Please contact the owner of the site that linked you to the original URL and let them know their link is broken.
diff --git a/docs/assets/images/agent-zero-01-5977b5b913065e4d018f6154a23ee527.png b/docs/assets/images/agent-zero-01-5977b5b913065e4d018f6154a23ee527.png
new file mode 100644
index 0000000..7b265ae
Binary files /dev/null and b/docs/assets/images/agent-zero-01-5977b5b913065e4d018f6154a23ee527.png differ
diff --git a/docs/assets/images/agent-zero-02-7043b5f92118e22f7fc418c131c35965.png b/docs/assets/images/agent-zero-02-7043b5f92118e22f7fc418c131c35965.png
new file mode 100644
index 0000000..0052944
Binary files /dev/null and b/docs/assets/images/agent-zero-02-7043b5f92118e22f7fc418c131c35965.png differ
diff --git a/docs/assets/images/agent-zero-03-b5ebd8903dbb3ebdc2a9b01b9b8d522e.png b/docs/assets/images/agent-zero-03-b5ebd8903dbb3ebdc2a9b01b9b8d522e.png
new file mode 100644
index 0000000..d226a20
Binary files /dev/null and b/docs/assets/images/agent-zero-03-b5ebd8903dbb3ebdc2a9b01b9b8d522e.png differ
diff --git a/docs/assets/images/agent-zero-04-169d90a36a516babfd2025f500ce5cc9.png b/docs/assets/images/agent-zero-04-169d90a36a516babfd2025f500ce5cc9.png
new file mode 100644
index 0000000..d6997d3
Binary files /dev/null and b/docs/assets/images/agent-zero-04-169d90a36a516babfd2025f500ce5cc9.png differ
diff --git a/docs/assets/images/agent-zero-05-8f884d2fdad5e381880fb9fde3c1c14b.png b/docs/assets/images/agent-zero-05-8f884d2fdad5e381880fb9fde3c1c14b.png
new file mode 100644
index 0000000..f5431cc
Binary files /dev/null and b/docs/assets/images/agent-zero-05-8f884d2fdad5e381880fb9fde3c1c14b.png differ
diff --git a/docs/assets/images/agent-zero-06-865e4e1235f0eceec9395c8d85a01db9.png b/docs/assets/images/agent-zero-06-865e4e1235f0eceec9395c8d85a01db9.png
new file mode 100644
index 0000000..a81c29c
Binary files /dev/null and b/docs/assets/images/agent-zero-06-865e4e1235f0eceec9395c8d85a01db9.png differ
diff --git a/docs/assets/images/agent-zero-08-f040087da5fa37caa0fa94399e22e464.png b/docs/assets/images/agent-zero-08-f040087da5fa37caa0fa94399e22e464.png
new file mode 100644
index 0000000..d0b7e2e
Binary files /dev/null and b/docs/assets/images/agent-zero-08-f040087da5fa37caa0fa94399e22e464.png differ
diff --git a/docs/assets/images/agent-zero-09-f745e0628a6fafe58231ca5987e2bad3.png b/docs/assets/images/agent-zero-09-f745e0628a6fafe58231ca5987e2bad3.png
new file mode 100644
index 0000000..a6d7bae
Binary files /dev/null and b/docs/assets/images/agent-zero-09-f745e0628a6fafe58231ca5987e2bad3.png differ
diff --git a/docs/assets/js/2689485b.ba49ef37.js b/docs/assets/js/2689485b.ba49ef37.js
new file mode 100644
index 0000000..72df7ff
--- /dev/null
+++ b/docs/assets/js/2689485b.ba49ef37.js
@@ -0,0 +1 @@
+"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[31],{1927:(e,n,t)=>{t.r(n),t.d(n,{assets:()=>d,contentTitle:()=>r,default:()=>u,frontMatter:()=>s,metadata:()=>c,toc:()=>l});var a=t(4848),i=t(8453);const s={sidebar_position:9},r="Agent Zero",c={id:"user-guide/openai-api/agent-zero",title:"Agent Zero",description:"Agent Zero is a general purpose AI agent application. You can simply ask it to accomplish tasks on the command line.",source:"@site/docs/user-guide/openai-api/agent-zero.md",sourceDirName:"user-guide/openai-api",slug:"/user-guide/openai-api/agent-zero",permalink:"/docs/user-guide/openai-api/agent-zero",draft:!1,unlisted:!1,editUrl:"https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/docs/user-guide/openai-api/agent-zero.md",tags:[],version:"current",sidebarPosition:9,frontMatter:{sidebar_position:9},sidebar:"tutorialSidebar",previous:{title:"LangChain",permalink:"/docs/user-guide/openai-api/langchain"},next:{title:"Long-term memory and knowledge",permalink:"/docs/category/long-term-memory-and-knowledge"}},d={},l=[{value:"Prerequisites",id:"prerequisites",level:2},{value:"Configure the agent",id:"configure-the-agent",level:2},{value:"Run the agent",id:"run-the-agent",level:2},{value:"Example 1",id:"example-1",level:3},{value:"Example 2",id:"example-2",level:3},{value:"Example 3",id:"example-3",level:3},{value:"Example 4",id:"example-4",level:3},{value:"Example 5",id:"example-5",level:3}];function o(e){const n={a:"a",blockquote:"blockquote",code:"code",h1:"h1",h2:"h2",h3:"h3",img:"img",li:"li",p:"p",pre:"pre",strong:"strong",ul:"ul",...(0,i.R)(),...e.components};return(0,a.jsxs)(a.Fragment,{children:[(0,a.jsx)(n.h1,{id:"agent-zero",children:"Agent Zero"}),"\n",(0,a.jsxs)(n.p,{children:[(0,a.jsx)(n.a,{href:"https://github.com/frdel/agent-zero",children:"Agent Zero"})," is a general purpose AI agent application. You can simply ask it to accomplish tasks on the command line.\nIt is designed to be dynamic, organically growing, and learning as users use it. It leverages your computer as a tool to accomplish your tasks."]}),"\n",(0,a.jsx)(n.h2,{id:"prerequisites",children:"Prerequisites"}),"\n",(0,a.jsxs)(n.p,{children:["Follow ",(0,a.jsx)(n.a,{href:"/docs/user-guide/openai-api/intro",children:"this guide"})," to run an open-source LLM locally. In this example, we will use ",(0,a.jsx)(n.a,{href:"https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF",children:"Llama-3.1-8B"})," as the chat model and nomic-text-embed as the embedding model."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -LO https://huggingface.co/second-state/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf\ncurl -LO https://huggingface.co/second-state/Nomic-embed-text-v1.5-Embedding-GGUF/resolve/main/nomic-embed-text-v1.5-Q5_K_M.gguf\n"})}),"\n",(0,a.jsxs)(n.p,{children:["Then start the LlamaEdge API server with the Llama-3.1-8B model ",(0,a.jsx)(n.code,{children:"Meta-Llama-3.1-8B-Instruct-Q5_K_M"})," and nomic embed model ",(0,a.jsx)(n.code,{children:"nomic-embed-text-v1.5.f16"}),"."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"wasmedge --dir .:. \\\n --nn-preload default:GGML:AUTO:Meta-Llama-3.1-8B-Instruct-Q5_K_M.gguf \\\n --nn-preload embedding:GGML:AUTO:nomic-embed-text-v1.5.f16.gguf \\\n llama-api-server.wasm \\\n --model-alias default,embedding \\\n --model-name Meta-Llama-3.1-8B-Instruct-Q5_K_M,nomic-embed-text-v1.5.f16 \\\n --prompt-template llama-3-chat,embedding \\\n --batch-size 128,8192 \\\n --ctx-size 32768,8192\n"})}),"\n",(0,a.jsxs)(n.blockquote,{children:["\n",(0,a.jsx)(n.p,{children:"You can also start a Gaia node for the Llama-3.1-8B model and the nomic embed model. You can then use the node's API URL endpoint and model name in this app."}),"\n"]}),"\n",(0,a.jsxs)(n.p,{children:[(0,a.jsx)(n.strong,{children:"You will also need to make sure your Docker engine is running."})," Because the Agent Zero framework will leverage Docker to execute the generated code."]}),"\n",(0,a.jsx)(n.h2,{id:"configure-the-agent",children:"Configure the agent"}),"\n",(0,a.jsx)(n.p,{children:"First, we will need to get the source code of a Gaia-compatible version of Agent Zero."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"git clone https://github.com/JYC0413/agent-zero-gaia.git\ncd agent-zero-gaia\n"})}),"\n",(0,a.jsx)(n.p,{children:"Then, let's install the required dependencies."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"pip install -r requirements.txt\n"})}),"\n",(0,a.jsx)(n.p,{children:"Next, let's configure the gaia node and other parameters."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"cp example.env .env\n"})}),"\n",(0,a.jsx)(n.p,{children:"You will need to configure the following items:"}),"\n",(0,a.jsxs)(n.ul,{children:["\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"CHAT_MODEL_BASE_URL"}),": URL for the LLM API base URL. E.g., ",(0,a.jsx)(n.code,{children:"http://localhost:8080/v1"})]}),"\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"CHAT_MODEL_NAME"}),": Name of the chat model to be used. E.g., ",(0,a.jsx)(n.code,{children:"Meta-Llama-3.1-8B-Instruct-Q5_K_M"})]}),"\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"CHAT_API_KEY"}),": An API key to access the LLM services. You can enter several random characters here. E.g., ",(0,a.jsx)(n.code,{children:"LlamaEdge"})]}),"\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"EMBEDDING_MODEL_BASE_URL"}),": URL for the embedding model API base URL. E.g., ",(0,a.jsx)(n.code,{children:"http://localhost:8080/v1"})]}),"\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"EMBEDDING_MODEL_NAME"}),": Name of the embedding model name. E.g., ",(0,a.jsx)(n.code,{children:"nomic-embed-text-v1.5.f16"})]}),"\n",(0,a.jsxs)(n.li,{children:[(0,a.jsx)(n.code,{children:"EMBEDDING_API_KEY"}),": An API key to access the embedding services. You can enter several random characters here. E.g., ",(0,a.jsx)(n.code,{children:"LlamaEdge"})]}),"\n"]}),"\n",(0,a.jsx)(n.h2,{id:"run-the-agent",children:"Run the agent"}),"\n",(0,a.jsx)(n.p,{children:"Finally, let's run the Agent Zero application backed by the Llama 3.1 8b model."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"python main.py\n"})}),"\n",(0,a.jsx)(n.p,{children:"You can interact with Agent Zero via the command line. You will see the Agent Zero framework will call the related tools and execute some code to complete your task."}),"\n",(0,a.jsx)(n.h3,{id:"example-1",children:"Example 1"}),"\n",(0,a.jsx)(n.p,{children:"Get time in Berlin and Seattle"}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(773).A+"",width:"1570",height:"598"})}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(2942).A+"",width:"1421",height:"515"})}),"\n",(0,a.jsx)(n.p,{children:"Save the above result in a file using node.js"}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(2439).A+"",width:"1452",height:"942"})}),"\n",(0,a.jsx)(n.h3,{id:"example-2",children:"Example 2"}),"\n",(0,a.jsxs)(n.p,{children:["Install ",(0,a.jsx)(n.a,{href:"https://midnight-commander.org/",children:"mc"}),". do not use ",(0,a.jsx)(n.code,{children:"-y"})," flag"]}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(296).A+"",width:"964",height:"549"})}),"\n",(0,a.jsx)(n.h3,{id:"example-3",children:"Example 3"}),"\n",(0,a.jsxs)(n.p,{children:["Run ",(0,a.jsx)(n.code,{children:"top"}),", show the system load"]}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(1425).A+"",width:"917",height:"525"})}),"\n",(0,a.jsx)(n.h3,{id:"example-4",children:"Example 4"}),"\n",(0,a.jsx)(n.p,{children:"Memorize my openai api key - 563434643464"}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(346).A+"",width:"996",height:"676"})}),"\n",(0,a.jsx)(n.h3,{id:"example-5",children:"Example 5"}),"\n",(0,a.jsxs)(n.p,{children:["Extract an mp3 audio track from a mp4 video file using ffmpeg. You will need to put an mp4 file (e.g., ",(0,a.jsx)(n.code,{children:"video.mp4"}),") into the ",(0,a.jsx)(n.code,{children:"work_dir"})," and tell the agent about it."]}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(5907).A+"",width:"244",height:"276"})}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(9988).A+"",width:"886",height:"202"})}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:t(1117).A+"",width:"1930",height:"1040"})})]})}function u(e={}){const{wrapper:n}={...(0,i.R)(),...e.components};return n?(0,a.jsx)(n,{...e,children:(0,a.jsx)(o,{...e})}):o(e)}},773:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-01-5977b5b913065e4d018f6154a23ee527.png"},2942:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-02-7043b5f92118e22f7fc418c131c35965.png"},2439:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-03-b5ebd8903dbb3ebdc2a9b01b9b8d522e.png"},296:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-04-169d90a36a516babfd2025f500ce5cc9.png"},1425:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-05-8f884d2fdad5e381880fb9fde3c1c14b.png"},346:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-06-865e4e1235f0eceec9395c8d85a01db9.png"},5907:(e,n,t)=>{t.d(n,{A:()=>a});const a="data:image/png;base64,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"},9988:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-08-f040087da5fa37caa0fa94399e22e464.png"},1117:(e,n,t)=>{t.d(n,{A:()=>a});const a=t.p+"assets/images/agent-zero-09-f745e0628a6fafe58231ca5987e2bad3.png"},8453:(e,n,t)=>{t.d(n,{R:()=>r,x:()=>c});var a=t(6540);const i={},s=a.createContext(i);function r(e){const n=a.useContext(s);return a.useMemo((function(){return"function"==typeof e?e(n):{...n,...e}}),[n,e])}function c(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(i):e.components||i:r(e.components),a.createElement(s.Provider,{value:n},e.children)}}}]);
\ No newline at end of file
diff --git a/docs/assets/js/89b72d9d.85a3ad7b.js b/docs/assets/js/89b72d9d.85a3ad7b.js
deleted file mode 100644
index 3e18d1b..0000000
--- a/docs/assets/js/89b72d9d.85a3ad7b.js
+++ /dev/null
@@ -1 +0,0 @@
-"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[74],{9412:(e,n,t)=>{t.r(n),t.d(n,{assets:()=>r,contentTitle:()=>o,default:()=>h,frontMatter:()=>s,metadata:()=>l,toc:()=>c});var a=t(4848),i=t(8453);const s={sidebar_position:7},o="LangChain",l={id:"user-guide/openai-api/langchain",title:"LangChain",description:"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain.",source:"@site/docs/user-guide/openai-api/langchain.md",sourceDirName:"user-guide/openai-api",slug:"/user-guide/openai-api/langchain",permalink:"/docs/user-guide/openai-api/langchain",draft:!1,unlisted:!1,editUrl:"https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/docs/user-guide/openai-api/langchain.md",tags:[],version:"current",sidebarPosition:7,frontMatter:{sidebar_position:7},sidebar:"tutorialSidebar",previous:{title:"Translation Agent",permalink:"/docs/user-guide/openai-api/translation-agent"},next:{title:"Long-term memory and knowledge",permalink:"/docs/category/long-term-memory-and-knowledge"}},r={},c=[{value:"Build the client app using Langchian with vector DB support",id:"build-the-client-app-using-langchian-with-vector-db-support",level:3},{value:"Build an OpenAI compatible API server for the open source LLM using LlamaEdge",id:"build-an-openai-compatible-api-server-for-the-open-source-llm-using-llamaedge",level:3},{value:"Connect your self-hosted LLMs with the chatbot web app",id:"connect-your-self-hosted-llms-with-the-chatbot-web-app",level:3},{value:"What\u2019s next?",id:"whats-next",level:3}];function d(e){const n={a:"a",blockquote:"blockquote",code:"code",h1:"h1",h3:"h3",img:"img",p:"p",pre:"pre",...(0,i.R)(),...e.components};return(0,a.jsxs)(a.Fragment,{children:[(0,a.jsx)(n.h1,{id:"langchain",children:"LangChain"}),"\n",(0,a.jsx)(n.p,{children:"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain."}),"\n",(0,a.jsxs)(n.blockquote,{children:["\n",(0,a.jsxs)(n.p,{children:["LlamaEdge has ",(0,a.jsx)(n.a,{href:"https://twitter.com/realwasmedge/status/1742437253107130552",children:"recently became"})," an official inference backend for LangChain, allowing LangChain applications to run open source LLMs on heterogeneous GPU devices."]}),"\n"]}),"\n",(0,a.jsx)(n.h3,{id:"build-the-client-app-using-langchian-with-vector-db-support",children:"Build the client app using Langchian with vector DB support"}),"\n",(0,a.jsx)(n.p,{children:"First, let's build a chatbot web app using Langchain. This part will be built in Python. The app includes uploading file and attaches the Chroma DB and the gpt4all embedding algorithms."}),"\n",(0,a.jsxs)(n.p,{children:["To quick start, fork or clone ",(0,a.jsx)(n.a,{href:"https://github.com/second-state/wasm-llm",children:"the wasm-llm repo"})," and open the wasm-bot folder."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"git clone https://github.com/second-state/wasm-llm.git\ncd wasm-llm/wasm-rag-service\n"})}),"\n",(0,a.jsx)(n.p,{children:"Next, let\u2019s install the required python dependencies for this program. We will use conda to control the version and environment."}),"\n",(0,a.jsxs)(n.p,{children:["Follow the ",(0,a.jsx)(n.a,{href:"https://docs.conda.io/projects/miniconda/en/latest/#quick-command-line-install",children:"miniconda installation instruction"})," to install mini conda your own machine. After that, create a conda environment for the chatbot web app. Let\u2019s use chatbot as the name."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"conda create -n wasm-rag python=3.11\nconda activate wasm-rag\n"})}),"\n",(0,a.jsxs)(n.p,{children:["Then, you may notice that your terminal has entered the ",(0,a.jsx)(n.code,{children:"chatbot"})," environment. Let\u2019s ",(0,a.jsx)(n.a,{href:"https://github.com/second-state/wasm-llm/blob/main/wasm-bot/requirements.txt",children:"install the dependencies for this chatbot app"}),". All the dependencies are included in the ",(0,a.jsx)(n.code,{children:"requirements.txt"}),"."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"pip install -r requirements.txt\n"})}),"\n",(0,a.jsx)(n.p,{children:"With all dependencies installed, then we can execute the chatbot app."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"streamlit run app.py\n"})}),"\n",(0,a.jsx)(n.p,{children:"If everything goes well, you will see the following messages on your terminal. In the meanwhile, a web page will be opened in your browser."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"You can now view your Streamlit app in your browser.\nLocal URL: http://localhost:8501\nNetwork URL: http://192.168.0.103:8501\n"})}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:"https://github.com/LlamaEdge/docs/assets/45785633/af418d8e-9377-4613-b976-4ed3bec1836c",alt:"image"})}),"\n",(0,a.jsx)(n.p,{children:"Now, we have completed the first part \u2014 a RAG client app waiting for a LLM backend to answer user\u2019s question."}),"\n",(0,a.jsx)(n.h3,{id:"build-an-openai-compatible-api-server-for-the-open-source-llm-using-llamaedge",children:"Build an OpenAI compatible API server for the open source LLM using LlamaEdge"}),"\n",(0,a.jsx)(n.p,{children:"Let\u2019s build a API server for the open source LLM with WasmEdge."}),"\n",(0,a.jsx)(n.p,{children:"First, install WasmEdge runtime with one single command line."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | bash -s -- --plugin wasi_nn-ggml\n"})}),"\n",(0,a.jsx)(n.p,{children:"Second, download the model file in GGUF file. Here, I use llama2-7b as an example. We have tried several LLMs and concluded that Llama2-7B is the beat for RAG applications."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -LO https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/resolve/main/Llama-2-7b-chat-hf-Q5_K_M.gguf\n"})}),"\n",(0,a.jsx)(n.p,{children:"Third, download an API server app. It is a cross-platform portable Wasm app that can run on many CPU and GPU devices."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -LO https://github.com/second-state/LlamaEdge/releases/latest/download/llama-api-server.wasm\n"})}),"\n",(0,a.jsx)(n.p,{children:"Finally, use the following command lines to start an API server for the model. If you have did the above steps, just run the follwing command line."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-7b-chat-hf-Q5_K_M.gguf llama-api-server.wasm -p llama-2-chat -c 4096\n"})}),"\n",(0,a.jsx)(n.p,{children:"If everything goes well, the following information will be printed on the terminal."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"[INFO] Socket address: 0.0.0.0:8080\n[INFO] Model name: default\n[INFO] Model alias: default\n[INFO] Prompt context size: 512\n[INFO] Number of tokens to predict: 1024\n[INFO] Number of layers to run on the GPU: 100\n[INFO] Batch size for prompt processing: 512\n[INFO] Temperature for sampling: 0.8\n[INFO] Penalize repeat sequence of tokens: 1.1\n[INFO] Prompt template: HumanAssistant\n[INFO] Log prompts: false\n[INFO] Log statistics: false\n[INFO] Log all information: false\n[INFO] Starting server ...\nggml_init_cublas: GGML_CUDA_FORCE_MMQ: no\nggml_init_cublas: CUDA_USE_TENSOR_CORES: yes\nggml_init_cublas: found 1 CUDA devices:\n Device 0: Orin, compute capability 8.7, VMM: yes\n[INFO] Plugin version: b1953 (commit 6f9939d1)\n[INFO] Listening on http://0.0.0.0:8080\n"})}),"\n",(0,a.jsx)(n.p,{children:"Now the Llama2-7B-Chat model is hosted at the port of 8080."}),"\n",(0,a.jsx)(n.h3,{id:"connect-your-self-hosted-llms-with-the-chatbot-web-app",children:"Connect your self-hosted LLMs with the chatbot web app"}),"\n",(0,a.jsx)(n.p,{children:"Go back to the web page opened in the first step. Click Use cusom service on the bottom left of page and click the Connect button.\nThen you will see a section to upload your own data locally. Upload a pdf file here. When the uploading process is done, the bot will send you a message: \u201cHello \ud83d\udc4b, how can I help you?\u201d, which is a ready sign."}),"\n",(0,a.jsx)(n.p,{children:"Ask a question, and the bot will reply to you based on the file you uploaded."}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:"https://github.com/LlamaEdge/docs/assets/45785633/0b5273f6-7edd-4fcf-b917-c5931609c5db",alt:"image"})}),"\n",(0,a.jsx)(n.h3,{id:"whats-next",children:"What\u2019s next?"}),"\n",(0,a.jsx)(n.p,{children:"We will introduce you how to build such a client-side RAG app with OpenWebui"})]})}function h(e={}){const{wrapper:n}={...(0,i.R)(),...e.components};return n?(0,a.jsx)(n,{...e,children:(0,a.jsx)(d,{...e})}):d(e)}},8453:(e,n,t)=>{t.d(n,{R:()=>o,x:()=>l});var a=t(6540);const i={},s=a.createContext(i);function o(e){const n=a.useContext(s);return a.useMemo((function(){return"function"==typeof e?e(n):{...n,...e}}),[n,e])}function l(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(i):e.components||i:o(e.components),a.createElement(s.Provider,{value:n},e.children)}}}]);
\ No newline at end of file
diff --git a/docs/assets/js/89b72d9d.c29812d1.js b/docs/assets/js/89b72d9d.c29812d1.js
new file mode 100644
index 0000000..35a673c
--- /dev/null
+++ b/docs/assets/js/89b72d9d.c29812d1.js
@@ -0,0 +1 @@
+"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[74],{9412:(e,n,t)=>{t.r(n),t.d(n,{assets:()=>r,contentTitle:()=>o,default:()=>h,frontMatter:()=>s,metadata:()=>l,toc:()=>c});var a=t(4848),i=t(8453);const s={sidebar_position:7},o="LangChain",l={id:"user-guide/openai-api/langchain",title:"LangChain",description:"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain.",source:"@site/docs/user-guide/openai-api/langchain.md",sourceDirName:"user-guide/openai-api",slug:"/user-guide/openai-api/langchain",permalink:"/docs/user-guide/openai-api/langchain",draft:!1,unlisted:!1,editUrl:"https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/docs/user-guide/openai-api/langchain.md",tags:[],version:"current",sidebarPosition:7,frontMatter:{sidebar_position:7},sidebar:"tutorialSidebar",previous:{title:"Translation Agent",permalink:"/docs/user-guide/openai-api/translation-agent"},next:{title:"Agent Zero",permalink:"/docs/user-guide/openai-api/agent-zero"}},r={},c=[{value:"Build the client app using Langchian with vector DB support",id:"build-the-client-app-using-langchian-with-vector-db-support",level:3},{value:"Build an OpenAI compatible API server for the open source LLM using LlamaEdge",id:"build-an-openai-compatible-api-server-for-the-open-source-llm-using-llamaedge",level:3},{value:"Connect your self-hosted LLMs with the chatbot web app",id:"connect-your-self-hosted-llms-with-the-chatbot-web-app",level:3},{value:"What\u2019s next?",id:"whats-next",level:3}];function d(e){const n={a:"a",blockquote:"blockquote",code:"code",h1:"h1",h3:"h3",img:"img",p:"p",pre:"pre",...(0,i.R)(),...e.components};return(0,a.jsxs)(a.Fragment,{children:[(0,a.jsx)(n.h1,{id:"langchain",children:"LangChain"}),"\n",(0,a.jsx)(n.p,{children:"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain."}),"\n",(0,a.jsxs)(n.blockquote,{children:["\n",(0,a.jsxs)(n.p,{children:["LlamaEdge has ",(0,a.jsx)(n.a,{href:"https://twitter.com/realwasmedge/status/1742437253107130552",children:"recently became"})," an official inference backend for LangChain, allowing LangChain applications to run open source LLMs on heterogeneous GPU devices."]}),"\n"]}),"\n",(0,a.jsx)(n.h3,{id:"build-the-client-app-using-langchian-with-vector-db-support",children:"Build the client app using Langchian with vector DB support"}),"\n",(0,a.jsx)(n.p,{children:"First, let's build a chatbot web app using Langchain. This part will be built in Python. The app includes uploading file and attaches the Chroma DB and the gpt4all embedding algorithms."}),"\n",(0,a.jsxs)(n.p,{children:["To quick start, fork or clone ",(0,a.jsx)(n.a,{href:"https://github.com/second-state/wasm-llm",children:"the wasm-llm repo"})," and open the wasm-bot folder."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"git clone https://github.com/second-state/wasm-llm.git\ncd wasm-llm/wasm-rag-service\n"})}),"\n",(0,a.jsx)(n.p,{children:"Next, let\u2019s install the required python dependencies for this program. We will use conda to control the version and environment."}),"\n",(0,a.jsxs)(n.p,{children:["Follow the ",(0,a.jsx)(n.a,{href:"https://docs.conda.io/projects/miniconda/en/latest/#quick-command-line-install",children:"miniconda installation instruction"})," to install mini conda your own machine. After that, create a conda environment for the chatbot web app. Let\u2019s use chatbot as the name."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"conda create -n wasm-rag python=3.11\nconda activate wasm-rag\n"})}),"\n",(0,a.jsxs)(n.p,{children:["Then, you may notice that your terminal has entered the ",(0,a.jsx)(n.code,{children:"chatbot"})," environment. Let\u2019s ",(0,a.jsx)(n.a,{href:"https://github.com/second-state/wasm-llm/blob/main/wasm-bot/requirements.txt",children:"install the dependencies for this chatbot app"}),". All the dependencies are included in the ",(0,a.jsx)(n.code,{children:"requirements.txt"}),"."]}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"pip install -r requirements.txt\n"})}),"\n",(0,a.jsx)(n.p,{children:"With all dependencies installed, then we can execute the chatbot app."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"streamlit run app.py\n"})}),"\n",(0,a.jsx)(n.p,{children:"If everything goes well, you will see the following messages on your terminal. In the meanwhile, a web page will be opened in your browser."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"You can now view your Streamlit app in your browser.\nLocal URL: http://localhost:8501\nNetwork URL: http://192.168.0.103:8501\n"})}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:"https://github.com/LlamaEdge/docs/assets/45785633/af418d8e-9377-4613-b976-4ed3bec1836c",alt:"image"})}),"\n",(0,a.jsx)(n.p,{children:"Now, we have completed the first part \u2014 a RAG client app waiting for a LLM backend to answer user\u2019s question."}),"\n",(0,a.jsx)(n.h3,{id:"build-an-openai-compatible-api-server-for-the-open-source-llm-using-llamaedge",children:"Build an OpenAI compatible API server for the open source LLM using LlamaEdge"}),"\n",(0,a.jsx)(n.p,{children:"Let\u2019s build a API server for the open source LLM with WasmEdge."}),"\n",(0,a.jsx)(n.p,{children:"First, install WasmEdge runtime with one single command line."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | bash -s -- --plugin wasi_nn-ggml\n"})}),"\n",(0,a.jsx)(n.p,{children:"Second, download the model file in GGUF file. Here, I use llama2-7b as an example. We have tried several LLMs and concluded that Llama2-7B is the beat for RAG applications."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -LO https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/resolve/main/Llama-2-7b-chat-hf-Q5_K_M.gguf\n"})}),"\n",(0,a.jsx)(n.p,{children:"Third, download an API server app. It is a cross-platform portable Wasm app that can run on many CPU and GPU devices."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"curl -LO https://github.com/second-state/LlamaEdge/releases/latest/download/llama-api-server.wasm\n"})}),"\n",(0,a.jsx)(n.p,{children:"Finally, use the following command lines to start an API server for the model. If you have did the above steps, just run the follwing command line."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-2-7b-chat-hf-Q5_K_M.gguf llama-api-server.wasm -p llama-2-chat -c 4096\n"})}),"\n",(0,a.jsx)(n.p,{children:"If everything goes well, the following information will be printed on the terminal."}),"\n",(0,a.jsx)(n.pre,{children:(0,a.jsx)(n.code,{children:"[INFO] Socket address: 0.0.0.0:8080\n[INFO] Model name: default\n[INFO] Model alias: default\n[INFO] Prompt context size: 512\n[INFO] Number of tokens to predict: 1024\n[INFO] Number of layers to run on the GPU: 100\n[INFO] Batch size for prompt processing: 512\n[INFO] Temperature for sampling: 0.8\n[INFO] Penalize repeat sequence of tokens: 1.1\n[INFO] Prompt template: HumanAssistant\n[INFO] Log prompts: false\n[INFO] Log statistics: false\n[INFO] Log all information: false\n[INFO] Starting server ...\nggml_init_cublas: GGML_CUDA_FORCE_MMQ: no\nggml_init_cublas: CUDA_USE_TENSOR_CORES: yes\nggml_init_cublas: found 1 CUDA devices:\n Device 0: Orin, compute capability 8.7, VMM: yes\n[INFO] Plugin version: b1953 (commit 6f9939d1)\n[INFO] Listening on http://0.0.0.0:8080\n"})}),"\n",(0,a.jsx)(n.p,{children:"Now the Llama2-7B-Chat model is hosted at the port of 8080."}),"\n",(0,a.jsx)(n.h3,{id:"connect-your-self-hosted-llms-with-the-chatbot-web-app",children:"Connect your self-hosted LLMs with the chatbot web app"}),"\n",(0,a.jsx)(n.p,{children:"Go back to the web page opened in the first step. Click Use cusom service on the bottom left of page and click the Connect button.\nThen you will see a section to upload your own data locally. Upload a pdf file here. When the uploading process is done, the bot will send you a message: \u201cHello \ud83d\udc4b, how can I help you?\u201d, which is a ready sign."}),"\n",(0,a.jsx)(n.p,{children:"Ask a question, and the bot will reply to you based on the file you uploaded."}),"\n",(0,a.jsx)(n.p,{children:(0,a.jsx)(n.img,{src:"https://github.com/LlamaEdge/docs/assets/45785633/0b5273f6-7edd-4fcf-b917-c5931609c5db",alt:"image"})}),"\n",(0,a.jsx)(n.h3,{id:"whats-next",children:"What\u2019s next?"}),"\n",(0,a.jsx)(n.p,{children:"We will introduce you how to build such a client-side RAG app with OpenWebui"})]})}function h(e={}){const{wrapper:n}={...(0,i.R)(),...e.components};return n?(0,a.jsx)(n,{...e,children:(0,a.jsx)(d,{...e})}):d(e)}},8453:(e,n,t)=>{t.d(n,{R:()=>o,x:()=>l});var a=t(6540);const i={},s=a.createContext(i);function o(e){const n=a.useContext(s);return a.useMemo((function(){return"function"==typeof e?e(n):{...n,...e}}),[n,e])}function l(e){let n;return n=e.disableParentContext?"function"==typeof e.components?e.components(i):e.components||i:o(e.components),a.createElement(s.Provider,{value:n},e.children)}}}]);
\ No newline at end of file
diff --git a/docs/assets/js/935f2afb.3dc903e3.js b/docs/assets/js/935f2afb.3dc903e3.js
deleted file mode 100644
index 9c5b6e7..0000000
--- a/docs/assets/js/935f2afb.3dc903e3.js
+++ /dev/null
@@ -1 +0,0 @@
-"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[581],{5610:e=>{e.exports=JSON.parse('{"pluginId":"default","version":"current","label":"Next","banner":null,"badge":false,"noIndex":false,"className":"docs-version-current","isLast":true,"docsSidebars":{"tutorialSidebar":[{"type":"link","label":"LlamaEdge","href":"/docs/intro","docId":"intro","unlisted":false},{"type":"link","label":"LlamaEdge vs Python","href":"/docs/llamaedge_vs_python","docId":"llamaedge_vs_python","unlisted":false},{"type":"link","label":"LlamaEdge vs llama.cpp","href":"/docs/llamaedge_vs_llamacpp","docId":"llamaedge_vs_llamacpp","unlisted":false},{"type":"link","label":"LlamaEdge vs Ollama","href":"/docs/llamaedge_vs_ollama","docId":"llamaedge_vs_ollama","unlisted":false},{"type":"category","label":"User Guide","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Quick start","href":"/docs/user-guide/quick-start-command","docId":"user-guide/quick-start-command","unlisted":false},{"type":"link","label":"LlamaEdge step-by-step","href":"/docs/user-guide/get-started-with-llamaedge","docId":"user-guide/get-started-with-llamaedge","unlisted":false},{"type":"link","label":"Calling external tools","href":"/docs/user-guide/tool-call","docId":"user-guide/tool-call","unlisted":false},{"type":"category","label":"Ecosystem apps","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Start an LlamaEdge API service","href":"/docs/user-guide/openai-api/intro","docId":"user-guide/openai-api/intro","unlisted":false},{"type":"link","label":"LobeChat","href":"/docs/user-guide/openai-api/lobechat","docId":"user-guide/openai-api/lobechat","unlisted":false},{"type":"link","label":"AI coding assistant: Continue","href":"/docs/user-guide/openai-api/continue","docId":"user-guide/openai-api/continue","unlisted":false},{"type":"link","label":"Obsidian","href":"/docs/user-guide/openai-api/obsidian","docId":"user-guide/openai-api/obsidian","unlisted":false},{"type":"link","label":"FlowiseAI tool call","href":"/docs/user-guide/openai-api/flowiseai-tool-call","docId":"user-guide/openai-api/flowiseai-tool-call","unlisted":false},{"type":"link","label":"Translation Agent","href":"/docs/user-guide/openai-api/translation-agent","docId":"user-guide/openai-api/translation-agent","unlisted":false},{"type":"link","label":"LangChain","href":"/docs/user-guide/openai-api/langchain","docId":"user-guide/openai-api/langchain","unlisted":false}],"href":"/docs/category/ecosystem-apps"},{"type":"category","label":"Long-term memory and knowledge","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Long-term memory for the LLM","href":"/docs/user-guide/server-side-rag/quick-start","docId":"user-guide/server-side-rag/quick-start","unlisted":false},{"type":"link","label":"Knowledge base from a plain text file","href":"/docs/user-guide/server-side-rag/text","docId":"user-guide/server-side-rag/text","unlisted":false},{"type":"link","label":"Knowledge base from a markdown file","href":"/docs/user-guide/server-side-rag/markdown","docId":"user-guide/server-side-rag/markdown","unlisted":false},{"type":"link","label":"Use the API server","href":"/docs/user-guide/server-side-rag/rag-service","docId":"user-guide/server-side-rag/rag-service","unlisted":false}],"href":"/docs/category/long-term-memory-and-knowledge"},{"type":"link","label":"Use LlamaEdge in Docker","href":"/docs/user-guide/llamaedge-docker","docId":"user-guide/llamaedge-docker","unlisted":false},{"type":"link","label":"Use LlamaEdge in Kubernetes","href":"/docs/user-guide/llamaedge-kubernetes","docId":"user-guide/llamaedge-kubernetes","unlisted":false}],"href":"/docs/category/user-guide"},{"type":"category","label":"Developer Guide","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Create a basic LLM app","href":"/docs/developer-guide/basic-llm-app","docId":"developer-guide/basic-llm-app","unlisted":false},{"type":"link","label":"Create a chatbot LLM app","href":"/docs/developer-guide/chatbot-llm-app","docId":"developer-guide/chatbot-llm-app","unlisted":false},{"type":"link","label":"Create a multimodal app","href":"/docs/developer-guide/multimodal-app","docId":"developer-guide/multimodal-app","unlisted":false},{"type":"link","label":"Create an embedding app","href":"/docs/developer-guide/embedding-app","docId":"developer-guide/embedding-app","unlisted":false},{"type":"link","label":"Create knowledge embeddings using the API server","href":"/docs/developer-guide/create-embeddings-collection","docId":"developer-guide/create-embeddings-collection","unlisted":false},{"type":"link","label":"Implement your own RAG API server","href":"/docs/developer-guide/rag-api-server","docId":"developer-guide/rag-api-server","unlisted":false}],"href":"/docs/category/developer-guide"}]},"docs":{"developer-guide/basic-llm-app":{"id":"developer-guide/basic-llm-app","title":"Create a basic LLM app","description":"At the most basic level, the LLM completes text. That is why the input text is called a \\"prompt\\". The base model simply comes up with the next words that are likely to follow the prompt. In this example, we will demonstrate this basic use case.","sidebar":"tutorialSidebar"},"developer-guide/chatbot-llm-app":{"id":"developer-guide/chatbot-llm-app","title":"Create a chatbot LLM app","description":"The most common LLM app has to be the chatbot. For that, the base LLM is finetuned with a lot of back and forth conversation examples. The base LLM \\"learns\\" how to follow conversations and becomes a chat LLM. Since the conversation examples are fed into the LLM using certain formats, the chat LLM will expect the input prompt to follow the same format. This is called the prompt template. Let\'s see how that works.","sidebar":"tutorialSidebar"},"developer-guide/create-embeddings-collection":{"id":"developer-guide/create-embeddings-collection","title":"Create knowledge embeddings using the API server","description":"The LlamaEdge API server project demonstrates how to support OpenAI style APIs to upload, chunck, and create embeddings for a text document. In this guide, I will show you how to use those API endpoints as a developer.","sidebar":"tutorialSidebar"},"developer-guide/embedding-app":{"id":"developer-guide/embedding-app","title":"Create an embedding app","description":"An important LLM task is to generate embeddings for natural language sentences. It converts a sentence to a vector of numbers called an \\"embedding\\". The embedding vectors can then be stored in a vector database. You can search it later to find similiar sentences.","sidebar":"tutorialSidebar"},"developer-guide/multimodal-app":{"id":"developer-guide/multimodal-app","title":"Create a multimodal app","description":"Coming soon.","sidebar":"tutorialSidebar"},"developer-guide/rag-api-server":{"id":"developer-guide/rag-api-server","title":"Implement your own RAG API server","description":"Coming soon.","sidebar":"tutorialSidebar"},"intro":{"id":"intro","title":"LlamaEdge","description":"LlamaEdge is the easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge.","sidebar":"tutorialSidebar"},"llamaedge_vs_llamacpp":{"id":"llamaedge_vs_llamacpp","title":"LlamaEdge vs llama.cpp","description":"The llama.cpp project is one of the inference backends for LlamaEdge. LlamaEdge provides high level application","sidebar":"tutorialSidebar"},"llamaedge_vs_ollama":{"id":"llamaedge_vs_ollama","title":"LlamaEdge vs Ollama","description":"There are several popular tools to run \\"local LLMs\\". Ollama is one of the earlist and most popular. Why do people","sidebar":"tutorialSidebar"},"llamaedge_vs_python":{"id":"llamaedge_vs_python","title":"LlamaEdge vs Python","description":"Most AI models are trained and even finetuned in Python / PyTorch, but you should not deploy and run them in Python.","sidebar":"tutorialSidebar"},"user-guide/get-started-with-llamaedge":{"id":"user-guide/get-started-with-llamaedge","title":"LlamaEdge step-by-step","description":"Let\'s dive into a simple and practical tutorial on getting started with LlamaEdge, focusing on how to use a Command Line Interface (CLI) installer to run a model, along with some useful WasmEdge commands. This guide can be adjusted and applied to run Llama 2 series of models, tailored to give you a hands-on approach to running your large language model with LlamaEdge.","sidebar":"tutorialSidebar"},"user-guide/llamaedge-docker":{"id":"user-guide/llamaedge-docker","title":"Use LlamaEdge in Docker","description":"You can run all the commands in this document without any change on any machine with the latest Docker and at least 8GB of RAM available to the container.","sidebar":"tutorialSidebar"},"user-guide/llamaedge-kubernetes":{"id":"user-guide/llamaedge-kubernetes","title":"Use LlamaEdge in Kubernetes","description":"Coming soon.","sidebar":"tutorialSidebar"},"user-guide/openai-api/continue":{"id":"user-guide/openai-api/continue","title":"AI coding assistant: Continue","description":"Continue is the leading open-source AI code assistant.","sidebar":"tutorialSidebar"},"user-guide/openai-api/flowiseai-tool-call":{"id":"user-guide/openai-api/flowiseai-tool-call","title":"FlowiseAI tool call","description":"FlowiseAI is a low-code tool for developers to build customized LLM orchestration flows & AI agents.","sidebar":"tutorialSidebar"},"user-guide/openai-api/intro":{"id":"user-guide/openai-api/intro","title":"Start an LlamaEdge API service","description":"Since LlamaEdge provides an OpenAI-compatible API service, it can be a drop-in replacement for OpenAI in almost all LLM applications and frameworks.","sidebar":"tutorialSidebar"},"user-guide/openai-api/langchain":{"id":"user-guide/openai-api/langchain","title":"LangChain","description":"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain.","sidebar":"tutorialSidebar"},"user-guide/openai-api/lobechat":{"id":"user-guide/openai-api/lobechat","title":"LobeChat","description":"The LobeChat framework is a modern chatbot framework that supports a wide range of","sidebar":"tutorialSidebar"},"user-guide/openai-api/obsidian":{"id":"user-guide/openai-api/obsidian","title":"Obsidian","description":"Obsidian is a note-taking application that enables users to create, link, and visualize ideas directly on their devices. With Obsidian, you can seamlessly sync notes across devices, publish your work, and collaborate with others. The app is highly customizable, allowing users to enhance functionality through a wide range of plugins and themes. Its unique features include a graph view to visualize connections between notes, making it ideal for managing complex information and fostering creativity. Obsidian also emphasizes data privacy by storing notes locally.","sidebar":"tutorialSidebar"},"user-guide/openai-api/translation-agent":{"id":"user-guide/openai-api/translation-agent","title":"Translation Agent","description":"This LLM Translation Agent originally built by Prof. Andrew Ng is designed to facilitate accurate and efficient translation across multiple languages. It employs open source LLMs (Large Language Models) to provide high-quality translations. You can use your own fine-tuned models or any LLMs on Hugging Face like Meta\'s Llama 3. This documentation shows how the Transgenic Agent utilizes the Gemma-2-9B model for translation.","sidebar":"tutorialSidebar"},"user-guide/quick-start-command":{"id":"user-guide/quick-start-command","title":"Quick start","description":"Enhance your onboarding experience and quickly get started with LlamaEdge using the following scripts.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/markdown":{"id":"user-guide/server-side-rag/markdown","title":"Knowledge base from a markdown file","description":"In this section, we will discuss how to create a vector collection snapshot from a markdown file. The","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/quick-start":{"id":"user-guide/server-side-rag/quick-start","title":"Long-term memory for the LLM","description":"The LLM app requires both long-term and short-term memories. Long-term memory includes factual knowledge, historical facts, background stories etc. They are best added to the context as complete chapters instead of small chunks of text to maintain the internal consistency of the knowledge.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/rag-service":{"id":"user-guide/server-side-rag/rag-service","title":"Use the API server","description":"The LlamaEdge RAG API server provides an API endpoint /create/rag that takes a text file, segments it into small chunks, turns the chunks into embeddings (i.e., vectors), and then stores the embeddings into the Qdrant database.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/text":{"id":"user-guide/server-side-rag/text","title":"Knowledge base from a plain text file","description":"In this section, we will discuss how to create a vector collection snapshot from a plain text file. The","sidebar":"tutorialSidebar"},"user-guide/tool-call":{"id":"user-guide/tool-call","title":"Calling external tools","description":"Tool calling is one of the truly \\"LLM native\\" interaction modes that has never existed before.","sidebar":"tutorialSidebar"}}}')}}]);
\ No newline at end of file
diff --git a/docs/assets/js/935f2afb.9b3b2419.js b/docs/assets/js/935f2afb.9b3b2419.js
new file mode 100644
index 0000000..7cb2c84
--- /dev/null
+++ b/docs/assets/js/935f2afb.9b3b2419.js
@@ -0,0 +1 @@
+"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[581],{5610:e=>{e.exports=JSON.parse('{"pluginId":"default","version":"current","label":"Next","banner":null,"badge":false,"noIndex":false,"className":"docs-version-current","isLast":true,"docsSidebars":{"tutorialSidebar":[{"type":"link","label":"LlamaEdge","href":"/docs/intro","docId":"intro","unlisted":false},{"type":"link","label":"LlamaEdge vs Python","href":"/docs/llamaedge_vs_python","docId":"llamaedge_vs_python","unlisted":false},{"type":"link","label":"LlamaEdge vs llama.cpp","href":"/docs/llamaedge_vs_llamacpp","docId":"llamaedge_vs_llamacpp","unlisted":false},{"type":"link","label":"LlamaEdge vs Ollama","href":"/docs/llamaedge_vs_ollama","docId":"llamaedge_vs_ollama","unlisted":false},{"type":"category","label":"User Guide","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Quick start","href":"/docs/user-guide/quick-start-command","docId":"user-guide/quick-start-command","unlisted":false},{"type":"link","label":"LlamaEdge step-by-step","href":"/docs/user-guide/get-started-with-llamaedge","docId":"user-guide/get-started-with-llamaedge","unlisted":false},{"type":"link","label":"Calling external tools","href":"/docs/user-guide/tool-call","docId":"user-guide/tool-call","unlisted":false},{"type":"category","label":"Ecosystem apps","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Start an LlamaEdge API service","href":"/docs/user-guide/openai-api/intro","docId":"user-guide/openai-api/intro","unlisted":false},{"type":"link","label":"LobeChat","href":"/docs/user-guide/openai-api/lobechat","docId":"user-guide/openai-api/lobechat","unlisted":false},{"type":"link","label":"AI coding assistant: Continue","href":"/docs/user-guide/openai-api/continue","docId":"user-guide/openai-api/continue","unlisted":false},{"type":"link","label":"Obsidian","href":"/docs/user-guide/openai-api/obsidian","docId":"user-guide/openai-api/obsidian","unlisted":false},{"type":"link","label":"FlowiseAI tool call","href":"/docs/user-guide/openai-api/flowiseai-tool-call","docId":"user-guide/openai-api/flowiseai-tool-call","unlisted":false},{"type":"link","label":"Translation Agent","href":"/docs/user-guide/openai-api/translation-agent","docId":"user-guide/openai-api/translation-agent","unlisted":false},{"type":"link","label":"LangChain","href":"/docs/user-guide/openai-api/langchain","docId":"user-guide/openai-api/langchain","unlisted":false},{"type":"link","label":"Agent Zero","href":"/docs/user-guide/openai-api/agent-zero","docId":"user-guide/openai-api/agent-zero","unlisted":false}],"href":"/docs/category/ecosystem-apps"},{"type":"category","label":"Long-term memory and knowledge","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Long-term memory for the LLM","href":"/docs/user-guide/server-side-rag/quick-start","docId":"user-guide/server-side-rag/quick-start","unlisted":false},{"type":"link","label":"Knowledge base from a plain text file","href":"/docs/user-guide/server-side-rag/text","docId":"user-guide/server-side-rag/text","unlisted":false},{"type":"link","label":"Knowledge base from a markdown file","href":"/docs/user-guide/server-side-rag/markdown","docId":"user-guide/server-side-rag/markdown","unlisted":false},{"type":"link","label":"Use the API server","href":"/docs/user-guide/server-side-rag/rag-service","docId":"user-guide/server-side-rag/rag-service","unlisted":false}],"href":"/docs/category/long-term-memory-and-knowledge"},{"type":"link","label":"Use LlamaEdge in Docker","href":"/docs/user-guide/llamaedge-docker","docId":"user-guide/llamaedge-docker","unlisted":false},{"type":"link","label":"Use LlamaEdge in Kubernetes","href":"/docs/user-guide/llamaedge-kubernetes","docId":"user-guide/llamaedge-kubernetes","unlisted":false}],"href":"/docs/category/user-guide"},{"type":"category","label":"Developer Guide","collapsible":true,"collapsed":true,"items":[{"type":"link","label":"Create a basic LLM app","href":"/docs/developer-guide/basic-llm-app","docId":"developer-guide/basic-llm-app","unlisted":false},{"type":"link","label":"Create a chatbot LLM app","href":"/docs/developer-guide/chatbot-llm-app","docId":"developer-guide/chatbot-llm-app","unlisted":false},{"type":"link","label":"Create a multimodal app","href":"/docs/developer-guide/multimodal-app","docId":"developer-guide/multimodal-app","unlisted":false},{"type":"link","label":"Create an embedding app","href":"/docs/developer-guide/embedding-app","docId":"developer-guide/embedding-app","unlisted":false},{"type":"link","label":"Create knowledge embeddings using the API server","href":"/docs/developer-guide/create-embeddings-collection","docId":"developer-guide/create-embeddings-collection","unlisted":false},{"type":"link","label":"Implement your own RAG API server","href":"/docs/developer-guide/rag-api-server","docId":"developer-guide/rag-api-server","unlisted":false}],"href":"/docs/category/developer-guide"}]},"docs":{"developer-guide/basic-llm-app":{"id":"developer-guide/basic-llm-app","title":"Create a basic LLM app","description":"At the most basic level, the LLM completes text. That is why the input text is called a \\"prompt\\". The base model simply comes up with the next words that are likely to follow the prompt. In this example, we will demonstrate this basic use case.","sidebar":"tutorialSidebar"},"developer-guide/chatbot-llm-app":{"id":"developer-guide/chatbot-llm-app","title":"Create a chatbot LLM app","description":"The most common LLM app has to be the chatbot. For that, the base LLM is finetuned with a lot of back and forth conversation examples. The base LLM \\"learns\\" how to follow conversations and becomes a chat LLM. Since the conversation examples are fed into the LLM using certain formats, the chat LLM will expect the input prompt to follow the same format. This is called the prompt template. Let\'s see how that works.","sidebar":"tutorialSidebar"},"developer-guide/create-embeddings-collection":{"id":"developer-guide/create-embeddings-collection","title":"Create knowledge embeddings using the API server","description":"The LlamaEdge API server project demonstrates how to support OpenAI style APIs to upload, chunck, and create embeddings for a text document. In this guide, I will show you how to use those API endpoints as a developer.","sidebar":"tutorialSidebar"},"developer-guide/embedding-app":{"id":"developer-guide/embedding-app","title":"Create an embedding app","description":"An important LLM task is to generate embeddings for natural language sentences. It converts a sentence to a vector of numbers called an \\"embedding\\". The embedding vectors can then be stored in a vector database. You can search it later to find similiar sentences.","sidebar":"tutorialSidebar"},"developer-guide/multimodal-app":{"id":"developer-guide/multimodal-app","title":"Create a multimodal app","description":"Coming soon.","sidebar":"tutorialSidebar"},"developer-guide/rag-api-server":{"id":"developer-guide/rag-api-server","title":"Implement your own RAG API server","description":"Coming soon.","sidebar":"tutorialSidebar"},"intro":{"id":"intro","title":"LlamaEdge","description":"LlamaEdge is the easiest & fastest way to run customized and fine-tuned LLMs locally or on the edge.","sidebar":"tutorialSidebar"},"llamaedge_vs_llamacpp":{"id":"llamaedge_vs_llamacpp","title":"LlamaEdge vs llama.cpp","description":"The llama.cpp project is one of the inference backends for LlamaEdge. LlamaEdge provides high level application","sidebar":"tutorialSidebar"},"llamaedge_vs_ollama":{"id":"llamaedge_vs_ollama","title":"LlamaEdge vs Ollama","description":"There are several popular tools to run \\"local LLMs\\". Ollama is one of the earlist and most popular. Why do people","sidebar":"tutorialSidebar"},"llamaedge_vs_python":{"id":"llamaedge_vs_python","title":"LlamaEdge vs Python","description":"Most AI models are trained and even finetuned in Python / PyTorch, but you should not deploy and run them in Python.","sidebar":"tutorialSidebar"},"user-guide/get-started-with-llamaedge":{"id":"user-guide/get-started-with-llamaedge","title":"LlamaEdge step-by-step","description":"Let\'s dive into a simple and practical tutorial on getting started with LlamaEdge, focusing on how to use a Command Line Interface (CLI) installer to run a model, along with some useful WasmEdge commands. This guide can be adjusted and applied to run Llama 2 series of models, tailored to give you a hands-on approach to running your large language model with LlamaEdge.","sidebar":"tutorialSidebar"},"user-guide/llamaedge-docker":{"id":"user-guide/llamaedge-docker","title":"Use LlamaEdge in Docker","description":"You can run all the commands in this document without any change on any machine with the latest Docker and at least 8GB of RAM available to the container.","sidebar":"tutorialSidebar"},"user-guide/llamaedge-kubernetes":{"id":"user-guide/llamaedge-kubernetes","title":"Use LlamaEdge in Kubernetes","description":"Coming soon.","sidebar":"tutorialSidebar"},"user-guide/openai-api/agent-zero":{"id":"user-guide/openai-api/agent-zero","title":"Agent Zero","description":"Agent Zero is a general purpose AI agent application. You can simply ask it to accomplish tasks on the command line.","sidebar":"tutorialSidebar"},"user-guide/openai-api/continue":{"id":"user-guide/openai-api/continue","title":"AI coding assistant: Continue","description":"Continue is the leading open-source AI code assistant.","sidebar":"tutorialSidebar"},"user-guide/openai-api/flowiseai-tool-call":{"id":"user-guide/openai-api/flowiseai-tool-call","title":"FlowiseAI tool call","description":"FlowiseAI is a low-code tool for developers to build customized LLM orchestration flows & AI agents.","sidebar":"tutorialSidebar"},"user-guide/openai-api/intro":{"id":"user-guide/openai-api/intro","title":"Start an LlamaEdge API service","description":"Since LlamaEdge provides an OpenAI-compatible API service, it can be a drop-in replacement for OpenAI in almost all LLM applications and frameworks.","sidebar":"tutorialSidebar"},"user-guide/openai-api/langchain":{"id":"user-guide/openai-api/langchain","title":"LangChain","description":"In this tutorial, I will introduce you how to build a client-side RAG using Llama2-7b-chat model, based on LlamaEdge and Langchain.","sidebar":"tutorialSidebar"},"user-guide/openai-api/lobechat":{"id":"user-guide/openai-api/lobechat","title":"LobeChat","description":"The LobeChat framework is a modern chatbot framework that supports a wide range of","sidebar":"tutorialSidebar"},"user-guide/openai-api/obsidian":{"id":"user-guide/openai-api/obsidian","title":"Obsidian","description":"Obsidian is a note-taking application that enables users to create, link, and visualize ideas directly on their devices. With Obsidian, you can seamlessly sync notes across devices, publish your work, and collaborate with others. The app is highly customizable, allowing users to enhance functionality through a wide range of plugins and themes. Its unique features include a graph view to visualize connections between notes, making it ideal for managing complex information and fostering creativity. Obsidian also emphasizes data privacy by storing notes locally.","sidebar":"tutorialSidebar"},"user-guide/openai-api/translation-agent":{"id":"user-guide/openai-api/translation-agent","title":"Translation Agent","description":"This LLM Translation Agent originally built by Prof. Andrew Ng is designed to facilitate accurate and efficient translation across multiple languages. It employs open source LLMs (Large Language Models) to provide high-quality translations. You can use your own fine-tuned models or any LLMs on Hugging Face like Meta\'s Llama 3. This documentation shows how the Transgenic Agent utilizes the Gemma-2-9B model for translation.","sidebar":"tutorialSidebar"},"user-guide/quick-start-command":{"id":"user-guide/quick-start-command","title":"Quick start","description":"Enhance your onboarding experience and quickly get started with LlamaEdge using the following scripts.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/markdown":{"id":"user-guide/server-side-rag/markdown","title":"Knowledge base from a markdown file","description":"In this section, we will discuss how to create a vector collection snapshot from a markdown file. The","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/quick-start":{"id":"user-guide/server-side-rag/quick-start","title":"Long-term memory for the LLM","description":"The LLM app requires both long-term and short-term memories. Long-term memory includes factual knowledge, historical facts, background stories etc. They are best added to the context as complete chapters instead of small chunks of text to maintain the internal consistency of the knowledge.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/rag-service":{"id":"user-guide/server-side-rag/rag-service","title":"Use the API server","description":"The LlamaEdge RAG API server provides an API endpoint /create/rag that takes a text file, segments it into small chunks, turns the chunks into embeddings (i.e., vectors), and then stores the embeddings into the Qdrant database.","sidebar":"tutorialSidebar"},"user-guide/server-side-rag/text":{"id":"user-guide/server-side-rag/text","title":"Knowledge base from a plain text file","description":"In this section, we will discuss how to create a vector collection snapshot from a plain text file. The","sidebar":"tutorialSidebar"},"user-guide/tool-call":{"id":"user-guide/tool-call","title":"Calling external tools","description":"Tool calling is one of the truly \\"LLM native\\" interaction modes that has never existed before.","sidebar":"tutorialSidebar"}}}')}}]);
\ No newline at end of file
diff --git a/docs/assets/js/f7a718d8.d77718b9.js b/docs/assets/js/f7a718d8.ab59607e.js
similarity index 53%
rename from docs/assets/js/f7a718d8.d77718b9.js
rename to docs/assets/js/f7a718d8.ab59607e.js
index c7f98ef..e7a909b 100644
--- a/docs/assets/js/f7a718d8.d77718b9.js
+++ b/docs/assets/js/f7a718d8.ab59607e.js
@@ -1 +1 @@
-"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[397],{8422:e=>{e.exports=JSON.parse('{"title":"Long-term memory and knowledge","slug":"/category/long-term-memory-and-knowledge","permalink":"/docs/category/long-term-memory-and-knowledge","navigation":{"previous":{"title":"LangChain","permalink":"/docs/user-guide/openai-api/langchain"},"next":{"title":"Long-term memory for the LLM","permalink":"/docs/user-guide/server-side-rag/quick-start"}}}')}}]);
\ No newline at end of file
+"use strict";(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[397],{8422:e=>{e.exports=JSON.parse('{"title":"Long-term memory and knowledge","slug":"/category/long-term-memory-and-knowledge","permalink":"/docs/category/long-term-memory-and-knowledge","navigation":{"previous":{"title":"Agent Zero","permalink":"/docs/user-guide/openai-api/agent-zero"},"next":{"title":"Long-term memory for the LLM","permalink":"/docs/user-guide/server-side-rag/quick-start"}}}')}}]);
\ No newline at end of file
diff --git a/docs/assets/js/main.3cca63b7.js b/docs/assets/js/main.3cca63b7.js
deleted file mode 100644
index 9ed8a86..0000000
--- a/docs/assets/js/main.3cca63b7.js
+++ /dev/null
@@ -1,2 +0,0 @@
-/*! For license information please see main.3cca63b7.js.LICENSE.txt */
-(self.webpackChunkdocs=self.webpackChunkdocs||[]).push([[792],{8328:(e,t,n)=>{"use strict";n.d(t,{A:()=>p});n(6540);var r=n(3259),a=n.n(r),o=n(4054);const i={"08a17b15":[()=>n.e(680).then(n.bind(n,9140)),"@site/docs/developer-guide/basic-llm-app.md",9140],"0e384e19":[()=>n.e(976).then(n.bind(n,1512)),"@site/docs/intro.md",1512],"1429b7e2":[()=>n.e(531).then(n.t.bind(n,122,19)),"~docs/default/category-docs-tutorialsidebar-category-user-guide-a78.json",122],"14eb3368":[()=>Promise.all([n.e(869),n.e(969)]).then(n.bind(n,4136)),"@theme/DocCategoryGeneratedIndexPage",4136],17896441:[()=>Promise.all([n.e(869),n.e(674),n.e(401)]).then(n.bind(n,3761)),"@theme/DocItem",3761],"1f391b9e":[()=>Promise.all([n.e(869),n.e(674),n.e(61)]).then(n.bind(n,7973)),"@theme/MDXPage",7973],"23b1c9b9":[()=>n.e(882).then(n.bind(n,1032)),"@site/docs/developer-guide/multimodal-app.md",1032],"247783bb":[()=>n.e(548).then(n.t.bind(n,1966,19)),"/home/runner/work/docs/docs/.docusaurus/docusaurus-plugin-content-docs/default/plugin-route-context-module-100.json",1966],"26fe1d28":[()=>n.e(469).then(n.bind(n,8505)),"@site/docs/developer-guide/embedding-app.md",8505],"28397fbf":[()=>n.e(918).then(n.bind(n,3792)),"@site/docs/user-guide/openai-api/continue.md",3792],"2f1a0122":[()=>n.e(348).then(n.bind(n,2764)),"@site/docs/user-guide/openai-api/flowiseai-tool-call.md",2764],33630671:[()=>n.e(322).then(n.bind(n,6931)),"@site/docs/llamaedge_vs_ollama.md",6931],"3563a78d":[()=>n.e(830).then(n.bind(n,7461)),"@site/docs/developer-guide/rag-api-server.md",7461],"393be207":[()=>n.e(134).then(n.bind(n,6602)),"@site/src/pages/markdown-page.md",6602],"42b607eb":[()=>n.e(211).then(n.t.bind(n,6086,19)),"~docs/default/category-docs-tutorialsidebar-category-ecosystem-apps-2d9.json",6086],"4c50c399":[()=>n.e(671).then(n.bind(n,2692)),"@site/docs/llamaedge_vs_python.md",2692],"55fa9a31":[()=>n.e(284).then(n.bind(n,3469)),"@site/docs/developer-guide/chatbot-llm-app.md",3469],"5e95c892":[()=>n.e(647).then(n.bind(n,7121)),"@theme/DocsRoot",7121],"5e9f5e1a":[()=>Promise.resolve().then(n.bind(n,4784)),"@generated/docusaurus.config",4784],"7c225f1f":[()=>n.e(509).then(n.t.bind(n,4817,19)),"~docs/default/category-docs-tutorialsidebar-category-developer-guide-2ae.json",4817],"89b72d9d":[()=>n.e(74).then(n.bind(n,9412)),"@site/docs/user-guide/openai-api/langchain.md",9412],"935f2afb":[()=>n.e(581).then(n.t.bind(n,5610,19)),"~docs/default/version-current-metadata-prop-751.json",5610],"95e1d156":[()=>n.e(83).then(n.bind(n,547)),"@site/docs/llamaedge_vs_llamacpp.md",547],"9d0bdc28":[()=>n.e(327).then(n.bind(n,825)),"@site/docs/user-guide/server-side-rag/text.md",825],a03793ee:[()=>n.e(784).then(n.bind(n,8326)),"@site/docs/user-guide/llamaedge-docker.md",8326],a3b48427:[()=>n.e(840).then(n.bind(n,1683)),"@site/docs/user-guide/openai-api/lobechat.md",1683],a3b5ba69:[()=>n.e(264).then(n.bind(n,2906)),"@site/docs/user-guide/openai-api/translation-agent.md",2906],a7434565:[()=>n.e(678).then(n.t.bind(n,4061,19)),"/home/runner/work/docs/docs/.docusaurus/docusaurus-plugin-content-pages/default/plugin-route-context-module-100.json",4061],a7bd4aaa:[()=>n.e(98).then(n.bind(n,4532)),"@theme/DocVersionRoot",4532],a94703ab:[()=>Promise.all([n.e(869),n.e(48)]).then(n.bind(n,2559)),"@theme/DocRoot",2559],ac7af1dc:[()=>n.e(511).then(n.bind(n,2960)),"@site/docs/user-guide/server-side-rag/rag-service.md",2960],b75a693e:[()=>n.e(643).then(n.bind(n,6267)),"@site/docs/user-guide/quick-start-command.md",6267],c4f5d8e4:[()=>n.e(634).then(n.bind(n,192)),"@site/src/pages/index.js",192],c9e9c5bd:[()=>n.e(431).then(n.bind(n,8035)),"@site/docs/user-guide/openai-api/intro.md",8035],ccb8e574:[()=>n.e(0).then(n.bind(n,8936)),"@site/docs/developer-guide/create-embeddings-collection.md",8936],cf9f8924:[()=>n.e(546).then(n.bind(n,9580)),"@site/docs/user-guide/openai-api/obsidian.md",9580],d3ca0ead:[()=>n.e(910).then(n.bind(n,6308)),"@site/docs/user-guide/tool-call.md",6308],d6563973:[()=>n.e(550).then(n.bind(n,5246)),"@site/docs/user-guide/server-side-rag/quick-start.md",5246],e4f9ea1b:[()=>n.e(76).then(n.bind(n,2755)),"@site/docs/user-guide/get-started-with-llamaedge.md",2755],e5876591:[()=>n.e(899).then(n.bind(n,8762)),"@site/docs/user-guide/llamaedge-kubernetes.md",8762],f7a718d8:[()=>n.e(397).then(n.t.bind(n,8422,19)),"~docs/default/category-docs-tutorialsidebar-category-long-term-memory-and-knowledge-8a5.json",8422],f805ca34:[()=>n.e(793).then(n.bind(n,5180)),"@site/docs/user-guide/server-side-rag/markdown.md",5180]};var l=n(4848);function s(e){let{error:t,retry:n,pastDelay:r}=e;return t?(0,l.jsxs)("div",{style:{textAlign:"center",color:"#fff",backgroundColor:"#fa383e",borderColor:"#fa383e",borderStyle:"solid",borderRadius:"0.25rem",borderWidth:"1px",boxSizing:"border-box",display:"block",padding:"1rem",flex:"0 0 50%",marginLeft:"25%",marginRight:"25%",marginTop:"5rem",maxWidth:"50%",width:"100%"},children:[(0,l.jsx)("p",{children:String(t)}),(0,l.jsx)("div",{children:(0,l.jsx)("button",{type:"button",onClick:n,children:"Retry"})})]}):r?(0,l.jsx)("div",{style:{display:"flex",justifyContent:"center",alignItems:"center",height:"100vh"},children:(0,l.jsx)("svg",{id:"loader",style:{width:128,height:110,position:"absolute",top:"calc(100vh - 64%)"},viewBox:"0 0 45 45",xmlns:"http://www.w3.org/2000/svg",stroke:"#61dafb",children:(0,l.jsxs)("g",{fill:"none",fillRule:"evenodd",transform:"translate(1 1)",strokeWidth:"2",children:[(0,l.jsxs)("circle",{cx:"22",cy:"22",r:"6",strokeOpacity:"0",children:[(0,l.jsx)("animate",{attributeName:"r",begin:"1.5s",dur:"3s",values:"6;22",calcMode:"linear",repeatCount:"indefinite"}),(0,l.jsx)("animate",{attributeName:"stroke-opacity",begin:"1.5s",dur:"3s",values:"1;0",calcMode:"linear",repeatCount:"indefinite"}),(0,l.jsx)("animate",{attributeName:"stroke-width",begin:"1.5s",dur:"3s",values:"2;0",calcMode:"linear",repeatCount:"indefinite"})]}),(0,l.jsxs)("circle",{cx:"22",cy:"22",r:"6",strokeOpacity:"0",children:[(0,l.jsx)("animate",{attributeName:"r",begin:"3s",dur:"3s",values:"6;22",calcMode:"linear",repeatCount:"indefinite"}),(0,l.jsx)("animate",{attributeName:"stroke-opacity",begin:"3s",dur:"3s",values:"1;0",calcMode:"linear",repeatCount:"indefinite"}),(0,l.jsx)("animate",{attributeName:"stroke-width",begin:"3s",dur:"3s",values:"2;0",calcMode:"linear",repeatCount:"indefinite"})]}),(0,l.jsx)("circle",{cx:"22",cy:"22",r:"8",children:(0,l.jsx)("animate",{attributeName:"r",begin:"0s",dur:"1.5s",values:"6;1;2;3;4;5;6",calcMode:"linear",repeatCount:"indefinite"})})]})})}):null}var u=n(6921),c=n(3102);function d(e,t){if("*"===e)return a()({loading:s,loader:()=>n.e(237).then(n.bind(n,2237)),modules:["@theme/NotFound"],webpack:()=>[2237],render(e,t){const n=e.default;return(0,l.jsx)(c.W,{value:{plugin:{name:"native",id:"default"}},children:(0,l.jsx)(n,{...t})})}});const r=o[`${e}-${t}`],d={},p=[],f=[],m=(0,u.A)(r);return Object.entries(m).forEach((e=>{let[t,n]=e;const r=i[n];r&&(d[t]=r[0],p.push(r[1]),f.push(r[2]))})),a().Map({loading:s,loader:d,modules:p,webpack:()=>f,render(t,n){const a=JSON.parse(JSON.stringify(r));Object.entries(t).forEach((t=>{let[n,r]=t;const o=r.default;if(!o)throw new Error(`The page component at ${e} doesn't have a default export. This makes it impossible to render anything. Consider default-exporting a React component.`);"object"!=typeof o&&"function"!=typeof o||Object.keys(r).filter((e=>"default"!==e)).forEach((e=>{o[e]=r[e]}));let i=a;const l=n.split(".");l.slice(0,-1).forEach((e=>{i=i[e]})),i[l[l.length-1]]=o}));const o=a.__comp;delete a.__comp;const i=a.__context;return delete a.__context,(0,l.jsx)(c.W,{value:i,children:(0,l.jsx)(o,{...a,...n})})}})}const p=[{path:"/docs/markdown-page",component:d("/docs/markdown-page","9ec"),exact:!0},{path:"/docs/",component:d("/docs/","6f9"),exact:!0},{path:"/docs/",component:d("/docs/","10f"),routes:[{path:"/docs/",component:d("/docs/","ebe"),routes:[{path:"/docs/",component:d("/docs/","25d"),routes:[{path:"/docs/category/developer-guide",component:d("/docs/category/developer-guide","854"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/category/ecosystem-apps",component:d("/docs/category/ecosystem-apps","3db"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/category/long-term-memory-and-knowledge",component:d("/docs/category/long-term-memory-and-knowledge","09f"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/category/user-guide",component:d("/docs/category/user-guide","2a4"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/basic-llm-app",component:d("/docs/developer-guide/basic-llm-app","8ea"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/chatbot-llm-app",component:d("/docs/developer-guide/chatbot-llm-app","edd"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/create-embeddings-collection",component:d("/docs/developer-guide/create-embeddings-collection","440"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/embedding-app",component:d("/docs/developer-guide/embedding-app","9ec"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/multimodal-app",component:d("/docs/developer-guide/multimodal-app","72a"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/developer-guide/rag-api-server",component:d("/docs/developer-guide/rag-api-server","eb3"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/intro",component:d("/docs/intro","aed"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/llamaedge_vs_llamacpp",component:d("/docs/llamaedge_vs_llamacpp","ada"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/llamaedge_vs_ollama",component:d("/docs/llamaedge_vs_ollama","89e"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/llamaedge_vs_python",component:d("/docs/llamaedge_vs_python","2c9"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/get-started-with-llamaedge",component:d("/docs/user-guide/get-started-with-llamaedge","4ed"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/llamaedge-docker",component:d("/docs/user-guide/llamaedge-docker","549"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/llamaedge-kubernetes",component:d("/docs/user-guide/llamaedge-kubernetes","cab"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/continue",component:d("/docs/user-guide/openai-api/continue","5b3"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/flowiseai-tool-call",component:d("/docs/user-guide/openai-api/flowiseai-tool-call","549"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/intro",component:d("/docs/user-guide/openai-api/intro","88b"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/langchain",component:d("/docs/user-guide/openai-api/langchain","14c"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/lobechat",component:d("/docs/user-guide/openai-api/lobechat","d13"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/obsidian",component:d("/docs/user-guide/openai-api/obsidian","b79"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/openai-api/translation-agent",component:d("/docs/user-guide/openai-api/translation-agent","a28"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/quick-start-command",component:d("/docs/user-guide/quick-start-command","f07"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/server-side-rag/markdown",component:d("/docs/user-guide/server-side-rag/markdown","0e8"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/server-side-rag/quick-start",component:d("/docs/user-guide/server-side-rag/quick-start","073"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/server-side-rag/rag-service",component:d("/docs/user-guide/server-side-rag/rag-service","c4f"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/server-side-rag/text",component:d("/docs/user-guide/server-side-rag/text","c23"),exact:!0,sidebar:"tutorialSidebar"},{path:"/docs/user-guide/tool-call",component:d("/docs/user-guide/tool-call","e52"),exact:!0,sidebar:"tutorialSidebar"}]}]}]},{path:"*",component:d("*")}]},6125:(e,t,n)=>{"use strict";n.d(t,{o:()=>o,x:()=>i});var r=n(6540),a=n(4848);const o=r.createContext(!1);function i(e){let{children:t}=e;const[n,i]=(0,r.useState)(!1);return(0,r.useEffect)((()=>{i(!0)}),[]),(0,a.jsx)(o.Provider,{value:n,children:t})}},8536:(e,t,n)=>{"use strict";var r=n(6540),a=n(5338),o=n(4625),i=n(545),l=n(8193);const s=[n(119),n(6134),n(6294),n(1043)];var u=n(8328),c=n(6347),d=n(2831),p=n(4848);function f(e){let{children:t}=e;return(0,p.jsx)(p.Fragment,{children:t})}var m=n(5260),g=n(4586),h=n(6025),y=n(6342),b=n(1003),v=n(2131),w=n(4090),k=n(2967),x=n(440),S=n(1463);function E(){const{i18n:{currentLocale:e,defaultLocale:t,localeConfigs:n}}=(0,g.A)(),r=(0,v.o)(),a=n[e].htmlLang,o=e=>e.replace("-","_");return(0,p.jsxs)(m.A,{children:[Object.entries(n).map((e=>{let[t,{htmlLang:n}]=e;return(0,p.jsx)("link",{rel:"alternate",href:r.createUrl({locale:t,fullyQualified:!0}),hrefLang:n},t)})),(0,p.jsx)("link",{rel:"alternate",href:r.createUrl({locale:t,fullyQualified:!0}),hrefLang:"x-default"}),(0,p.jsx)("meta",{property:"og:locale",content:o(a)}),Object.values(n).filter((e=>a!==e.htmlLang)).map((e=>(0,p.jsx)("meta",{property:"og:locale:alternate",content:o(e.htmlLang)},`meta-og-${e.htmlLang}`)))]})}function C(e){let{permalink:t}=e;const{siteConfig:{url:n}}=(0,g.A)(),r=function(){const{siteConfig:{url:e,baseUrl:t,trailingSlash:n}}=(0,g.A)(),{pathname:r}=(0,c.zy)();return e+(0,x.applyTrailingSlash)((0,h.A)(r),{trailingSlash:n,baseUrl:t})}(),a=t?`${n}${t}`:r;return(0,p.jsxs)(m.A,{children:[(0,p.jsx)("meta",{property:"og:url",content:a}),(0,p.jsx)("link",{rel:"canonical",href:a})]})}function _(){const{i18n:{currentLocale:e}}=(0,g.A)(),{metadata:t,image:n}=(0,y.p)();return(0,p.jsxs)(p.Fragment,{children:[(0,p.jsxs)(m.A,{children:[(0,p.jsx)("meta",{name:"twitter:card",content:"summary_large_image"}),(0,p.jsx)("body",{className:w.w})]}),n&&(0,p.jsx)(b.be,{image:n}),(0,p.jsx)(C,{}),(0,p.jsx)(E,{}),(0,p.jsx)(S.A,{tag:k.Cy,locale:e}),(0,p.jsx)(m.A,{children:t.map(((e,t)=>(0,p.jsx)("meta",{...e},t)))})]})}const A=new Map;function T(e){if(A.has(e.pathname))return{...e,pathname:A.get(e.pathname)};if((0,d.u)(u.A,e.pathname).some((e=>{let{route:t}=e;return!0===t.exact})))return A.set(e.pathname,e.pathname),e;const t=e.pathname.trim().replace(/(?:\/index)?\.html$/,"")||"/";return A.set(e.pathname,t),{...e,pathname:t}}var j=n(6125),N=n(6988),L=n(205);function R(e){for(var t=arguments.length,n=new Array(t>1?t-1:0),r=1;r{const r=t.default?.[e]??t[e];return r?.(...n)}));return()=>a.forEach((e=>e?.()))}const P=function(e){let{children:t,location:n,previousLocation:r}=e;return(0,L.A)((()=>{r!==n&&(!function(e){let{location:t,previousLocation:n}=e;if(!n)return;const r=t.pathname===n.pathname,a=t.hash===n.hash,o=t.search===n.search;if(r&&a&&!o)return;const{hash:i}=t;if(i){const e=decodeURIComponent(i.substring(1)),t=document.getElementById(e);t?.scrollIntoView()}else window.scrollTo(0,0)}({location:n,previousLocation:r}),R("onRouteDidUpdate",{previousLocation:r,location:n}))}),[r,n]),t};function O(e){const t=Array.from(new Set([e,decodeURI(e)])).map((e=>(0,d.u)(u.A,e))).flat();return Promise.all(t.map((e=>e.route.component.preload?.())))}class D extends r.Component{previousLocation;routeUpdateCleanupCb;constructor(e){super(e),this.previousLocation=null,this.routeUpdateCleanupCb=l.A.canUseDOM?R("onRouteUpdate",{previousLocation:null,location:this.props.location}):()=>{},this.state={nextRouteHasLoaded:!0}}shouldComponentUpdate(e,t){if(e.location===this.props.location)return t.nextRouteHasLoaded;const n=e.location;return this.previousLocation=this.props.location,this.setState({nextRouteHasLoaded:!1}),this.routeUpdateCleanupCb=R("onRouteUpdate",{previousLocation:this.previousLocation,location:n}),O(n.pathname).then((()=>{this.routeUpdateCleanupCb(),this.setState({nextRouteHasLoaded:!0})})).catch((e=>{console.warn(e),window.location.reload()})),!1}render(){const{children:e,location:t}=this.props;return(0,p.jsx)(P,{previousLocation:this.previousLocation,location:t,children:(0,p.jsx)(c.qh,{location:t,render:()=>e})})}}const I=D,M="__docusaurus-base-url-issue-banner-container",F="__docusaurus-base-url-issue-banner",z="__docusaurus-base-url-issue-banner-suggestion-container";function B(e){return`\ndocument.addEventListener('DOMContentLoaded', function maybeInsertBanner() {\n var shouldInsert = typeof window['docusaurus'] === 'undefined';\n shouldInsert && insertBanner();\n});\n\nfunction insertBanner() {\n var bannerContainer = document.createElement('div');\n bannerContainer.id = '${M}';\n var bannerHtml = ${JSON.stringify(function(e){return`\n