Skip to content

ai_service #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
samay-hash merged 2 commits into from
Jul 13, 2026
Merged

ai_service #37

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aee550c
fix: updated ai engine dependencies and switched to groq for cloud
samay-hash Jul 13, 2026
b5e5df0
test direct push
samay-hash Jul 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,3 +185,5 @@ Distributed under the MIT License. See [`LICENSE`](LICENSE) for more information
<p><i>Made with 💙 by Samay</i></p>

</div>

# Test direct push
6 changes: 3 additions & 3 deletions ai_engine/local_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
from typing import TypedDict, List, Dict, Any

from faster_whisper import WhisperModel
from langchain_ollama import ChatOllama
from langchain_groq import ChatGroq
from langchain_core.messages import SystemMessage, HumanMessage
from langgraph.graph import StateGraph, START, END

Expand Down Expand Up @@ -305,10 +305,10 @@ def node_transcribe(state: VideoState) -> VideoState:
return {"audio_path": audio, "video_duration": dur, "words": words, "segments": sentences, "status": "Transcribed"}

def node_plan(state: VideoState) -> VideoState:
print("\n--- [Ollama] Strategizing Top 0.1% Cinematic B-Roll Placements ---")
print("\n--- [Groq] Strategizing Top 0.1% Cinematic B-Roll Placements ---")
segments = state["segments"]

llm = ChatOllama(model="qwen3:4b", temperature=0.2)
llm = ChatGroq(model="llama3-70b-8192", temperature=0.2, groq_api_key=os.getenv("GROQ_API_KEY"))

transcript_summary = ""
for i, seg in enumerate(segments):
Expand Down
5 changes: 5 additions & 0 deletions ai_engine/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,3 +15,8 @@ google-generativeai==0.8.2
# YouTube Download
yt-dlp>=2024.1.0

# AI Pipeline (Cloud-ready)
faster_whisper>=1.0.3
langgraph>=0.1.5
langchain_groq>=0.1.6
langchain_core>=0.2.11
Loading