From 790ba693c4b87ffa92929e8929112d06fbfe9fcd Mon Sep 17 00:00:00 2001
From: Ankush Malaker <43288948+AnkushMalaker@users.noreply.github.com>
Date: Sat, 20 Dec 2025 03:25:10 +0000
Subject: [PATCH] Update configuration files for model providers and Docker
 setup

- Changed LLM, embedding, and STT providers in `config.yml` to OpenAI and Deepgram.
- Removed read-only flag from `config.yml` in Docker Compose files to allow UI configuration saving.
- Updated memory configuration endpoint to accept plain text for YAML input.
---
 backends/advanced/docker-compose.yml          |   4 +-
 .../routers/modules/system_routes.py          |   4 +-
 config.yml                                    | 389 +++++++++---------
 3 files changed, 188 insertions(+), 209 deletions(-)

diff --git a/backends/advanced/docker-compose.yml b/backends/advanced/docker-compose.yml
index dced4041..34f12c53 100644
--- a/backends/advanced/docker-compose.yml
+++ b/backends/advanced/docker-compose.yml
@@ -12,7 +12,7 @@ services:
       - ./data/audio_chunks:/app/audio_chunks
       - ./data/debug_dir:/app/debug_dir
       - ./data:/app/data
-      - ../../config.yml:/app/config.yml:ro
+      - ../../config.yml:/app/config.yml  # Removed :ro to allow UI config saving
     environment:
       - DEEPGRAM_API_KEY=${DEEPGRAM_API_KEY}
       - MISTRAL_API_KEY=${MISTRAL_API_KEY}
@@ -65,7 +65,7 @@ services:
       - ./start-workers.sh:/app/start-workers.sh
       - ./data/audio_chunks:/app/audio_chunks
       - ./data:/app/data
-      - ../../config.yml:/app/config.yml:ro
+      - ../../config.yml:/app/config.yml  # Removed :ro for consistency
     environment:
       - DEEPGRAM_API_KEY=${DEEPGRAM_API_KEY}
       - MISTRAL_API_KEY=${MISTRAL_API_KEY}
diff --git a/backends/advanced/src/advanced_omi_backend/routers/modules/system_routes.py b/backends/advanced/src/advanced_omi_backend/routers/modules/system_routes.py
index e51c036c..5737171c 100644
--- a/backends/advanced/src/advanced_omi_backend/routers/modules/system_routes.py
+++ b/backends/advanced/src/advanced_omi_backend/routers/modules/system_routes.py
@@ -82,7 +82,7 @@ async def get_memory_config_raw(current_user: User = Depends(current_superuser))
 
 @router.post("/admin/memory/config/raw")
 async def update_memory_config_raw(
-    config_yaml: str = Body(..., embed=True),
+    config_yaml: str = Body(..., media_type="text/plain"),
     current_user: User = Depends(current_superuser)
 ):
     """Update memory configuration YAML and hot reload. Admin only."""
@@ -91,7 +91,7 @@ async def update_memory_config_raw(
 
 @router.post("/admin/memory/config/validate")
 async def validate_memory_config(
-    config_yaml: str = Body(..., embed=True),
+    config_yaml: str = Body(..., media_type="text/plain"),
     current_user: User = Depends(current_superuser)
 ):
     """Validate memory configuration YAML syntax. Admin only."""
diff --git a/config.yml b/config.yml
index 678e6d70..ac412d1e 100644
--- a/config.yml
+++ b/config.yml
@@ -1,220 +1,199 @@
 defaults:
-  llm: emberfang-llm
-  embedding: emberfang-embed
-  stt: stt-parakeet-batch
+  llm: openai-llm
+  embedding: openai-embed
+  stt: stt-deepgram
   tts: tts-http
   vector_store: vs-qdrant
-
 models:
-  # llama cpp llm, name can be anything
-  - name: emberfang-llm
-    description: Emberfang One LLM
-    model_type: llm
-    model_provider: openai
-    model_name: gpt-oss-20b-f16
-    model_url: http://192.168.1.166:8084/v1
-    api_key: "1234"
-    model_params:
-      temperature: 0.2
-      max_tokens: 2000
-    model_output: json
-
-  - name: emberfang-embed
-    description: Emberfang embeddings (nomic-embed-text)
-    model_type: embedding
-    model_provider: openai
-    model_name: nomic-embed-text-v1.5
-    model_url: http://192.168.1.166:8084/v1
-    api_key: "1234"
-    embedding_dimensions: 768
-    model_output: vector
-
-  # Local Ollama LLM (OpenAI-compatible)
-  - name: local-llm
-    description: Local Ollama LLM
-    model_type: llm
-    model_provider: ollama
-    api_family: openai
-    model_name: llama3.1:latest
-    model_url: http://localhost:11434/v1
-    api_key: ${OPENAI_API_KEY:-ollama}
-    model_params:
-      temperature: 0.2
-      max_tokens: 2000
-    model_output: json
-
-  # Local Ollama embedding model (OpenAI-compatible embeddings endpoint)
-  - name: local-embed
-    description: Local embeddings via Ollama nomic-embed-text
-    model_type: embedding
-    model_provider: ollama
-    api_family: openai
-    model_name: nomic-embed-text:latest
-    model_url: http://localhost:11434/v1
-    api_key: ${OPENAI_API_KEY:-ollama}
-    embedding_dimensions: 768
-    model_output: vector
-
-  # Hosted OpenAI (optional)
-  - name: openai-llm
-    description: OpenAI GPT-4o-mini
-    model_type: llm
-    model_provider: openai
-    api_family: openai
-    model_name: gpt-4o-mini
-    model_url: https://api.openai.com/v1
-    api_key: ${OPENAI_API_KEY:-}
-    model_params:
-      temperature: 0.2
-      max_tokens: 2000
-    model_output: json
-
-  - name: openai-embed
-    description: OpenAI text-embedding-3-small
-    model_type: embedding
-    model_provider: openai
-    api_family: openai
-    model_name: text-embedding-3-small
-    model_url: https://api.openai.com/v1
-    api_key: ${OPENAI_API_KEY:-}
-    embedding_dimensions: 1536
-    model_output: vector
-
-  # Hosted Groq (OpenAI-compatible chat)
-  - name: groq-llm
-    description: Groq LLM via OpenAI-compatible API
-    model_type: llm
-    model_provider: groq
-    api_family: openai
-    model_name: llama-3.1-70b-versatile
-    model_url: https://api.groq.com/openai/v1
-    api_key: ${GROQ_API_KEY:-}
-    model_params:
-      temperature: 0.2
-      max_tokens: 2000
-    model_output: json
-
-  # Vector store (Qdrant)
-  - name: vs-qdrant
-    description: Qdrant vector database
-    model_type: vector_store
-    model_provider: qdrant
-    api_family: qdrant
-    model_url: http://qdrant:6333
-    model_params:
-      host: qdrant
-      port: 6333
-      collection_name: omi_memories
-
-  # STT (Parakeet over HTTP, batch transcription)
-  - name: stt-parakeet-batch
-    description: Parakeet NeMo ASR (batch)
-    model_type: stt
-    model_provider: parakeet
-    api_family: http
-    model_url: http://172.17.0.1:8767
-    api_key: ""
-    operations:
-      stt_transcribe:
-        method: POST
-        path: /transcribe
-        content_type: multipart/form-data
-        response:
-          type: json
-          extract:
-            text: text
-            words: words
-            segments: segments
-
-  # STT (Deepgram over HTTP, config-driven)
-  - name: stt-deepgram
-    description: Deepgram Nova 3 (batch)
-    model_type: stt
-    model_provider: deepgram
-    api_family: http
-    model_url: https://api.deepgram.com/v1
-    api_key: ${DEEPGRAM_API_KEY:-}
-    operations:
-      stt_transcribe:
-        method: POST
-        path: /listen
-        headers:
-          Authorization: Token ${DEEPGRAM_API_KEY:-}
-          Content-Type: audio/raw
-        query:
-          model: nova-3
-          language: multi
-          smart_format: "true"
-          punctuate: "true"
-          diarize: false
-          encoding: linear16
-          sample_rate: 16000
-          channels: "1"
-        response:
-          type: json
-          extract:
-            text: results.channels[0].alternatives[0].transcript
-            words: results.channels[0].alternatives[0].words
-            segments: results.channels[0].alternatives[0].paragraphs.paragraphs
-
-  # TTS (placeholder; configure to your provider)
-  - name: tts-http
-    description: Generic JSON TTS endpoint
-    model_type: tts
-    model_provider: custom
-    api_family: http
-    model_url: http://localhost:9000
-    operations:
-      tts_synthesize:
-        method: POST
-        path: /synthesize
-        headers:
-          Content-Type: application/json
-        response:
-          type: json
-
-  # STT streaming (Parakeet via WebSocket; config-driven template)
-  - name: stt-parakeet-stream
-    description: Parakeet streaming transcription over WebSocket
-    model_type: stt_stream
-    model_provider: parakeet
-    api_family: websocket
-    model_url: ws://localhost:9001/stream
-    operations:
-      start:
-        message:
-          type: transcribe
-          config:
-            vad_enabled: true
-            vad_silence_ms: 1000
-            time_interval_seconds: 30
-            return_interim_results: true
-            min_audio_seconds: 0.5
-      chunk_header:
-        message:
-          type: audio_chunk
-          rate: 16000
-          width: 2
-          channels: 1
-      end:
-        message:
-          type: stop
-      expect:
-        interim_type: interim_result
-        final_type: final_result
+- name: emberfang-llm
+  description: Emberfang One LLM
+  model_type: llm
+  model_provider: openai
+  model_name: gpt-oss-20b-f16
+  model_url: http://192.168.1.166:8084/v1
+  api_key: '1234'
+  model_params:
+    temperature: 0.2
+    max_tokens: 2000
+  model_output: json
+- name: emberfang-embed
+  description: Emberfang embeddings (nomic-embed-text)
+  model_type: embedding
+  model_provider: openai
+  model_name: nomic-embed-text-v1.5
+  model_url: http://192.168.1.166:8084/v1
+  api_key: '1234'
+  embedding_dimensions: 768
+  model_output: vector
+- name: local-llm
+  description: Local Ollama LLM
+  model_type: llm
+  model_provider: ollama
+  api_family: openai
+  model_name: llama3.1:latest
+  model_url: http://localhost:11434/v1
+  api_key: ${OPENAI_API_KEY:-ollama}
+  model_params:
+    temperature: 0.2
+    max_tokens: 2000
+  model_output: json
+- name: local-embed
+  description: Local embeddings via Ollama nomic-embed-text
+  model_type: embedding
+  model_provider: ollama
+  api_family: openai
+  model_name: nomic-embed-text:latest
+  model_url: http://localhost:11434/v1
+  api_key: ${OPENAI_API_KEY:-ollama}
+  embedding_dimensions: 768
+  model_output: vector
+- name: openai-llm
+  description: OpenAI GPT-4o-mini
+  model_type: llm
+  model_provider: openai
+  api_family: openai
+  model_name: gpt-4o-mini
+  model_url: https://api.openai.com/v1
+  api_key: ${OPENAI_API_KEY:-}
+  model_params:
+    temperature: 0.2
+    max_tokens: 2000
+  model_output: json
+- name: openai-embed
+  description: OpenAI text-embedding-3-small
+  model_type: embedding
+  model_provider: openai
+  api_family: openai
+  model_name: text-embedding-3-small
+  model_url: https://api.openai.com/v1
+  api_key: ${OPENAI_API_KEY:-}
+  embedding_dimensions: 1536
+  model_output: vector
+- name: groq-llm
+  description: Groq LLM via OpenAI-compatible API
+  model_type: llm
+  model_provider: groq
+  api_family: openai
+  model_name: llama-3.1-70b-versatile
+  model_url: https://api.groq.com/openai/v1
+  api_key: ${GROQ_API_KEY:-}
+  model_params:
+    temperature: 0.2
+    max_tokens: 2000
+  model_output: json
+- name: vs-qdrant
+  description: Qdrant vector database
+  model_type: vector_store
+  model_provider: qdrant
+  api_family: qdrant
+  model_url: http://${QDRANT_BASE_URL:-qdrant}:${QDRANT_PORT:-6333}
+  model_params:
+    host: ${QDRANT_BASE_URL:-qdrant}
+    port: ${QDRANT_PORT:-6333}
+    collection_name: omi_memories
+- name: stt-parakeet-batch
+  description: Parakeet NeMo ASR (batch)
+  model_type: stt
+  model_provider: parakeet
+  api_family: http
+  model_url: http://172.17.0.1:8767
+  api_key: ''
+  operations:
+    stt_transcribe:
+      method: POST
+      path: /transcribe
+      content_type: multipart/form-data
+      response:
+        type: json
         extract:
           text: text
           words: words
           segments: segments
-
+- name: stt-deepgram
+  description: Deepgram Nova 3 (batch)
+  model_type: stt
+  model_provider: deepgram
+  api_family: http
+  model_url: https://api.deepgram.com/v1
+  api_key: ${DEEPGRAM_API_KEY:-}
+  operations:
+    stt_transcribe:
+      method: POST
+      path: /listen
+      headers:
+        Authorization: Token ${DEEPGRAM_API_KEY:-}
+        Content-Type: audio/raw
+      query:
+        model: nova-3
+        language: multi
+        smart_format: 'true'
+        punctuate: 'true'
+        diarize: false
+        encoding: linear16
+        sample_rate: 16000
+        channels: '1'
+      response:
+        type: json
+        extract:
+          text: results.channels[0].alternatives[0].transcript
+          words: results.channels[0].alternatives[0].words
+          segments: results.channels[0].alternatives[0].paragraphs.paragraphs
+- name: tts-http
+  description: Generic JSON TTS endpoint
+  model_type: tts
+  model_provider: custom
+  api_family: http
+  model_url: http://localhost:9000
+  operations:
+    tts_synthesize:
+      method: POST
+      path: /synthesize
+      headers:
+        Content-Type: application/json
+      response:
+        type: json
+- name: stt-parakeet-stream
+  description: Parakeet streaming transcription over WebSocket
+  model_type: stt_stream
+  model_provider: parakeet
+  api_family: websocket
+  model_url: ws://localhost:9001/stream
+  operations:
+    start:
+      message:
+        type: transcribe
+        config:
+          vad_enabled: true
+          vad_silence_ms: 1000
+          time_interval_seconds: 30
+          return_interim_results: true
+          min_audio_seconds: 0.5
+    chunk_header:
+      message:
+        type: audio_chunk
+        rate: 16000
+        width: 2
+        channels: 1
+    end:
+      message:
+        type: stop
+    expect:
+      interim_type: interim_result
+      final_type: final_result
+      extract:
+        text: text
+        words: words
+        segments: segments
 memory:
-  provider: chronicle  # chronicle | openmemory_mcp | mycelia
+  provider: chronicle
   timeout_seconds: 1200
   extraction:
     enabled: true
-    # Optional custom prompt; if omitted, a built-in default is used
-    prompt: |
-      Extract important information from this conversation and return a JSON object with an array named "facts". Include personal preferences, plans, names, dates, locations, numbers, and key details. Keep items concise and useful.
+    prompt: 'Extract important information from this conversation and return a JSON
+      object with an array named "facts". Include personal preferences, plans, names,
+      dates, locations, numbers, and key details hehehe. Keep items concise and useful.
+
+      '
   openmemory_mcp:
     server_url: http://localhost:8765
     client_name: chronicle