julep-ai · HamadaSalhab · Oct 22, 2024 · Oct 19, 2024 · Oct 19, 2024 · Oct 19, 2024
diff --git a/README-CN.md b/README-CN.md
@@ -62,39 +62,34 @@
 
 <!-- START doctoc generated TOC please keep comment here to allow auto update -->
 <!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
-<h3>📖 目录</h3>
-
-- [简介](#introduction)
-- [主要特点](#key-features)
-- [快速示例](#quick-example)
-- [安装](#安装)
-- [Python 快速入门 🐍](#python-quick-start-)
-- [Node.js 快速入门🟩](#nodejs-quick-start-)
-- [步骤 1：创建代理](#step-1-create-an-agent)
-- [组件](#components)
-- [心智模型](#mental-model)
-- [概念](#concepts)
-- [理解任务](#understanding-tasks)
-- [任务的生命周期](#lifecycle-of-a-task)
-- [工作流步骤的类型](#types-of-workflow-steps)
-- [工具类型](#tool-types)
-- [用户定义的`函数`](#user-defined-functions)
-- [`系统` 工具](#system-tools)
-- [内置 `integrations`](#built-in-integrations)
--[直接`api_calls`]（#direct-api_calls）
-- [集成](#integrations)
-- [其他功能](#other-features)
-- [向代理添加工具](#adding-tools-to-agents)
-- [管理会话和用户](#managing-sessions-and-users)
-- [文档集成与搜索](#document-integration-and-search)
-- [参考](#reference)
-- [SDK 参考](#sdk-reference)
-- [API 参考](#api-reference)
-- [本地快速启动](#local-quickstart)
-- [Julep 和 LangChain 等有什么区别？](#julep 和 langchain 等之间有什么区别)
-- [不同用例](#different-use-cases)
-- [不同的外形尺寸](#different-form-factor)
-- [总结](#in-summary)
+<h3>📖 Table of Contents</h3>
+
+- [主要特点](#%E4%B8%BB%E8%A6%81%E7%89%B9%E7%82%B9)
+- [Python 快速入门🐍](#python-%E5%BF%AB%E9%80%9F%E5%85%A5%E9%97%A8)
+- [Node.js Quick Start 🟩](#nodejs-quick-start-)
+  - [Step 1: Create an Agent](#step-1-create-an-agent)
+- [Components](#components)
+  - [Mental Model](#mental-model)
+- [Concepts](#concepts)
+- [Understanding Tasks](#understanding-tasks)
+  - [Lifecycle of a Task](#lifecycle-of-a-task)
+  - [Types of Workflow Steps](#types-of-workflow-steps)
+- [Tool Types](#tool-types)
+  - [User-defined `functions`](#user-defined-functions)
+  - [`system` tools](#system-tools)
+  - [Built-in `integrations`](#built-in-integrations)
+  - [Direct `api_calls`](#direct-api_calls)
+- [Integrations](#integrations)
+- [Other Features](#other-features)
+  - [Adding Tools to Agents](#adding-tools-to-agents)
+  - [Managing Sessions and Users](#managing-sessions-and-users)
+  - [Document Integration and Search](#document-integration-and-search)
+  - [SDK 参考](#sdk-%E5%8F%82%E8%80%83)
+  - [API 参考](#api-%E5%8F%82%E8%80%83)
+- [本地快速启动](#%E6%9C%AC%E5%9C%B0%E5%BF%AB%E9%80%9F%E5%90%AF%E5%8A%A8)
+- [Julep 和 LangChain 等有什么区别？](#julep-%E5%92%8C-langchain-%E7%AD%89%E6%9C%89%E4%BB%80%E4%B9%88%E5%8C%BA%E5%88%AB)
+  - [不同的用例](#%E4%B8%8D%E5%90%8C%E7%9A%84%E7%94%A8%E4%BE%8B)
+  - [不同的外形尺寸](#%E4%B8%8D%E5%90%8C%E7%9A%84%E5%A4%96%E5%BD%A2%E5%B0%BA%E5%AF%B8)
 
 <!-- END doctoc generated TOC please keep comment here to allow auto update -->
 

diff --git a/README-FR.md b/README-FR.md
@@ -62,39 +62,39 @@ Des nouvelles passionnantes ! Nous participons au DevFest.AI tout au long du moi
 
 <!-- START doctoc generated TOC please keep comment here to allow auto update -->
 <!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
-<h3>📖 Table des matières</h3>
+<h3>📖 Table of Contents</h3>
 
-- [Présentation](#introduction)
-- [Caractéristiques principales](#key-features)
-- [Exemple rapide](#quick-example)
+- [Introduction](#introduction)
+- [Principales caractéristiques](#principales-caract%C3%A9ristiques)
+- [Exemple rapide](#exemple-rapide)
 - [Installation](#installation)
-- [Démarrage rapide de Python 🐍](#python-quick-start-)
-- [Démarrage rapide de Node.js 🟩](#nodejs-quick-start-)
-- [Étape 1 : Créer un agent](#step-1-create-an-agent)
-- [Composants](#composants)
-- [Modèle mental](#mental-model)
+- [Démarrage rapide de Python 🐍](#d%C3%A9marrage-rapide-de-python-)
+- [Node.js Quick Start 🟩](#nodejs-quick-start-)
+  - [Step 1: Create an Agent](#step-1-create-an-agent)
+- [Components](#components)
+  - [Mental Model](#mental-model)
 - [Concepts](#concepts)
-- [Comprendre les tâches](#understanding-tasks)
-- [Cycle de vie d'une tâche](#cycle-de-vie-d-une-tâche)
-- [Types d'étapes de flux de travail](#types-of-workflow-steps)
-- [Types d'outils](#types-d'outils)
-- [`Fonctions` définies par l'utilisateur](#user-defined-functions)
-- [outils système](#outils-système)
-- [`Intégrations` intégrées](#integrations-integrées)
-- [Appels directs `api_calls`](#appels directs-api_calls)
-- [Intégrations](#intégrations)
-- [Autres fonctionnalités](#other-features)
-- [Ajout d'outils aux agents](#adding-tools-to-agents)
-- [Gestion des sessions et des utilisateurs](#managing-sessions-and-users)
-- [Intégration et recherche de documents](#document-integration-and-search)
-- [Référence](#référence)
-- [Référence SDK](#sdk-reference)
-- [Référence API](#api-reference)
-- [Démarrage rapide local](#local-quickstart)
-- [Quelle est la différence entre Julep et LangChain etc ?](#quelle-est-la-différence-entre-julep-et-langchain-etc)
-- [Différents cas d'utilisation](#different-use-cases)
-- [Facteur de forme différent](#different-form-factor)
-- [En résumé](#en-resumé)
+- [Understanding Tasks](#understanding-tasks)
+  - [Lifecycle of a Task](#lifecycle-of-a-task)
+  - [Types of Workflow Steps](#types-of-workflow-steps)
+- [Tool Types](#tool-types)
+  - [User-defined `functions`](#user-defined-functions)
+  - [`system` tools](#system-tools)
+  - [Built-in `integrations`](#built-in-integrations)
+  - [Direct `api_calls`](#direct-api_calls)
+- [Integrations](#integrations)
+- [Other Features](#other-features)
+  - [Adding Tools to Agents](#adding-tools-to-agents)
+  - [Managing Sessions and Users](#managing-sessions-and-users)
+  - [Document Integration and Search](#document-integration-and-search)
+- [Référence](#r%C3%A9f%C3%A9rence)
+  - [Référence du SDK](#r%C3%A9f%C3%A9rence-du-sdk)
+  - [Référence API](#r%C3%A9f%C3%A9rence-api)
+- [Démarrage rapide local](#d%C3%A9marrage-rapide-local)
+- [Quelle est la différence entre Julep et LangChain etc ?](#quelle-est-la-diff%C3%A9rence-entre-julep-et-langchain-etc-)
+  - [Différents cas d'utilisation](#diff%C3%A9rents-cas-dutilisation)
+  - [Facteur de forme différent](#facteur-de-forme-diff%C3%A9rent)
+  - [En résumé](#en-r%C3%A9sum%C3%A9)
 
 <!-- END doctoc generated TOC please keep comment here to allow auto update -->
 

diff --git a/README-JA.md b/README-JA.md
@@ -62,39 +62,36 @@ Julep プロジェクトに新しい貢献者を迎えられることを嬉し
 
 <!-- START doctoc generated TOC please keep comment here to allow auto update -->
 <!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
-<h3>📖 目次</h3>
-
-- [はじめに](#introduction)
-- [主な特徴](#key-features)
-- [簡単な例](#quick-example)
-- [インストール](#installation)
-- [Python クイックスタート 🐍](#python-quick-start-)
-- [Node.js クイック スタート 🟩](#nodejs-quick-start-)
-- [ステップ 1: エージェントを作成する](#step-1-create-an-agent)
-- [コンポーネント](#components)
-- [メンタルモデル](#mental-model)
-- [コンセプト](#concepts)
-- [タスクの理解](#understanding-tasks)
-- [タスクのライフサイクル](#lifecycle-of-a-task)
-- [ワークフロー ステップの種類](#types-of-workflow-steps)
-- [ツールの種類](#tool-types)
-- [ユーザー定義の `functions`](#user-defined-functions)
-- [`システム` ツール](#system-tools)
-- [組み込みの `integrations`](#built-in-integrations)
-- [直接の `api_calls`](#direct-api_calls)
-- [統合](#integrations)
-- [その他の機能](#other-features)
-- [エージェントへのツールの追加](#adding-tools-to-agents)
-- [セッションとユーザーの管理](#managing-sessions-and-users)
-- [ドキュメントの統合と検索](#document-integration-and-search)
-- [参考](#reference)
-- [SDKリファレンス](#sdk-reference)
-- [APIリファレンス](#api-reference)
-- [ローカルクイックスタート](#local-quickstart)
-- [Julep と LangChain などの違いは何ですか?](#whats-the-difference-between-julep-and-langchain-etc)
-- [さまざまなユースケース](#different-use-cases)
-- [異なるフォームファクター](#different-form-factor)
-- [要約](#in-summary)
+<h3>📖 Table of Contents</h3>
+
+- [主な特徴](#%E4%B8%BB%E3%81%AA%E7%89%B9%E5%BE%B4)
+- [簡単な例](#%E7%B0%A1%E5%8D%98%E3%81%AA%E4%BE%8B)
+- [インストール](#%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%BC%E3%83%AB)
+- [Python クイックスタート 🐍](#python-%E3%82%AF%E3%82%A4%E3%83%83%E3%82%AF%E3%82%B9%E3%82%BF%E3%83%BC%E3%83%88-)
+- [Node.js Quick Start 🟩](#nodejs-quick-start-)
+  - [Step 1: Create an Agent](#step-1-create-an-agent)
+- [Components](#components)
+  - [Mental Model](#mental-model)
+- [Concepts](#concepts)
+- [Understanding Tasks](#understanding-tasks)
+  - [Lifecycle of a Task](#lifecycle-of-a-task)
+  - [Types of Workflow Steps](#types-of-workflow-steps)
+- [Tool Types](#tool-types)
+  - [User-defined `functions`](#user-defined-functions)
+  - [`system` tools](#system-tools)
+  - [Built-in `integrations`](#built-in-integrations)
+  - [Direct `api_calls`](#direct-api_calls)
+- [Integrations](#integrations)
+- [Other Features](#other-features)
+  - [Adding Tools to Agents](#adding-tools-to-agents)
+  - [Managing Sessions and Users](#managing-sessions-and-users)
+  - [Document Integration and Search](#document-integration-and-search)
+  - [SDK リファレンス](#sdk-%E3%83%AA%E3%83%95%E3%82%A1%E3%83%AC%E3%83%B3%E3%82%B9)
+  - [API リファレンス](#api-%E3%83%AA%E3%83%95%E3%82%A1%E3%83%AC%E3%83%B3%E3%82%B9)
+- [ローカルクイックスタート](#%E3%83%AD%E3%83%BC%E3%82%AB%E3%83%AB%E3%82%AF%E3%82%A4%E3%83%83%E3%82%AF%E3%82%B9%E3%82%BF%E3%83%BC%E3%83%88)
+- [Julep と LangChain などの違いは何ですか?](#julep-%E3%81%A8-langchain-%E3%81%AA%E3%81%A9%E3%81%AE%E9%81%95%E3%81%84%E3%81%AF%E4%BD%95%E3%81%A7%E3%81%99%E3%81%8B)
+  - [さまざまなユースケース](#%E3%81%95%E3%81%BE%E3%81%96%E3%81%BE%E3%81%AA%E3%83%A6%E3%83%BC%E3%82%B9%E3%82%B1%E3%83%BC%E3%82%B9)
+  - [異なるフォームファクタ](#%E7%95%B0%E3%81%AA%E3%82%8B%E3%83%95%E3%82%A9%E3%83%BC%E3%83%A0%E3%83%95%E3%82%A1%E3%82%AF%E3%82%BF)
 
 <!-- END doctoc generated TOC please keep comment here to allow auto update -->
 

diff --git a/agents-api/agents_api/autogen/Docs.py b/agents-api/agents_api/autogen/Docs.py
@@ -37,6 +37,10 @@ class CreateDocRequest(BaseModel):
     """
     Contents of the document
     """
+    embed_instruction: str | None = None
+    """
+    Instruction for the embedding model.
+    """
 
 
 class Doc(BaseModel):
@@ -113,6 +117,10 @@ class EmbedQueryRequest(BaseModel):
     """
     Text or texts to embed
     """
+    embed_instruction: str = ""
+    """
+    Instruction for the embedding model.
+    """
 
 
 class EmbedQueryResponse(BaseModel):

diff --git a/agents-api/agents_api/models/docs/create_doc.py b/agents-api/agents_api/models/docs/create_doc.py
@@ -67,6 +67,7 @@ def create_doc(
     data.metadata = data.metadata or {}
 
     doc_data = data.model_dump()
+    doc_data.pop("embed_instruction", None)
     content = doc_data.pop("content")
 
     doc_data["owner_type"] = owner_type

diff --git a/agents-api/agents_api/routers/docs/create_doc.py b/agents-api/agents_api/routers/docs/create_doc.py
@@ -6,7 +6,7 @@
 from temporalio.client import Client as TemporalClient
 
 from ...activities.types import EmbedDocsPayload
-from ...autogen.openapi_model import CreateDocRequest, ResourceCreatedResponse
+from ...autogen.openapi_model import CreateDocRequest, Doc, ResourceCreatedResponse
 from ...clients import temporal
 from ...common.retry_policies import DEFAULT_RETRY_POLICY
 from ...dependencies.developer_id import get_developer_id
@@ -21,6 +21,7 @@ async def run_embed_docs_task(
     doc_id: UUID,
     title: str,
     content: list[str],
+    embed_instruction: str | None = None,
     job_id: UUID,
     background_tasks: BackgroundTasks,
     client: TemporalClient | None = None,
@@ -34,7 +35,7 @@ async def run_embed_docs_task(
         doc_id=doc_id,
         content=content,
         title=title,
-        embed_instruction=None,
+        embed_instruction=embed_instruction,
     )
 
     handle = await client.start_workflow(
@@ -60,7 +61,7 @@ async def create_user_doc(
     x_developer_id: Annotated[UUID, Depends(get_developer_id)],
     background_tasks: BackgroundTasks,
 ) -> ResourceCreatedResponse:
-    doc = create_doc_query(
+    doc: Doc = create_doc_query(
         developer_id=x_developer_id,
         owner_type="user",
         owner_id=user_id,
@@ -74,6 +75,7 @@ async def create_user_doc(
         doc_id=doc.id,
         title=doc.title,
         content=doc.content,
+        embed_instruction=data.embed_instruction,
         job_id=embed_job_id,
         background_tasks=background_tasks,
     )
@@ -90,7 +92,7 @@ async def create_agent_doc(
     x_developer_id: Annotated[UUID, Depends(get_developer_id)],
     background_tasks: BackgroundTasks,
 ) -> ResourceCreatedResponse:
-    doc = create_doc_query(
+    doc: Doc = create_doc_query(
         developer_id=x_developer_id,
         owner_type="agent",
         owner_id=agent_id,
@@ -104,6 +106,7 @@ async def create_agent_doc(
         doc_id=doc.id,
         title=doc.title,
         content=doc.content,
+        embed_instruction=data.embed_instruction,
         job_id=embed_job_id,
         background_tasks=background_tasks,
     )

diff --git a/agents-api/agents_api/routers/docs/embed.py b/agents-api/agents_api/routers/docs/embed.py
@@ -21,7 +21,8 @@ async def embed(
     text_to_embed: list[str] = (
         [text_to_embed] if isinstance(text_to_embed, str) else text_to_embed
     )
-
-    vectors = await litellm.aembedding(inputs=text_to_embed)
+    vectors = await litellm.aembedding(
+        inputs=[data.embed_instruction + text for text in text_to_embed]
+    )
 
     return EmbedQueryResponse(vectors=vectors)
diff --git a/agents-api/notebooks/RecSum-experiments.ipynb b/agents-api/notebooks/RecSum-experiments.ipynb
@@ -145,7 +145,7 @@
     "\n",
     "\n",
     "def chat():\n",
-    "    while (user_input := input(\"You: \").lower()) != \"bye\": \n",
+    "    while (user_input := input(\"You: \").lower()) != \"bye\":\n",
     "        chat_session.append(user(user_input))\n",
     "\n",
     "        result = generate(chat_session)\n",