Dindn't solve all conflicts in previous commit

.gitignore

@@ -4,3 +4,4 @@ __pycache__
 .DS_Store
 .venv
 _scripts
+*.env

app/dtos/user_batch.py

@@ -1,30 +1,35 @@
-import uuid
+import uuid
-from typing import Optional
+from typing import Optional
-
+
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field
-
+
-
+
-class DemographicInfo(BaseModel):
+class DemographicInfo(BaseModel):
-    phone: str
+  phone: str
-    passport_id: Optional[str] = None
+  passport_id: Optional[str] = None
-    country: Optional[str] = None
+  country: Optional[str] = None
-
+
-
+class Entity(BaseModel):
-class UserDTO(BaseModel):
+	id: str
-    id: uuid.UUID = Field(default_factory=uuid.uuid4)
+	role: str
-    email: str
+
-    name: str
+
-    type: str
+class UserDTO(BaseModel):
-    passport_id: str
+  id: uuid.UUID = Field(default_factory=uuid.uuid4)
-    passwordHash: str
+  email: str
-    passwordSalt: str
+  name: str
-    groupName: Optional[str] = None
+  type: str
-    corporate: Optional[str] = None
+  passport_id: str
-    studentID: Optional[str | int] = None
+  passwordHash: str
-    expiryDate: Optional[str] = None
+  passwordSalt: str
-    demographicInformation: Optional[DemographicInfo] = None
+  groupName: Optional[str] = None
-
+  corporate: Optional[str] = None
-
+  studentID: Optional[str] = None
-class BatchUsersDTO(BaseModel):
+  expiryDate: Optional[str] = None
-    makerID: str
+  demographicInformation: Optional[DemographicInfo] = None
-    users: list[UserDTO]
+  entities: list[dict] = Field(default_factory=list)
+
+
+class BatchUsersDTO(BaseModel):
+  makerID: str
+  users: list[UserDTO]

app/services/impl/training/training.py

@@ -96,7 +96,9 @@ class TrainingService(ITrainingService):
         for area in training_content.weak_areas:
             weak_areas["weak_areas"].append(area.dict())
 
+        new_id = str(uuid.uuid4())
         training_doc = {
+            'id': new_id,
             'created_at': int(datetime.now().timestamp() * 1000),
             **exam_map,
             **usefull_tips.dict(),
@@ -105,6 +107,7 @@ class TrainingService(ITrainingService):
         }
         doc_id = await self._db.save_to_db('training', training_doc)
         return {
+            "id": new_id
             "id": doc_id
         }
 

app/services/impl/user.py

@@ -7,6 +7,11 @@ import shortuuid
 
 from datetime import datetime
 from logging import getLogger
+
+import pandas as pd
+from typing import Dict
+
+import shortuuid
 from pymongo.database import Database
 
 from app.dtos.user_batch import BatchUsersDTO, UserDTO
@@ -49,6 +54,15 @@ class UserService(IUserService):
         FileHelper.remove_file(path)
         return {"ok": True}
 
+    @staticmethod
+    def _map_to_batch(request_data: Dict) -> BatchUsersDTO:
+        users_list = [{**user} for user in request_data["users"]]
+        for user in users_list:
+            user["studentID"] = str(user["studentID"])
+
+        users: list[UserDTO] = [UserDTO(**user) for user in users_list]
+        return BatchUsersDTO(makerID=request_data["makerID"], users=users)
+
     @staticmethod
     def _generate_firebase_auth_csv(batch_dto: BatchUsersDTO, path: str):
         # https://firebase.google.com/docs/cli/auth#file_format
@@ -119,12 +133,6 @@ class UserService(IUserService):
             self._insert_new_user(user)
             code = self._create_code(user, maker_id)
 
-            if user.type == "corporate":
-                self._set_corporate_default_groups(user)
-
-            if user.corporate:
-                self._assign_corporate_to_user(user, code)
-
             if user.groupName and len(user.groupName.strip()) > 0:
                 self._assign_user_to_group_by_name(user, maker_id)
 
@@ -144,7 +152,8 @@ class UserService(IUserService):
             'isFirstLogin': False,
             'isVerified': True,
             'registrationDate': datetime.now(),
-            'subscriptionExpirationDate': user.expiryDate
+            'subscriptionExpirationDate': user.expiryDate,
+            'entities': user.entities
         }
         self._db.users.insert_one(new_user)
 
@@ -164,74 +173,6 @@ class UserService(IUserService):
         })
         return code
 
-    def _set_corporate_default_groups(self, user: UserDTO):
-        user_id = str(user.id)
-        default_groups = [
-            {
-                'admin': user_id,
-                'id': str(uuid.uuid4()),
-                'name': "Teachers",
-                'participants': [],
-                'disableEditing': True,
-            },
-            {
-                'admin': user_id,
-                'id': str(uuid.uuid4()),
-                'name': "Students",
-                'participants': [],
-                'disableEditing': True,
-            },
-            {
-                'admin': user_id,
-                'id': str(uuid.uuid4()),
-                'name': "Corporate",
-                'participants': [],
-                'disableEditing': True,
-            }
-        ]
-        for group in default_groups:
-            self._db.groups.insert_one(group)
-
-    def _assign_corporate_to_user(self, user: UserDTO, code: str):
-        user_id = str(user.id)
-        corporate_user = self._db.users.find_one(
-            {"email": user.corporate}
-        )
-        if corporate_user:
-            self._db.codes.update_one(
-                {"id": code},
-                {"$set": {"creator": corporate_user["id"]}},
-                upsert=True
-            )
-            group_type = "Students" if user.type == "student" else "Teachers"
-
-            group = self._db.groups.find_one(
-                {
-                    "admin": corporate_user["id"],
-                    "name": group_type
-                }
-            )
-
-            if group:
-                participants = group['participants']
-                if user_id not in participants:
-                    participants.append(user_id)
-                    self._db.groups.update_one(
-                        {"id": group["id"]},
-                        {"$set": {"participants": participants}}
-                    )
-
-            else:
-                group = {
-                    'admin': corporate_user["id"],
-                    'id': str(uuid.uuid4()),
-                    'name': group_type,
-                    'participants': [user_id],
-                    'disableEditing': True,
-                }
-
-                self._db.groups.insert_one(group)
-
     def _assign_user_to_group_by_name(self, user: UserDTO, maker_id: str):
         user_id = str(user.id)
 

elai/AvatarEnum.py

@@ -0,0 +1,62 @@
+from enum import Enum
+
+
+class AvatarEnum(Enum):
+    # Works
+    GIA_BUSINESS = {
+        "avatar_code": "gia.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/gia/business/gia_business.png",
+        "avatar_canvas": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/gia/business/gia_business.png",
+        "voice_id": "EXAVITQu4vr4xnSDxMaL",
+        "voice_provider": "elevenlabs"
+    }
+    # Works
+    VADIM_BUSINESS = {
+        "avatar_code": "vadim.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/vadim/business/vadim_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/vadim/business/vadim_business.png",
+        "voice_id": "flq6f7yk4E4fJM5XTYuZ",
+        "voice_provider": "elevenlabs"
+    }
+    ORHAN_BUSINESS = {
+        "avatar_code": "orhan.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/orhan/business/orhan.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/orhan/business/orhan.png",
+        "voice_id": "en-US-AndrewMultilingualNeural",
+        "voice_provider": "azure"
+    }
+    FLORA_BUSINESS = {
+        "avatar_code": "flora.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/flora/business/flora_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/flora/business/flora_business.png",
+        "voice_id": "en-US-JaneNeural",
+        "voice_provider": "azure"
+    }
+    SCARLETT_BUSINESS = {
+        "avatar_code": "scarlett.business",
+        "avatar_gender": "female",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/scarlett/business/scarlett_business.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/scarlett/business/scarlett_business.png",
+        "voice_id": "en-US-NancyNeural",
+        "voice_provider": "azure"
+    }
+    PARKER_CASUAL = {
+        "avatar_code": "parker.casual",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/parker/casual/parker_casual.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/parker/casual/parker_casual.png",
+        "voice_id": "en-US-TonyNeural",
+        "voice_provider": "azure"
+    }
+    ETHAN_BUSINESS = {
+        "avatar_code": "ethan.business",
+        "avatar_gender": "male",
+        "avatar_url": "https://elai-avatars.s3.us-east-2.amazonaws.com/common/ethan/business/ethan_business_low.png",
+        "avatar_canvas": "https://d3u63mhbhkevz8.cloudfront.net/common/ethan/business/ethan_business_low.png",
+        "voice_id": "en-US-JasonNeural",
+        "voice_provider": "azure"
+    }

elai/filter_json.py

@@ -0,0 +1,18 @@
+import json
+
+# Read JSON from a file
+input_filename = "english_voices.json"
+output_filename = "free_english_voices.json"
+
+with open(input_filename, "r") as json_file:
+    data = json.load(json_file)
+
+# Filter entries based on "language": "English"
+filtered_list = [entry for entry in data["data"]["list"] if not entry["is_paid"]]
+data["data"]["list"] = filtered_list
+
+# Write filtered JSON to a new file
+with open(output_filename, "w") as json_file:
+    json.dump(data, json_file, indent=2)
+
+print(f"Filtered JSON written to '{output_filename}'.")

helper/elai_api.py

@@ -0,0 +1,263 @@
+import os
+import random
+import time
+from logging import getLogger
+
+import requests
+from dotenv import load_dotenv
+
+from helper.constants import *
+from helper.firebase_helper import upload_file_firebase_get_url, save_to_db_with_id
+from elai.AvatarEnum import AvatarEnum
+
+load_dotenv()
+
+logger = getLogger(__name__)
+
+# Get ELAI token
+TOKEN = os.getenv("ELAI_TOKEN")
+FIREBASE_BUCKET = os.getenv('FIREBASE_BUCKET')
+
+# POST TO CREATE VIDEO
+POST_HEADER = {
+    "accept": "application/json",
+    "content-type": "application/json",
+    "Authorization": f"Bearer {TOKEN}"
+}
+GET_HEADER = {
+    "accept": "application/json",
+    "Authorization": f"Bearer {TOKEN}"
+}
+
+
+def create_videos_and_save_to_db(exercises, template, id):
+    avatar = random.choice(list(AvatarEnum))
+    # Speaking 1
+    # Using list comprehension to find the element with the desired value in the 'type' field
+    found_exercises_1 = [element for element in exercises if element.get('type') == 1]
+    # Check if any elements were found
+    if found_exercises_1:
+        exercise_1 = found_exercises_1[0]
+        sp1_questions = []
+        logger.info('Creating video for speaking part 1')
+        for question in exercise_1["questions"]:
+            sp1_result = create_video(question, avatar)
+            if sp1_result is not None:
+                sound_file_path = VIDEO_FILES_PATH + sp1_result
+                firebase_file_path = FIREBASE_SPEAKING_VIDEO_FILES_PATH + sp1_result
+                url = upload_file_firebase_get_url(FIREBASE_BUCKET, firebase_file_path, sound_file_path)
+                video = {
+                    "text": question,
+                    "video_path": firebase_file_path,
+                    "video_url": url
+                }
+                sp1_questions.append(video)
+            else:
+                logger.error("Failed to create video for part 1 question: " + exercise_1["question"])
+        template["exercises"][0]["prompts"] = sp1_questions
+        template["exercises"][0]["first_title"] = exercise_1["first_topic"]
+        template["exercises"][0]["second_title"] = exercise_1["second_topic"]
+
+    # Speaking 2
+    # Using list comprehension to find the element with the desired value in the 'type' field
+    found_exercises_2 = [element for element in exercises if element.get('type') == 2]
+    # Check if any elements were found
+    if found_exercises_2:
+        exercise_2 = found_exercises_2[0]
+        logger.info('Creating video for speaking part 2')
+        sp2_result = create_video(exercise_2["question"], avatar)
+        if sp2_result is not None:
+            sound_file_path = VIDEO_FILES_PATH + sp2_result
+            firebase_file_path = FIREBASE_SPEAKING_VIDEO_FILES_PATH + sp2_result
+            url = upload_file_firebase_get_url(FIREBASE_BUCKET, firebase_file_path, sound_file_path)
+            sp2_video_path = firebase_file_path
+            sp2_video_url = url
+            template["exercises"][1]["prompts"] = exercise_2["prompts"]
+            template["exercises"][1]["text"] = exercise_2["question"]
+            template["exercises"][1]["title"] = exercise_2["topic"]
+            template["exercises"][1]["video_url"] = sp2_video_url
+            template["exercises"][1]["video_path"] = sp2_video_path
+        else:
+            logger.error("Failed to create video for part 2 question: " + exercise_2["question"])
+
+    # Speaking 3
+    # Using list comprehension to find the element with the desired value in the 'type' field
+    found_exercises_3 = [element for element in exercises if element.get('type') == 3]
+    # Check if any elements were found
+    if found_exercises_3:
+        exercise_3 = found_exercises_3[0]
+        sp3_questions = []
+        logger.info('Creating videos for speaking part 3')
+        for question in exercise_3["questions"]:
+            result = create_video(question, avatar)
+            if result is not None:
+                sound_file_path = VIDEO_FILES_PATH + result
+                firebase_file_path = FIREBASE_SPEAKING_VIDEO_FILES_PATH + result
+                url = upload_file_firebase_get_url(FIREBASE_BUCKET, firebase_file_path, sound_file_path)
+                video = {
+                    "text": question,
+                    "video_path": firebase_file_path,
+                    "video_url": url
+                }
+                sp3_questions.append(video)
+            else:
+                logger.error("Failed to create video for part 3 question: " + question)
+        template["exercises"][2]["prompts"] = sp3_questions
+        template["exercises"][2]["title"] = exercise_3["topic"]
+
+    if not found_exercises_3:
+        template["exercises"].pop(2)
+    if not found_exercises_2:
+        template["exercises"].pop(1)
+    if not found_exercises_1:
+        template["exercises"].pop(0)
+
+    save_to_db_with_id("speaking", template, id)
+    logger.info('Saved speaking to DB with id ' + id + " : " + str(template))
+
+
+def create_video(text, avatar):
+    # POST TO CREATE VIDEO
+    create_video_url = "https://apis.elai.io/api/v1/videos"
+
+    avatar_url = AvatarEnum[avatar].value.get("avatar_url")
+    avatar_code = AvatarEnum[avatar].value.get("avatar_code")
+    avatar_gender = AvatarEnum[avatar].value.get("avatar_gender")
+    avatar_canvas = AvatarEnum[avatar].value.get("avatar_canvas")
+    voice_id = AvatarEnum[avatar].value.get("voice_id")
+    voice_provider = AvatarEnum[avatar].value.get("voice_provider")
+
+    data = {
+        "name": "API test",
+        "slides": [
+            {
+                "id": 1,
+                "canvas": {
+                    "objects": [
+                        {
+                            "type": "avatar",
+                            "left": 151.5,
+                            "top": 36,
+                            "fill": "#4868FF",
+                            "scaleX": 0.3,
+                            "scaleY": 0.3,
+                            "width": 1080,
+                            "height": 1080,
+                            "src": avatar_url,
+                            "avatarType": "transparent",
+                            "animation": {
+                                "type": None,
+                                "exitType": None
+                            }
+                        },
+                        {
+                            "type": "image",
+                            "version": "5.3.0",
+                            "originX": "left",
+                            "originY": "top",
+                            "left": 30,
+                            "top": 30,
+                            "width": 800,
+                            "height": 600,
+                            "fill": "rgb(0,0,0)",
+                            "stroke": None,
+                            "strokeWidth": 0,
+                            "strokeDashArray": None,
+                            "strokeLineCap": "butt",
+                            "strokeDashOffset": 0,
+                            "strokeLineJoin": "miter",
+                            "strokeUniform": False,
+                            "strokeMiterLimit": 4,
+                            "scaleX": 0.18821429,
+                            "scaleY": 0.18821429,
+                            "angle": 0,
+                            "flipX": False,
+                            "flipY": False,
+                            "opacity": 1,
+                            "shadow": None,
+                            "visible": True,
+                            "backgroundColor": "",
+                            "fillRule": "nonzero",
+                            "paintFirst": "fill",
+                            "globalCompositeOperation": "source-over",
+                            "skewX": 0,
+                            "skewY": 0,
+                            "cropX": 0,
+                            "cropY": 0,
+                            "id": 676845479989,
+                            "src": "https://d3u63mhbhkevz8.cloudfront.net/production/uploads/66f5190349f943682dd776ff/"
+                                   "en-coach-main-logo-800x600_sm1ype.jpg?Expires=1727654400&Policy=eyJTdGF0ZW1lbnQiOlt"
+                                   "7IlJlc291cmNlIjoiaHR0cHM6Ly9kM3U2M21oYmhrZXZ6OC5jbG91ZGZyb250Lm5ldC9wcm9kdWN0aW9uL3"
+                                   "VwbG9hZHMvNjZmNTE5MDM0OWY5NDM2ODJkZDc3NmZmL2VuLWNvYWNoLW1haW4tbG9nby04MDB4NjAwX3NtM"
+                                   "XlwZS5qcGciLCJDb25kaXRpb24iOnsiRGF0ZUxlc3NUaGFuIjp7IkFXUzpFcG9jaFRpbWUiOjE3Mjc2NTQ0"
+                                   "MDB9fX1dfQ__&Signature=kTVzlDeS7cua2HiAE5G%7E-yFqbhu0bHraFH5SauUln7yuNXoX7vtiKIBYiL"
+                                   "%7Eps3LCLEZS77arSZ7H%7EG8CKzabHDjAR-Y6Uc%7ELD5KQaMmk0jbAxbC3Wdoq6cfd0qIwEuodQYlC0It"
+                                   "2WBidP8KsgOy3uUQ%7EvcBoqlb255yMFw4pHuptOBB1kPs%7EFyzDV0fnRNsKaYRcy0Fn2EFUp13axm0CZQ"
+                                   "clazuLFM622AyCydKMy0vfxV%7Etny3sskwPaUe2OANGMFg07Q1pRuy6fUON0DsbhAh1tA2H6-nnem5KbFw"
+                                   "iZK3IIwwYGBx3H41ovzC6Ejt80Fd0%7EPSHw7GzVBnUmtP-IA__&Key-Pair-Id=K1Y7U91AR6T7E5",
+                            "crossOrigin": "anonymous",
+                            "filters": [],
+                            "_exists": True
+                        }
+                    ],
+                    "background": "#ffffff",
+                    "version": "4.4.0"
+                },
+                "avatar": {
+                    "code": avatar_code,
+                    "gender": avatar_gender,
+                    "canvas": avatar_canvas
+                },
+                "animation": "fade_in",
+                "language": "English",
+                "speech": text,
+                "voice": voice_id,
+                "voiceType": "text",
+                "voiceProvider": voice_provider
+            }
+        ]
+    }
+
+    response = requests.post(create_video_url, headers=POST_HEADER, json=data)
+    logger.info(response.status_code)
+    logger.info(response.json())
+
+    video_id = response.json()["_id"]
+
+    if video_id:
+        # Render Video
+        render_url = f"https://apis.elai.io/api/v1/videos/render/{video_id}"
+
+        requests.post(render_url, headers=GET_HEADER)
+
+        status_url = f"https://apis.elai.io/api/v1/videos/{video_id}"
+
+        while True:
+            response = requests.get(status_url, headers=GET_HEADER)
+            response_data = response.json()
+
+            if response_data['status'] == 'ready':
+                logger.info(response_data)
+                # DOWNLOAD VIDEO
+                download_url = response_data.get('url')
+                output_directory = 'download-video/'
+                output_filename = video_id + '.mp4'
+
+                response = requests.get(download_url)
+
+                if response.status_code == 200:
+                    os.makedirs(output_directory, exist_ok=True)  # Create the directory if it doesn't exist
+                    output_path = os.path.join(output_directory, output_filename)
+                    with open(output_path, 'wb') as f:
+                        f.write(response.content)
+                    logger.info(f"File '{output_filename}' downloaded successfully.")
+                    return output_filename
+                else:
+                    logger.error(f"Failed to download file. Status code: {response.status_code}")
+                    return None
+            elif response_data['status'] == 'failed':
+                print('Video creation failed.')
+                break
+            else:
+                print('Video is still processing. Checking again in 10 seconds...')
+                time.sleep(10)

modules/training_content/tips/instructions.MD

@@ -0,0 +1,67 @@
+# Adding new training content
+
+If you're ever tasked with the grueling task of adding more tips from manuals, my condolences.
+
+There are 4 components of a training content tip: the tip itself, the question, the additional and the segment.
+
+The tip is the actual tip, if the manual doesn't have an exercise that relates to that tip fill this out:
+
+```json
+{
+    "category": "<the category of the tip that will be used to categorize the embeddings and also used in the tip header>",
+    "embedding": "<the relevant part of the tip that is needed to make the embedding (clean the tip of useless info that might mislead the queries)>",
+    "text": "<The text that the llm will use to assess whether the tip is relevant according to the performance of the student (most of the time just include all the text of the tip)>",
+    "html": "<The html that will be rendered in the tip component>",
+    "id": "<a uuid4>",
+    "verified": <this is just to keep track of the tips that were manually confirmed by you>,
+    "standalone": <if the tip doesn't have an exercise this is true else it's false>
+}
+```
+
+If the manual does have an exercise that relates to the tip:
+
+```json
+{
+    // ...    
+    "question": "<the exercise question(s) html>",
+    "additional": "<context of the question html>",
+    "segments": [
+        {
+            "html": "<the html of a segment, you MUST wrap the html in a single <div> >",
+            "wordDelay": <the speed at which letters will be placed on the segment, 200ms is a good one>,
+            "holdDelay": <the total time that the segment will be paused before moving onto the next segment, 5000ms is a good one>,
+            "highlight": [
+                {
+                    "targets": ["<the target of the highlight can be: question, additional, segment, all>"],
+                    "phrases": ["<the words/phrases/raw html you want to highlight>"]
+                }
+            ],
+            "insertHTML": [
+                {
+                    "target": "<the target of the insert can be: question, additional>",
+                    "targetId": "<the id of an html element>",
+                    "position": "<the position of the inserted html can be: replace, prepend and append. Most of the time you will only use replace>",
+                    "html": "<the html to replace the element with targetId>"
+                },
+            ]
+        }
+    ]
+}
+```
+
+In order to create these structures you will have to mannually screenshot the tips, exercises, context and send them to an llm (gpt-4o or claude)
+with a prompt like "get me the html for this", you will have to check whether the html is properly structured and then
+paste them in the prompt.txt file of this directory and send it 
+back to an llm.
+
+Afterwards you will have to check whether the default styles in /src/components/TrainingContent/FormatTip.ts are adequate, divs 
+(except for the wrapper div of a segment) and span styles are not overriden but you should aim to use the least ammount of
+styles in the tip itself and create custom reusable html elements
+in FormatTip.ts.
+
+After checking all of the tips render you will have to create new embeddings in the backend, you CAN'T change ids of existing tips since there 
+might be training tips that are already stored in firebase.
+
+This is a very tedious task here's a recommendation for [background noise](https://www.youtube.com/watch?v=lDnva_3fcTc).
+
+GL HF 

modules/training_content/tips/prompt.txt

@@ -0,0 +1,62 @@
+I am going to give you an exercise and a tip, explain how to solve the exercise and how the tip is beneficial, 
+your response must be with this format:
+
+{
+  "segments": [
+    {
+        "html": "",
+        "wordDelay": 0,
+        "holdDelay"; 0,
+        "highlight": [
+          {
+              "targets": [],
+              "phrases": []
+          }
+        ],
+        "insertHTML": [
+          {
+              "target": "",
+              "targetId": "",
+              "position": "replace",
+              "html": ""
+          }
+        ]
+    }
+  ]
+}
+
+Basically you are going to produce multiple objects and place it in data with the format above to integrate with a react component that highlights passages and inserts html, 
+these objects are segments of your explanation that will be presented to a student. 
+
+In the html field place a segment of your response that will be streamed to the component with a delay of "wordDelay" ms and in the end of that segment stream the phrases or words inside 
+"highlight" will be highlighted for "holdDelay" ms, and the cycle repeats until the whole data array is iterated. Make it so
+that the delays are reasonable for the student have time to process the message your trying to send. Take note that 
+"wordDelay" is the time between words to display (always 200), and "holdDelay" (no less than 5000) is the total time the highlighter will highlight what you put
+inside "highlight". 
+
+There are 3 target areas:
+- "question": where the question is placed
+- "additional": where additional content is placed required to answer the question (this section is optional)
+- "segment": a particular segment
+
+You can use these targets in highlight and insertHTML. In order for insertHTML to work, you will have to place an html element with an "id" attribute
+in the targets you will reference and provide the id via the "targetId", by this I mean if you want to use insert you will need to provide me the 
+html I've sent you with either a placeholder element with an id set or set an id in an existent element.
+
+If there are already id's in the html I'm giving you then you must use insertHtml.
+
+Each segment html will be rendered in a div that as margins, you should condense the information don't give me just single short phrases that occupy a whole div.
+As previously said this wil be seen by a student so show some train of thought to solve the exercise.
+All the segment's html must be wrapped in a div element, and again since this div element will be rendered with some margins make proper use of the segments html.
+
+Try to make bulletpoints.
+Dont explicitely mention the tip right away at the beginning, aim more towards the end.
+
+
+Tip:
+
+
+Target: "question"
+
+
+Target: "additional"

modules/training_content/tips/send_tips_to_firestore.py

@@ -0,0 +1,34 @@
+import json
+import os
+
+from dotenv import load_dotenv
+
+from pymongo import MongoClient
+
+load_dotenv()
+
+# staging:   encoach-staging.json
+# prod:      storied-phalanx-349916.json
+
+mongo_db = MongoClient(os.getenv('MONGODB_URI'))[os.getenv('MONGODB_DB')]
+
+if __name__ == "__main__":
+    with open('pathways_2_rw.json', 'r', encoding='utf-8') as file:
+        book = json.load(file)
+
+    tips = []
+    for unit in book["units"]:
+        for page in unit["pages"]:
+            for tip in page["tips"]:
+                new_tip = {
+                    "id": tip["id"],
+                    "standalone": tip["standalone"],
+                    "tipCategory": tip["category"],
+                    "tipHtml": tip["html"]
+                }
+                if not tip["standalone"]:
+                    new_tip["exercise"] = tip["exercise"]
+                tips.append(new_tip)
+
+    for tip in tips:
+        doc_ref = mongo_db.walkthrough.insert_one(tip)