feat: New updates on the SDK (#12)

* feat: updated the code to new APIs structure * feat: adding the embeddings api * feat: adding test cases * feat: embedding APIs * fix: minor changes on tsconfig * fix: minor changes * feat: adding the new prompts API * feat: adding the embeddings api * fix: updating the embeddings API * fix: updating the baseurl and routes * feat: post api for proxy and minor changes on the urls * fix: adding the postmethdo file * fix: updating the test cases * fix: adding yarn.lock file * feat: adding the CI pipeline for publishing to NPM on release * fix: making portkey the default export * docs: adding an example docs * feat: adding commit checker * fix: updating the commit checker * fix: updating the commit checker * fix: updating the commit checker * fix: updating the commit checker * feat: adding feedback routes * fix: adding streaming to feedbacks and override configs in APIs * feat: over-ride of the params in chat and completions route * fix: feedbacks to accept array as input * fix: config override * fix: adding the embeddings api in client * fix: changing traceID to trace_id * fix: adding traceid type * fix: adding the tracid correction * feat: added the getHeaders function for each response in non-streaming mode * feat: added the completions method on embeddings * feat: added Llamaindex integration in portkey * fix: removing the langchain folder * fix: fixed override of configs with empty updated config. Also added an isempty check function * fix: added langchainjs * fix: updating the type * fix: overwriting the config everytime * fix: removing empty values on the headers * fix: embeddings and prompts completion * fix: handling last package in streaming mode * fix: minor fix * fix: update on the url of prompts api * fix: adding stream to prompts body * fix: updating the promptId to promptID * feat: adding authorization param in the client * fix: updating the post method * fix: fixing the camel case issue in the body * doc: Udpating the readme file with the latest changes * doc: URL update and contributing guidelines added * feat: version upgrade to 1.0.0
Portkey-AI · Dec 8, 2023 · df889c8 · df889c8
1 parent 9b4d860
commit df889c8
Show file tree

Hide file tree

Showing 43 changed files with 15,673 additions and 1,757 deletions.
diff --git a/.eslintrc.js b/.eslintrc.js
@@ -0,0 +1,13 @@
+module.exports = {
+    root: true,
+    parser: "@typescript-eslint/parser",
+    plugins: ["@typescript-eslint"],
+    extends: [
+        "eslint:recommended",
+        "plugin:@typescript-eslint/recommended",
+        "prettier",
+    ],
+    rules: {
+        'no-unused-vars': 'off',
+    }
+};
diff --git a/.github/workflows/commit-checker.yml b/.github/workflows/commit-checker.yml
@@ -0,0 +1,11 @@
+name: verify-conventional-commits
+
+on: [pull_request]
+
+jobs:
+  conventional-commits-checker:
+    runs-on: ubuntu-latest
+    steps:
+      - name: verify conventional commits
+        uses: taskmedia/[email protected]
+
diff --git a/.github/workflows/node-publish.yml b/.github/workflows/node-publish.yml
@@ -0,0 +1,18 @@
+name: Publish Package to npmjs
+on:
+  release:
+    types: [published]
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      # Setup .npmrc file to publish to npm
+      - uses: actions/setup-node@v3
+        with:
+          node-version: '20.x'
+          registry-url: 'https://registry.npmjs.org'
+      - run: npm ci
+      - run: npm run build && npm publish
+        env:
+          NODE_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
diff --git a/README.md b/README.md
@@ -36,17 +36,18 @@ $ export PORTKEY_API_KEY="PORTKEY_API_KEY"
 #### Now, let's make a request with GPT-4
 
 ```js
-import { Portkey } from "portkey-ai";
+import Portkey from 'portkey-ai';
 
+// Construct a client with a virtual key
 const portkey = new Portkey({
-    mode: "single",
-    llms: [{ provider: "openai", virtual_key: "open-ai-xxx" }]
-});
+    apiKey: "PORTKEY_API_KEY",
+    virtualKey: "VIRTUAL_KEY"
+})
 
 async function main() {
     const chatCompletion = await portkey.chat.completions.create({
         messages: [{ role: 'user', content: 'Say this is a test' }],
-        model: 'gpt-4'
+        model: 'gpt-3.5-turbo',
     });
 
     console.log(chatCompletion.choices);
@@ -58,104 +59,6 @@ main();
 Portkey fully adheres to the OpenAI SDK signature. This means that you can instantly switch to Portkey and start using Portkey's advanced production features right out of the box.
 
 
-## **🪜 Detailed Integration Guide**
-
-**There are 4️ Steps to Integrate Portkey**
-1. Setting your Portkey API key and your virtual key for AI providers.
-2. Constructing your LLM with Portkey features, provider features (and prompt!).
-3. Constructing the Portkey client and setting usage mode.
-4. Making your request!
-
-Let's dive in! If you are an advanced user and want to directly jump to various full-fledged examples, [click here](https://github.com/Portkey-AI/portkey-node-sdk/blob/main/examples).
-
----
-
-### **Step 1️ : Get your Portkey API Key and your Virtual Keys for AI providers**
-
-**Portkey API Key:** Log into [Portkey here](https://app.portkey.ai/), then click on the profile icon on top left and “Copy API Key”.
-```bash
-export PORTKEY_API_KEY="PORTKEY_API_KEY"
-```
-**Virtual Keys:** Navigate to the "Virtual Keys" page on [Portkey](https://app.portkey.ai/) and hit the "Add Key" button. Choose your AI provider and assign a unique name to your key. Your virtual key is ready!
-
-### **Step 2️ : Construct your LLM, add Portkey features, provider features, and prompt**
-
-**Portkey Features**:
-You can find a comprehensive [list of Portkey features here](#📔-list-of-portkey-features). This includes settings for caching, retries, metadata, and more.
-
-**Provider Features**:
-Portkey is designed to be flexible. All the features you're familiar with from your LLM provider, like `top_p`, `top_k`, and `temperature`, can be used seamlessly. Check out the [complete list of provider features here](https://github.com/Portkey-AI/portkey-node-sdk/blob/539021dcae8fa0945cf7f0b8c27fc26a7dd56092/src/_types/portkeyConstructs.ts#L34).
-
-**Setting the Prompt Input**:
-This param lets you override any prompt that is passed during the completion call - set a model-specific prompt here to optimise the model performance. You can set the input in two ways. For models like Claude and GPT3, use `prompt` = `(str)`, and for models like GPT3.5 & GPT4, use `messages` = `[array]`.
-
-Here's how you can combine everything:
-
-```js
-import { LLMOptions } from "portkey-ai";
-
-// Portkey Config
-const provider = "openai";
-const virtual_key = "open-ai-xxx";
-const trace_id = "portkey_sdk_test";
-const cache_status = "semantic";
-
-// Model Params
-const model = "gpt-4";
-const temperature = 1;
-
-// Prompt
-const messages = [{"role": "user", "content": "Who are you?"}];
-
-const llm_a: LLMOptions = {
-    provider: provider,
-    virtual_key: virtual_key,
-    cache_status: cache_status,
-    trace_id: trace_id,
-    model: model,
-    temperature: temperature,
-    messages: messages
-};
-
-```
-
-### **Step 3️ : Construct the Portkey Client**
-
-Portkey client's config takes 3 params: `api_key`, `mode`, `llms`.
-
-* `api_key`: You can set your Portkey API key here or with `$ EXPORT` as done above.
-* `mode`: There are **3** modes - Single, Fallback, Loadbalance.
-  * **Single** - This is the standard mode. Use it if you do not want Fallback OR Loadbalance features.
-  * **Fallback** - Set this mode if you want to enable the Fallback feature.
-  * **Loadbalance** - Set this mode if you want to enable the Loadbalance feature. 
-* `llms`: This is an array where we pass our LLMs constructed using the LLMOptions interface.
-
-```js
-import { Portkey } from "portkey-ai";
-
-const portkey = new Portkey({ mode: "single", llms: [llm_a] });
-```
-
-### **Step 4️ : Call the Portkey Client!**
-
-The Portkey client can do `ChatCompletions` and `Completions` calls.
-
-Since our LLM is GPT4, we will use ChatCompletions:
-
-```js
-async function main() {
-    const response = await portkey.chatCompletions.create({
-        messages: [{ "role": "user", "content": "Who are you ?"}]
-    });
-    console.log(response.choices[0].message);
-};
-
-main();
-```
-
-You have integrated Portkey's Node SDK in just 4 steps!
-
----
 
 
 ## **📔 List of Portkey Features**
@@ -189,7 +92,10 @@ You can set all of these features while constructing your LLMOptions object.
 
 ---
 
-#### [📝 Full Documentation](https://docs.portkey.ai/) | [🛠️ Integration Requests](https://github.com/Portkey-AI/portkey-node-sdk/issues) | 
+#### [📝 Full Documentation](https://docs.portkey.ai/docs) | [🛠️ Integration Requests](https://github.com/Portkey-AI/portkey-node-sdk/issues) | 
 
 <a href="https://twitter.com/intent/follow?screen_name=portkeyai"><img src="https://img.shields.io/twitter/follow/portkeyai?style=social&logo=twitter" alt="follow on Twitter"></a>
 <a href="https://discord.gg/sDk9JaNfK8" target="_blank"><img src="https://img.shields.io/discord/1143393887742861333?logo=discord" alt="Discord"></a>
+
+## **🛠️ Contributing**
+Get started by checking out Github issues. Feel free to open an issue, or reach out if you would like to add to the project!
diff --git a/babel.config.js b/babel.config.js
@@ -0,0 +1,6 @@
+module.exports = {
+    presets: [
+        ['@babel/preset-env', { targets: { node: 'current' } }],
+        '@babel/preset-typescript',
+    ],
+};
diff --git a/build b/build
@@ -0,0 +1,27 @@
+
+#!/usr/bin/env bash
+set -exuo pipefail
+
+node scripts/check-version.cjs
+
+# Build into dist and will publish the package from there,
+# so that src/resources/foo.ts becomes <package root>/resources/foo.js
+# This way importing from `"portkey-ai/apis/foo"` works
+# even with `"moduleResolution": "node"`
+
+rm -rf dist; mkdir dist
+
+# Copy src to dist/src and build from dist/src into dist, so that
+# the source map for index.js.map will refer to ./src/index.ts etc
+cp -rp src README.md dist
+# Copy the changelog and license files tp dist
+for file in LICENSE CHANGELOG.md; do
+  if [ -e "${file}" ]; then cp "${file}" dist; fi
+done
+
+# this converts the export map paths for the dist directory
+# and does a few other minor things
+node scripts/make-dist-package-json.cjs > dist/package.json
+
+# build to .js/.mjs/.d.ts files
+npm exec tsc-multi
diff --git a/examples/demo.ts b/examples/demo.ts
@@ -1,35 +1,23 @@
-import { Portkey } from "../src";
+import { config } from 'dotenv';
+import Portkey from '../src';
 
-const client = new Portkey({
-    mode: "fallback",
-    llms: [{
-        provider: "openai",
-        virtual_key: "openai-v"
-    }]
-});
+config({ override: true })
 
-const messages = [
-    { content: "You want to talk in rhymes.", role: "system" },
-    { content: "Hello, world!", role: "user" },
-    { content: "Hello!", role: "assistant" },
-    {
-        content:
-            "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
-        role: "user",
-    },
-]
+// Initialize the Portkey client
+const portkey = new Portkey({
+    apiKey: process.env["PORTKEY_API_KEY"] ?? "",
+    baseURL: "https://api.portkeydev.com/v1",
+    provider: "openai",
+    virtualKey: process.env["OPENAI_VIRTUAL_KEY"] ?? ""
+});
 
-const prompt = "write a story about a king"
+// Generate a text completion
+async function getTextCompletion() {
+    const completion = await portkey.completions.create({
+        prompt: "Say this is a test",
+        model: "gpt-3.5-turbo-instruct",
+    });
 
-async function main() {
-    const params = {}
-    const res = await client.chatCompletions.create({ messages, ...params, stream: true })
-    for await (const completion of res) {
-        process.stdout.write(completion.choices[0]?.delta?.content || "");
-    }
+    console.log(completion.choices[0]?.text);
 }
-
-main().catch((err) => {
-    console.error(err);
-    process.exit(1);
-});
+getTextCompletion();
diff --git a/examples/fallback.ts b/examples/fallback.ts
@@ -1,20 +1,20 @@
-import { Portkey } from "../src";
+// import { Portkey } from "../src";
 
-const portkey = new Portkey({
-    apiKey:"your-portkey-api-key",
-    mode: "fallback",
-    llms: [
-        { provider: "openai", virtual_key: "open-ai-key-1234", trace_id: "1234", metadata: { hello: "world" } },
-        { provider: "cohere", virtual_key: "cohere-api-key-1234", trace_id: "1234", metadata: { hello: "world" } },
-    ]
-});
+// const portkey = new Portkey({
+//     apiKey:"your-portkey-api-key",
+//     mode: "fallback",
+//     llms: [
+//         { provider: "openai", virtual_key: "open-ai-key-1234", trace_id: "1234", metadata: { hello: "world" } },
+//         { provider: "cohere", virtual_key: "cohere-api-key-1234", trace_id: "1234", metadata: { hello: "world" } },
+//     ]
+// });
 
-async function main() {
-    const chatCompletion = await portkey.chatCompletions.create({
-        messages: [{ role: 'user', content: 'Say this is a test' }],
-    });
+// async function main() {
+//     const chatCompletion = await portkey.chatCompletions.create({
+//         messages: [{ role: 'user', content: 'Say this is a test' }],
+//     });
 
-    console.log(chatCompletion.choices);
-};
+//     console.log(chatCompletion.choices);
+// };
 
-main();
+// main();
diff --git a/examples/promptGeneration.ts b/examples/promptGeneration.ts
@@ -1,16 +1,16 @@
-import { Portkey } from "../src";
+// import { Portkey } from "../src";
 
-const portkey = new Portkey({
-    mode: "fallback"
-});
+// const portkey = new Portkey({
+//     mode: "fallback"
+// });
 
-async function main() {
-    const chatCompletion = await portkey.generations.create({
-        promptId: "your-prompt-id",
-        // variables: {hello: "world"} # Add variables if required
-    });
+// async function main() {
+//     const chatCompletion = await portkey.generations.create({
+//         promptId: "your-prompt-id",
+//         // variables: {hello: "world"} # Add variables if required
+//     });
 
-    console.log(chatCompletion.data);
-};
+//     console.log(chatCompletion.data);
+// };
 
-main();
+// main();