owusu/ds_microdot
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Add tiered summarization based on pricing plans

Browse Source 
- Implement advanced AI summarization with action items for Pro plan
- Create basic bullet-point summarization for Freemium plan
- Add plan tier validation and feature differentiation
- Support speaker identification in transcripts
- Define plan limits (600 mins Pro/200 mins Freemium)
This commit is contained in:
Michael Ikehi
2025-04-24 17:18:53 +01:00
parent 316e82b6cf
commit a91613efe2
6 changed files with 270 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files
API_DOCUMENTATION.md
+47 -18
View File
@@ -33,11 +33,12 @@ Transcribes audio or video content from a URL.
```json
{
"media_url": "https://example.com/audio-file.mp3",
"media_type": "audio" // "audio" or "video"
"media_type": "audio", // "audio" or "video"
"plan_tier": "freemium" // "freemium" or "pro" (optional, defaults to "freemium")
}
```
**Response:**
**Pro Plan Response (with speaker identification):**
```json
{
@@ -45,7 +46,33 @@ Transcribes audio or video content from a URL.
"sentences": [
{
"sentence": "Hello and welcome to the meeting.",
"speaker": "speaker_0",
"speaker": "speaker_0", // Speaker identification included
"start": 0.0,
"end": 2.5,
"words": [
{
"word": "Hello",
"start": 0.0,
"end": 0.4
},
// Additional words...
]
},
// Additional sentences...
]
}
}
```
**Freemium Plan Response (without speaker identification):**
```json
{
"transcript": {
"sentences": [
{
"sentence": "Hello and welcome to the meeting.",
// No "speaker" field in freemium plan
"start": 0.0,
"end": 2.5,
"words": [
@@ -271,14 +298,15 @@ headers = {
"Content-Type": "application/json"
}
# 1. Transcribe an audio file
# 1. Transcribe an audio file (Pro plan with speaker identification)
transcribe_payload = {
"media_url": "https://example.com/meeting-recording.mp3",
"media_type": "audio"
"media_type": "audio",
"plan_tier": "pro" # Specify "pro" for speaker identification or "freemium" for no speakers
}
transcribe_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
f"{base_url}/microdot-ai/transcribe",
headers=headers,
json=transcribe_payload
)
@@ -287,19 +315,19 @@ transcribe_response = requests.post(
if transcribe_response.status_code == 200:
transcript_data = transcribe_response.json()
transcript_json = json.dumps(transcript_data["transcript"])
# 2. Generate a summary (Pro plan)
summary_payload = {
"transcript": transcript_json,
"plan_tier": "pro"
}
summary_response = requests.post(
f"{base_url}/microdot-ai/general-summary",
f"{base_url}/microdot-ai/general-summary",
headers=headers,
json=summary_payload
)
if summary_response.status_code == 200:
summary_data = summary_response.json()
print("Summary generated successfully!")
@@ -316,7 +344,7 @@ else:
const axios = require('axios');
// API endpoint
const baseUrl = 'https://api.microdot.ai';
const baseUrl = 'http://0.0.0.0:5056';
// Your API key
const apiKey = 'your_api_key_here';
@@ -331,34 +359,35 @@ const headers = {
const transcribeAudio = async () => {
const transcribePayload = {
media_url: 'https://example.com/meeting-recording.mp3',
media_type: 'audio'
media_type: 'audio',
plan_tier: 'pro' // Specify 'pro' for speaker identification or 'freemium' for no speakers
};
try {
const transcribeResponse = await axios.post(
`${baseUrl}/microdot-ai/transcribe`,
transcribePayload,
{ headers }
);
const transcriptData = transcribeResponse.data;
const transcriptJson = JSON.stringify(transcriptData.transcript);
// 2. Generate a summary (Pro plan)
const summaryPayload = {
transcript: transcriptJson,
plan_tier: 'pro'
};
const summaryResponse = await axios.post(
`${baseUrl}/microdot-ai/general-summary`,
summaryPayload,
{ headers }
);
console.log('Summary generated successfully!');
console.log(JSON.stringify(summaryResponse.data.transcript, null, 2));
} catch (error) {
console.error('Error:', error.response ? error.response.data : error.message);
}
app.py
+12 -1
View File
@@ -55,6 +55,7 @@ async def get_api_key(api_key_header: str = Security(api_key_header)) -> str:
class TranscribeRequest(BaseModel):
media_url: Optional[str] = None
media_type: Optional[str] # Corrected type hint for media_type
plan_tier: Optional[str] = "freemium" # Default to freemium plan if not specified
class ChatResp(BaseModel): # Added BaseModel inheritance
error: Optional[str] = None
@@ -78,6 +79,16 @@ async def chat_endpoint(
api_key: str = Depends(get_api_key)
):
try:
# Get the plan tier from the request or default to freemium
plan_tier = request.plan_tier.lower() if request.plan_tier else "freemium"
# Validate plan tier using our PlanTier enum
valid_tiers = [t.value for t in PlanTier]
if plan_tier not in valid_tiers:
plan_tier = PlanTier.FREEMIUM.value # Default to freemium if invalid tier
# Check if the plan includes speaker identification
include_speakers = PlanLimits.get_limit(plan_tier, "speaker_identification")
# Use the transcribe_media function to transcribe the media
if request.media_url:
@@ -88,7 +99,7 @@ async def chat_endpoint(
# Parse response
words = transcription_response["results"]["channels"][0]["alternatives"][0]["words"]
transcript = group_words_into_sentences(words=words)
transcript = group_words_into_sentences(words=words, include_speakers=include_speakers)
return TranscriptResponse(
transcript=transcript, # Corrected to return the transcript
error=None
scripts/transcriber.py
+52 -30
View File
@@ -28,7 +28,7 @@ def extract_audio(url: str, output_template=os.path.join(UPLOAD_FOLDER, "%(title
"""
Download and extract audio from a video URL using yt-dlp.
The file will be saved in the 'upload' folder.
Returns:
str: The absolute path to the downloaded audio file (with a unique id appended).
"""
@@ -42,51 +42,51 @@ def extract_audio(url: str, output_template=os.path.join(UPLOAD_FOLDER, "%(title
}],
"quiet": True,
}
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
info = ydl.extract_info(url, download=True)
# Prepare the filename from the info.
# Note: prepare_filename returns the filename *before* postprocessing,
# so we change the extension to mp3.
original_filepath = os.path.splitext(ydl.prepare_filename(info))[0] + ".mp3"
# Debug: list files in the upload folder
if not os.path.exists(original_filepath):
files = os.listdir(UPLOAD_FOLDER)
print("Warning: Could not find expected file.")
print("Files in upload folder:", files)
raise FileNotFoundError(f"Expected audio file not found: {original_filepath}")
# Get the video's title and sanitize it
title = info.get('title', 'audio')
safe_title = sanitize_filename(title)
# Generate a unique identifier
unique_id = uuid.uuid4().hex # Unique identifier in hex format
# Construct the new filename with the unique id appended.
new_audio_filename = f"{safe_title}_{unique_id}.mp3"
new_audio_filepath = os.path.join(UPLOAD_FOLDER, new_audio_filename)
# Rename the downloaded file to include the unique ID.
os.rename(original_filepath, new_audio_filepath)
print(f"Renamed file to: {new_audio_filepath}")
# Return the absolute path to the renamed audio file.
return os.path.abspath(new_audio_filepath)
def transcribe_media(file_loc: str, media_type: str = "audio"):
"""
Transcribe media using Deepgram.
If media_type is "audio" (remote URL), use Deepgram's URL transcription.
If media_type is "video" (remote URL), extract audio locally (in the upload folder),
transcribe via file, and then delete the local audio file.
Args:
file_loc (str): URL to the remote audio or video file.
media_type (str): "audio" or "video".
Returns:
dict: The transcription response from Deepgram.
"""
@@ -100,22 +100,22 @@ def transcribe_media(file_loc: str, media_type: str = "audio"):
smart_format=True,
diarize=True,
)
if media_type.lower() == "audio":
# For remote audio files, use the URL transcription method.
response = deepgram.listen.rest.v("1").transcribe_url({"url": file_loc}, options)
elif media_type.lower() == "video":
# For remote video files, first extract the audio locally.
local_audio_path = extract_audio(file_loc)
print(f"Extracted audio to: {local_audio_path}")
# Transcribe using the local file method.
with open(local_audio_path, "rb") as file:
buffer_data = file.read()
payload: FileSource = {"buffer": buffer_data}
response = deepgram.listen.rest.v("1").transcribe_file(payload, options)
# Clean up: delete the local audio file.
if os.path.exists(local_audio_path):
os.remove(local_audio_path)
@@ -123,7 +123,7 @@ def transcribe_media(file_loc: str, media_type: str = "audio"):
else:
raise ValueError("media_type must be either 'audio' or 'video'.")
return response
except Exception as e:
@@ -137,54 +137,76 @@ def transcribe_media(file_loc: str, media_type: str = "audio"):
def group_words_into_sentences(words, max_words=15):
def group_words_into_sentences(words, max_words=15, include_speakers=True):
"""
Group words into sentences based on speaker changes.
Args:
words: List of word objects from the transcription
max_words: Maximum number of words per sentence
include_speakers: Whether to include speaker information in the output
(True for Pro plan, False for Freemium plan)
Returns:
A dictionary containing the sentences
"""
sentences = []
current_sentence = []
current_speaker = None
start_time = None
for i, word_info in enumerate(words):
word = word_info["punctuated_word"]
speaker = word_info["speaker"]
speaker = word_info["speaker"] if include_speakers else "speaker_0" # Use a default speaker if not including speakers
start = word_info["start"]
end = word_info["end"]
# If speaker changes or sentence reaches max length, start a new sentence
if speaker != current_speaker:
if current_sentence:
sentences.append({
sentence_obj = {
"sentence": " ".join([w["word"] for w in current_sentence]),
"speaker": current_speaker,
"start": start_time,
"end": words[i-1]["end"],
"words": current_sentence
})
}
# Only include speaker information if include_speakers is True
if include_speakers:
sentence_obj["speaker"] = current_speaker
sentences.append(sentence_obj)
current_sentence = []
current_speaker = speaker
start_time = start
# Append word with metadata inside the current sentence
current_sentence.append({"word": word, "start": start, "end": end})
# Append the last sentence if any words remain
if current_sentence:
sentences.append({
sentence_obj = {
"sentence": " ".join([w["word"] for w in current_sentence]),
"speaker": current_speaker,
"start": start_time,
"end": words[-1]["end"],
"words": current_sentence
})
}
# Only include speaker information if include_speakers is True
if include_speakers:
sentence_obj["speaker"] = current_speaker
sentences.append(sentence_obj)
return {"sentences": sentences}
if __name__ == "__main__":
audio_url = "https://s3.us-east-2.amazonaws.com/com.mkdlabs.images/baas/jordan/019933724441Business%20English%20Conversation%20Lesson%2045_%20Meeting%20a%20New%20Colleague.mp3"
video_url = "https://s3.us-east-2.amazonaws.com/com.mkdlabs.images/baas/jordan/038426704141Business%20English%20Conversation%20Lesson%2045_%20%20Meeting%20a%20New%20Colleague.mp4"
# Folder for file uploads/downloads
response = transcribe_media(video_url, media_type="video")
print(response)
src/models.py
+4 -2
View File
@@ -15,13 +15,15 @@ class PlanLimits:
"transcription_minutes": 200,
"summary_type": "basic",
"transcript_history_days": 7,
"integrations": ["google_meet", "zoom"]
"integrations": ["google_meet", "zoom"],
"speaker_identification": False
},
PlanTier.PRO: {
"transcription_minutes": 600,
"summary_type": "advanced",
"transcript_history_days": 30,
"integrations": ["google_meet", "zoom", "slack", "notion", "asana", "microsoft_teams"]
"integrations": ["google_meet", "zoom", "slack", "notion", "asana", "microsoft_teams"],
"speaker_identification": True
}
}
test1.py
+65 -22
View File
@@ -19,33 +19,76 @@ headers = {
# Audio URL from your notebook
audio_url = "https://s3.us-east-2.amazonaws.com/com.mkdlabs.images/baas/jordan/019933724441Business%20English%20Conversation%20Lesson%2045_%20Meeting%20a%20New%20Colleague.mp3"
# 1. First, transcribe the audio
transcribe_payload = {
# 1. First, transcribe the audio with the Pro plan (with speaker identification)
pro_transcribe_payload = {
"media_url": audio_url,
"media_type": "audio"
"media_type": "audio",
"plan_tier": "pro" # Specify the pro plan to include speaker identification
}
transcribe_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
pro_transcribe_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
headers=headers,
json=transcribe_payload
json=pro_transcribe_payload
)
# Check if transcription was successful
if transcribe_response.status_code == 200:
transcript_data = transcribe_response.json()
print("Transcription successful!")
# Save the transcript for later use
transcript_json = json.dumps(transcript_data["transcript"], indent=4)
# Save the transcript to a file
with open("transcript.json", "w") as f:
f.write(transcript_json)
print("Transcript saved to transcript.json")
# Check if Pro plan transcription was successful
if pro_transcribe_response.status_code == 200:
pro_transcript_data = pro_transcribe_response.json()
print("Pro plan transcription successful!")
# Save the Pro plan transcript for later use
pro_transcript_json = json.dumps(pro_transcript_data["transcript"], indent=4)
# Save the Pro plan transcript to a file
with open("pro_transcript.json", "w") as f:
f.write(pro_transcript_json)
print("Pro plan transcript saved to pro_transcript.json")
# Check if the Pro plan transcript has speaker information
has_speaker_pro = "speaker" in pro_transcript_data["transcript"]["sentences"][0] if pro_transcript_data["transcript"]["sentences"] else False
print(f"Pro plan has speaker information: {has_speaker_pro}")
else:
print(f"Transcription failed with status code: {transcribe_response.status_code}")
print(transcribe_response.text)
print(f"Pro plan transcription failed with status code: {pro_transcribe_response.status_code}")
print(pro_transcribe_response.text)
# 1b. Now transcribe with the Free plan (without speaker identification)
free_transcribe_payload = {
"media_url": audio_url,
"media_type": "audio",
"plan_tier": "freemium" # Specify the freemium plan to exclude speaker identification
}
free_transcribe_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
headers=headers,
json=free_transcribe_payload
)
# Check if Free plan transcription was successful
if free_transcribe_response.status_code == 200:
free_transcript_data = free_transcribe_response.json()
print("Free plan transcription successful!")
# Save the Free plan transcript for later use
free_transcript_json = json.dumps(free_transcript_data["transcript"], indent=4)
# Save the Free plan transcript to a file
with open("free_transcript.json", "w") as f:
f.write(free_transcript_json)
print("Free plan transcript saved to free_transcript.json")
# Check if the Free plan transcript has speaker information
has_speaker_free = "speaker" in free_transcript_data["transcript"]["sentences"][0] if free_transcript_data["transcript"]["sentences"] else False
print(f"Free plan has speaker information: {has_speaker_free}")
# Use the Pro plan transcript for the summary tests
transcript_json = pro_transcript_json
else:
print(f"Free plan transcription failed with status code: {free_transcribe_response.status_code}")
print(free_transcribe_response.text)
# If Free plan fails but Pro plan succeeded, use Pro plan transcript for summary tests
if pro_transcribe_response.status_code == 200:
transcript_json = pro_transcript_json
@@ -56,7 +99,7 @@ basic_summary_payload = {
}
basic_summary_response = requests.post(
f"{base_url}/microdot-ai/general-summary",
f"{base_url}/microdot-ai/general-summary",
headers=headers,
json=basic_summary_payload
)
@@ -83,7 +126,7 @@ advanced_summary_payload = {
}
advanced_summary_response = requests.post(
f"{base_url}/microdot-ai/general-summary",
f"{base_url}/microdot-ai/general-summary",
headers=headers,
json=advanced_summary_payload
)
@@ -93,7 +136,7 @@ if advanced_summary_response.status_code == 200:
advanced_summary_data = advanced_summary_response.json()
print("\n--- Advanced (Pro) Summary ---")
advanced_summary_json = json.dumps(advanced_summary_data, indent=2)
with open("advanced_summary.json", "w") as f:
f.write(advanced_summary_json)
print("Advanced summary saved to advanced_summary.json")
test_plans.py
+90
View File
@@ -0,0 +1,90 @@
import os
import requests
import json
from dotenv import load_dotenv
load_dotenv()
# API endpoint
base_url = "http://localhost:5056"
# Your API key
api_key = os.getenv("API_KEY_ACCESS")
# Headers
headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json"
}
# Audio URL for testing
audio_url = "https://s3.us-east-2.amazonaws.com/com.mkdlabs.images/baas/jordan/019933724441Business%20English%20Conversation%20Lesson%2045_%20Meeting%20a%20New%20Colleague.mp3"
# Test function to compare freemium and pro plan transcriptions
def test_plan_differences():
# 1. Test the freemium plan (no speaker identification)
freemium_payload = {
"media_url": audio_url,
"media_type": "audio",
"plan_tier": "freemium"
}
print("Testing Freemium Plan (no speaker identification)...")
freemium_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
headers=headers,
json=freemium_payload
)
# 2. Test the pro plan (with speaker identification)
pro_payload = {
"media_url": audio_url,
"media_type": "audio",
"plan_tier": "pro"
}
print("Testing Pro Plan (with speaker identification)...")
pro_response = requests.post(
f"{base_url}/microdot-ai/transcribe",
headers=headers,
json=pro_payload
)
# Check if both requests were successful
if freemium_response.status_code == 200 and pro_response.status_code == 200:
freemium_data = freemium_response.json()
pro_data = pro_response.json()
# Save the transcripts for inspection
with open("freemium_transcript.json", "w") as f:
f.write(json.dumps(freemium_data, indent=4))
with open("pro_transcript.json", "w") as f:
f.write(json.dumps(pro_data, indent=4))
print("Transcripts saved to freemium_transcript.json and pro_transcript.json")
# Check if the freemium plan has speaker information
has_speaker_freemium = "speaker" in freemium_data["transcript"]["sentences"][0] if freemium_data["transcript"]["sentences"] else False
# Check if the pro plan has speaker information
has_speaker_pro = "speaker" in pro_data["transcript"]["sentences"][0] if pro_data["transcript"]["sentences"] else False
print(f"Freemium plan has speaker information: {has_speaker_freemium}")
print(f"Pro plan has speaker information: {has_speaker_pro}")
# Verify the expected behavior
if not has_speaker_freemium and has_speaker_pro:
print("✅ Test PASSED: Freemium plan doesn't show speakers, Pro plan does.")
else:
print("❌ Test FAILED: Expected behavior not observed.")
else:
print(f"Freemium request status: {freemium_response.status_code}")
print(f"Pro request status: {pro_response.status_code}")
if freemium_response.status_code != 200:
print(f"Freemium error: {freemium_response.text}")
if pro_response.status_code != 200:
print(f"Pro error: {pro_response.text}")
if __name__ == "__main__":
test_plan_differences()