources={{
light: "img/langflow_canvas.png",
dark: "img/langflow_canvas.png"
}}
/>

1
docs/docs/getting-started/hugging-face-spaces.mdx
View file

@ -12,6 +12,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/hugging-face.png",
dark: "img/hugging-face.png",
}}
style={{ width: "100%" }}
/>

1
docs/docs/guidelines/api.mdx
View file

@ -17,6 +17,7 @@ Langflow offers an API Key functionality that allows users to access their indiv
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/api-key.png"),
dark: useBaseUrl("img/api-key.png"),
}}
style={{ width: "50%", maxWidth: "600px", margin: "0 auto" }}
/>

4
docs/docs/guidelines/chat-interface.mdx
View file

@ -13,6 +13,7 @@ Langflow’s chat interface provides a user-friendly experience and functionalit
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/chat_interface.png"),
dark: useBaseUrl("img/chat_interface.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -25,6 +26,7 @@ Notice that editing variables in the chat interface take place temporarily and w
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/chat_interface2.png"),
dark: useBaseUrl("img/chat_interface2.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -36,6 +38,7 @@ To view the complete prompt in its original, structured format, click the "Displ
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/chat_interface3.png"),
dark: useBaseUrl("img/chat_interface3.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -47,6 +50,7 @@ In the chat interface, you can redefine which variable should be interpreted as
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/chat_interface4.png"),
dark: useBaseUrl("img/chat_interface4.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>

2
docs/docs/guidelines/chat-widget.mdx
View file

@ -38,6 +38,7 @@ import Admonition from "@theme/Admonition";
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/widget-sidebar.png"),
dark: useBaseUrl("img/widget-sidebar.png"),
}}
style={{ width: "50%", maxWidth: "600px", margin: "0 auto" }}
/>
@ -53,6 +54,7 @@ import Admonition from "@theme/Admonition";
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/widget-code.png"),
dark: useBaseUrl("img/widget-code.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>

1
docs/docs/guidelines/components.mdx
View file

@ -30,6 +30,7 @@ Components are the building blocks of the flows. They are made of inputs, output
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/single-compenent.png"),
dark: useBaseUrl("img/single-compenent.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>

3
docs/docs/guidelines/custom-component.mdx
View file

@ -63,6 +63,7 @@ class DocumentProcessor(CustomComponent):
alt="Document Processor Component"
sources={{
light: "img/document_processor.png",
dark: "img/document_processor.png",
}}
style={{
margin: "0 auto",
@ -330,6 +331,7 @@ All done! This is what our script and brand-new custom component look like:
alt="Document Processor Code"
sources={{
light: "img/document_processor_code.png",
dark: "img/document_processor_code.png",
}}
style={{
maxWidth: "100%",
@ -344,6 +346,7 @@ All done! This is what our script and brand-new custom component look like:
alt="Document Processor Component"
sources={{
light: "img/document_processor.png",
dark: "img/document_processor.png",
}}
style={{
width: "40%",

1
docs/docs/guidelines/features.mdx
View file

@ -18,6 +18,7 @@ import Admonition from "@theme/Admonition";
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/features.png"),
dark: useBaseUrl("img/features.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>

4
docs/docs/guidelines/login.mdx
View file

@ -86,6 +86,7 @@ With _`LANGFLOW_AUTO_LOGIN`_ set to _`False`_, Langflow requires users to sign u
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/sign-up.png"),
dark: useBaseUrl("img/sign-up.png"),
}}
style={{ width: "50%", maxWidth: "600px", margin: "0 auto" }}
/>
@ -102,6 +103,7 @@ Users can change their profile settings by clicking on the profile icon in the t
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/my-account.png"),
dark: useBaseUrl("img/my-account.png"),
}}
style={{ width: "50%", maxWidth: "600px", margin: "0 auto" }}
/>
@ -112,6 +114,7 @@ By clicking on **Profile Settings**, the user is taken to the profile settings p
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/profile-settings.png"),
dark: useBaseUrl("img/profile-settings.png"),
}}
style={{ maxWidth: "600px", margin: "0 auto" }}
/>
@ -122,6 +125,7 @@ By clicking on **Admin Page**, the superuser is taken to the admin page, where t
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/admin-page.png"),
dark: useBaseUrl("img/admin-page.png"),
}}
style={{ maxWidth: "600px", margin: "0 auto" }}

5
docs/docs/guidelines/prompt-customization.mdx
View file

@ -13,6 +13,7 @@ The prompt template allows users to create prompts and define variables that pro
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/prompt_customization.png"),
dark: useBaseUrl("img/prompt_customization.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -25,6 +26,7 @@ Variables can be used to define instructions, questions, context, inputs, or exa
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/prompt_customization2.png"),
dark: useBaseUrl("img/prompt_customization2.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -37,6 +39,7 @@ Once inserted, these variables are immediately recognized as new fields in the p
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/prompt_customization3.png"),
dark: useBaseUrl("img/prompt_customization3.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -49,6 +52,7 @@ You can also use documents or output parsers as prompt variables. By plugging th
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/prompt_customization4.png"),
dark: useBaseUrl("img/prompt_customization4.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>
@ -63,6 +67,7 @@ If working with an interactive (chat-like) flow, remember to keep one of the inp
alt="Docusaurus themed image"
sources={{
light: useBaseUrl("img/prompt_customization5.png"),
dark: useBaseUrl("img/prompt_customization5.png"),
}}
style={{ width: "100%", maxWidth: "800px", margin: "0 auto" }}
/>

1
docs/docs/index.mdx
View file

@ -12,6 +12,7 @@ import ZoomableImage from "/src/theme/ZoomableImage.js";
alt="Docusaurus themed image"
sources={{
light: "img/new_langflow_demo.gif",
dark: "img/new_langflow_demo.gif",
}}
style={{ width: "100%" }}
/>

BIN
docs/static/videos/langflow_api.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_build.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_collection.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_collection_example.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_fork.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_parameters.mp4 vendored
View file

Binary file not shown.

BIN
docs/static/videos/langflow_widget.mp4 vendored
View file

Binary file not shown.