.env

@@ -1,8 +1,3 @@
-# If set, HTTP_PROXY messes with inter-container communication in the deployment.
-# Ollama downloads the models via https anyway so it should be safe to unset it
-HTTP_PROXY=
-http_proxy=
-
 #=============================================================#
 #                   LibreChat Configuration                   #
 #=============================================================#

README.md

@@ -1,6 +1,6 @@
 # librechat-mistral
 
-A quick prototype to self-host [LibreChat](https://github.com/danny-avila/LibreChat) backed by a locally-run [Mistral](https://mistral.ai/news/announcing-mistral-7b/) model, and an OpenAI-like api provided by [LiteLLM](https://github.com/BerriAI/litellm) on the side.
+A quick prototype to self-host [LibreChat](https://github.com/danny-avila/LibreChat) with [Mistral](https://mistral.ai/news/announcing-mistral-7b/), and an OpenAI-like api provided by [LiteLLM](https://github.com/BerriAI/litellm) on the side.
 
 ## Goals
 
@@ -38,16 +38,7 @@ A quick prototype to self-host [LibreChat](https://github.com/danny-avila/LibreC
 6. Browse http://localhost:3080/
 7. Create an admin account and start chatting!
 
-### Steps for NO GPU (use CPU)
+The API along with the APIDoc will be available at http://localhost:8000/
-
-**Warning: This may be very slow depending on your CPU and may us a lot of RAM depending on the model**
-
-1. Make sure your drivers are up to date.
-2. Clone the repo.
-3. Copy the CPU compose spec to select it. `cp docker-compose.cpu.yml docker.compose.yml`
-4. Run `docker compose up`. Wait for a few minutes for the model to be downloaded and served.
-5. Browse http://localhost:3080/
-6. Create an admin account and start chatting!
 
 ## Configuring additional models
 
@@ -94,8 +85,3 @@ eg:
 * [LibreChat](https://github.com/danny-avila/LibreChat) is a ChatGPT clone with support for multiple AI endpoints. It's deployed alongside a [MongoDB](https://github.com/mongodb/mongo) database and [Meillisearch](https://github.com/meilisearch/meilisearch) for search. It's exposed on http://localhost:3080/.
 * [LiteLLM](https://github.com/BerriAI/litellm) is an OpenAI-like API. It is exposed on http://localhost:8000/ without any authentication by default.
 * [Ollama](https://github.com/ollama/ollama) manages and serve the local models.
-
-## Alternatives
-
-Check out [LM Studio](https://lmstudio.ai/) for a more integrated, but non web-based alternative!
-

docker-compose.base.yml

@@ -5,11 +5,6 @@ services:
     command: --config /config.yaml
     ports:
      - 8000:8000
-    env_file:
-      - .env
-    environment:
-      - HOST=0.0.0.0
-      - PORT=8000
     volumes:
       - ./litellm/config.yaml:/config.yaml:ro
 
@@ -38,8 +33,6 @@ services:
     volumes:
       - librechat_mongodb_data:/data/db
     command: mongod --noauth
-    env_file:
-      - .env
   meilisearch:
     image: getmeili/meilisearch:v1.5
     restart: unless-stopped
@@ -47,8 +40,6 @@ services:
     environment:
       - MEILI_HOST=http://meilisearch:7700
       - MEILI_NO_ANALYTICS=true
-    env_file:
-      - .env
     volumes:
       - librechat_meilisearch_data:/meili_data
 

docker-compose.cpu.yml

@@ -1,17 +0,0 @@
-include: 
-  - docker-compose.base.yml
-
-services:
-  # Begin Ollama service
-  ollama:
-    image: ollama/ollama:0.1.23
-    restart: unless-stopped
-    entrypoint: /bootstrap.sh
-    command: mistral
-    env_file:
-      - .env
-    ports:
-     - 11434:11434
-    volumes:
-      - ./ollama/bootstrap.sh:/bootstrap.sh:ro
-      - ./ollama:/root/.ollama

librechat/librechat.yaml

@@ -7,12 +7,12 @@ endpoints:
       apiKey: "noUse"
       baseURL: "http://litellm:8000"
       models: 
-        default: ["mistral"]
+        default: ["mistral-7b"]
         fetch: true
       titleConvo: true
-      titleModel: "mistral" 
+      titleModel: "mistral-7b" 
       summarize: true
-      summaryModel: "mistral" 
+      summaryModel: "mistral-7b" 
       forcePrompt: false 
       modelDisplayLabel: "Ollama"
       # addParams:

litellm/config.yaml

@@ -1,5 +1,5 @@
 model_list:
-  - model_name: mistral
+  - model_name: mistral-7b
     litellm_params:
       model: ollama/mistral
       api_base: http://ollama:11434

ollama/bootstrap.sh

@@ -1,5 +1,10 @@
 #!/bin/bash -x
 
+# Ollama has trouble handling HTTP_PROXY
+# https://github.com/ollama/ollama/issues/2168
+unset HTTP_PROXY
+unset http_proxy
+
 ollama serve &
 
 sleep 1