feat(docker): set default Docker to use Ollama (#1812)

Dockerfile.external

@@ -14,7 +14,7 @@ FROM base as dependencies
 WORKDIR /home/worker/app
 COPY pyproject.toml poetry.lock ./
 
-RUN poetry install --extras "ui vector-stores-qdrant"
+RUN poetry install --extras "ui vector-stores-qdrant llms-ollama embeddings-ollama"
 
 FROM base as app
 

docker-compose.yaml

@@ -1,13 +1,16 @@
 services:
   private-gpt:
     build:
-      dockerfile: Dockerfile.local
+      dockerfile: Dockerfile.external
     volumes:
       - ./local_data/:/home/worker/app/local_data
-      - ./models/:/home/worker/app/models
     ports:
       - 8001:8080
     environment:
       PORT: 8080
       PGPT_PROFILES: docker
-      PGPT_MODE: llamacpp
+      PGPT_MODE: ollama
+  ollama:
+    image: ollama/ollama:latest
+    volumes:
+      - ./models:/root/.ollama

settings-docker.yaml

@@ -19,6 +19,17 @@ sagemaker:
   llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}
   embedding_endpoint_name: ${PGPT_SAGEMAKER_EMBEDDING_ENDPOINT_NAME:}
 
+ollama:
+  llm_model: ${PGPT_OLLAMA_LLM_MODEL:mistral}
+  embedding_model: ${PGPT_OLLAMA_EMBEDDING_MODEL:nomic-embed-text}
+  api_base: ${PGPT_OLLAMA_API_BASE:http://ollama:11434}
+  tfs_z: ${PGPT_OLLAMA_TFS_Z:1.0}
+  top_k: ${PGPT_OLLAMA_TOP_K:40}
+  top_p: ${PGPT_OLLAMA_TOP_P:0.9}
+  repeat_last_n: ${PGPT_OLLAMA_REPEAT_LAST_N:64}
+  repeat_penalty: ${PGPT_OLLAMA_REPEAT_PENALTY:1.2}
+  request_timeout: ${PGPT_OLLAMA_REQUEST_TIMEOUT:600.0}
+
 ui:
   enabled: true
   path: /