From 38d19036bdd69123bfca8862e8df2d3faeefffa5 Mon Sep 17 00:00:00 2001
From: hcornet <hcornet@tips-of-mine.fr>
Date: Thu, 6 Mar 2025 19:27:34 +0100
Subject: [PATCH] first sync

---
 .env               | 329 ++++++++++++++++++++++++++++++++++++++++++++-
 README.md          |  12 ++
 docker-compose.yml |  80 +++++++----
 3 files changed, 392 insertions(+), 29 deletions(-)

diff --git a/.env b/.env
index 630b323..8291970 100644
--- a/.env
+++ b/.env
@@ -1 +1,328 @@
-# Template
\ No newline at end of file
+SERVER_PORT=3001
+STORAGE_DIR="/app/server/storage"
+UID='1000'
+GID='1000'
+# SIG_KEY='passphrase' # Please generate random string at least 32 chars long.
+# SIG_SALT='salt' # Please generate random string at least 32 chars long.
+# JWT_SECRET="my-random-string-for-seeding" # Only needed if AUTH_TOKEN is set. Please generate random string at least 12 chars long.
+
+###########################################
+######## LLM API SElECTION ################
+###########################################
+LLM_PROVIDER='openai'
+OPEN_AI_KEY=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
+OPEN_MODEL_PREF='gpt-4o-mini'
+
+# LLM_PROVIDER='gemini'
+# GEMINI_API_KEY=
+# GEMINI_LLM_MODEL_PREF='gemini-pro'
+
+# LLM_PROVIDER='azure'
+# AZURE_OPENAI_ENDPOINT=
+# AZURE_OPENAI_KEY=
+# OPEN_MODEL_PREF='my-gpt35-deployment' # This is the "deployment" on Azure you want to use. Not the base model.
+# EMBEDDING_MODEL_PREF='embedder-model' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002
+
+# LLM_PROVIDER='anthropic'
+# ANTHROPIC_API_KEY=sk-ant-xxxx
+# ANTHROPIC_MODEL_PREF='claude-2'
+
+# LLM_PROVIDER='lmstudio'
+# LMSTUDIO_BASE_PATH='http://your-server:1234/v1'
+# LMSTUDIO_MODEL_PREF='Loaded from Chat UI' # this is a bug in LMStudio 0.2.17
+# LMSTUDIO_MODEL_TOKEN_LIMIT=4096
+
+# LLM_PROVIDER='localai'
+# LOCAL_AI_BASE_PATH='http://host.docker.internal:8080/v1'
+# LOCAL_AI_MODEL_PREF='luna-ai-llama2'
+# LOCAL_AI_MODEL_TOKEN_LIMIT=4096
+# LOCAL_AI_API_KEY="sk-123abc"
+
+# LLM_PROVIDER='ollama'
+# OLLAMA_BASE_PATH='http://host.docker.internal:11434'
+# OLLAMA_MODEL_PREF='llama2'
+# OLLAMA_MODEL_TOKEN_LIMIT=4096
+# OLLAMA_AUTH_TOKEN='your-ollama-auth-token-here (optional, only for ollama running behind auth - Bearer token)'
+
+# LLM_PROVIDER='togetherai'
+# TOGETHER_AI_API_KEY='my-together-ai-key'
+# TOGETHER_AI_MODEL_PREF='mistralai/Mixtral-8x7B-Instruct-v0.1'
+
+# LLM_PROVIDER='mistral'
+# MISTRAL_API_KEY='example-mistral-ai-api-key'
+# MISTRAL_MODEL_PREF='mistral-tiny'
+
+# LLM_PROVIDER='perplexity'
+# PERPLEXITY_API_KEY='my-perplexity-key'
+# PERPLEXITY_MODEL_PREF='codellama-34b-instruct'
+
+# LLM_PROVIDER='openrouter'
+# OPENROUTER_API_KEY='my-openrouter-key'
+# OPENROUTER_MODEL_PREF='openrouter/auto'
+
+# LLM_PROVIDER='huggingface'
+# HUGGING_FACE_LLM_ENDPOINT=https://uuid-here.us-east-1.aws.endpoints.huggingface.cloud
+# HUGGING_FACE_LLM_API_KEY=hf_xxxxxx
+# HUGGING_FACE_LLM_TOKEN_LIMIT=8000
+
+# LLM_PROVIDER='groq'
+# GROQ_API_KEY=gsk_abcxyz
+# GROQ_MODEL_PREF=llama3-8b-8192
+
+# LLM_PROVIDER='koboldcpp'
+# KOBOLD_CPP_BASE_PATH='http://127.0.0.1:5000/v1'
+# KOBOLD_CPP_MODEL_PREF='koboldcpp/codellama-7b-instruct.Q4_K_S'
+# KOBOLD_CPP_MODEL_TOKEN_LIMIT=4096
+
+# LLM_PROVIDER='textgenwebui'
+# TEXT_GEN_WEB_UI_BASE_PATH='http://127.0.0.1:5000/v1'
+# TEXT_GEN_WEB_UI_TOKEN_LIMIT=4096
+# TEXT_GEN_WEB_UI_API_KEY='sk-123abc'
+
+# LLM_PROVIDER='generic-openai'
+# GENERIC_OPEN_AI_BASE_PATH='http://proxy.url.openai.com/v1'
+# GENERIC_OPEN_AI_MODEL_PREF='gpt-3.5-turbo'
+# GENERIC_OPEN_AI_MODEL_TOKEN_LIMIT=4096
+# GENERIC_OPEN_AI_API_KEY=sk-123abc
+
+# LLM_PROVIDER='litellm'
+# LITE_LLM_MODEL_PREF='gpt-3.5-turbo'
+# LITE_LLM_MODEL_TOKEN_LIMIT=4096
+# LITE_LLM_BASE_PATH='http://127.0.0.1:4000'
+# LITE_LLM_API_KEY='sk-123abc'
+
+# LLM_PROVIDER='novita'
+# NOVITA_LLM_API_KEY='your-novita-api-key-here' check on https://novita.ai/settings/key-management
+# NOVITA_LLM_MODEL_PREF='deepseek/deepseek-r1'
+
+# LLM_PROVIDER='cohere'
+# COHERE_API_KEY=
+# COHERE_MODEL_PREF='command-r'
+
+# LLM_PROVIDER='bedrock'
+# AWS_BEDROCK_LLM_ACCESS_KEY_ID=
+# AWS_BEDROCK_LLM_ACCESS_KEY=
+# AWS_BEDROCK_LLM_REGION=us-west-2
+# AWS_BEDROCK_LLM_MODEL_PREFERENCE=meta.llama3-1-8b-instruct-v1:0
+# AWS_BEDROCK_LLM_MODEL_TOKEN_LIMIT=8191
+
+# LLM_PROVIDER='fireworksai'
+# FIREWORKS_AI_LLM_API_KEY='my-fireworks-ai-key'
+# FIREWORKS_AI_LLM_MODEL_PREF='accounts/fireworks/models/llama-v3p1-8b-instruct'
+
+# LLM_PROVIDER='apipie'
+# APIPIE_LLM_API_KEY='sk-123abc'
+# APIPIE_LLM_MODEL_PREF='openrouter/llama-3.1-8b-instruct'
+
+# LLM_PROVIDER='xai'
+# XAI_LLM_API_KEY='xai-your-api-key-here'
+# XAI_LLM_MODEL_PREF='grok-beta'
+
+# LLM_PROVIDER='nvidia-nim'
+# NVIDIA_NIM_LLM_BASE_PATH='http://127.0.0.1:8000'
+# NVIDIA_NIM_LLM_MODEL_PREF='meta/llama-3.2-3b-instruct'
+
+# LLM_PROVIDER='deepseek'
+# DEEPSEEK_API_KEY='your-deepseek-api-key-here'
+# DEEPSEEK_MODEL_PREF='deepseek-chat'
+
+# LLM_PROVIDER='ppio'
+# PPIO_API_KEY='your-ppio-api-key-here'
+# PPIO_MODEL_PREF=deepseek/deepseek-v3/community
+
+###########################################
+######## Embedding API SElECTION ##########
+###########################################
+# Only used if you are using an LLM that does not natively support embedding (openai or Azure)
+# EMBEDDING_ENGINE='openai'
+# OPEN_AI_KEY=sk-xxxx
+# EMBEDDING_MODEL_PREF='text-embedding-ada-002'
+
+# EMBEDDING_ENGINE='azure'
+# AZURE_OPENAI_ENDPOINT=
+# AZURE_OPENAI_KEY=
+# EMBEDDING_MODEL_PREF='my-embedder-model' # This is the "deployment" on Azure you want to use for embeddings. Not the base model. Valid base model is text-embedding-ada-002
+
+# EMBEDDING_ENGINE='localai'
+# EMBEDDING_BASE_PATH='http://localhost:8080/v1'
+# EMBEDDING_MODEL_PREF='text-embedding-ada-002'
+# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=1000 # The max chunk size in chars a string to embed can be
+
+# EMBEDDING_ENGINE='ollama'
+# EMBEDDING_BASE_PATH='http://host.docker.internal:11434'
+# EMBEDDING_MODEL_PREF='nomic-embed-text:latest'
+# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
+
+# EMBEDDING_ENGINE='lmstudio'
+# EMBEDDING_BASE_PATH='https://host.docker.internal:1234/v1'
+# EMBEDDING_MODEL_PREF='nomic-ai/nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.Q4_0.gguf'
+# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
+
+# EMBEDDING_ENGINE='cohere'
+# COHERE_API_KEY=
+# EMBEDDING_MODEL_PREF='embed-english-v3.0'
+
+# EMBEDDING_ENGINE='voyageai'
+# VOYAGEAI_API_KEY=
+# EMBEDDING_MODEL_PREF='voyage-large-2-instruct'
+
+# EMBEDDING_ENGINE='litellm'
+# EMBEDDING_MODEL_PREF='text-embedding-ada-002'
+# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
+# LITE_LLM_BASE_PATH='http://127.0.0.1:4000'
+# LITE_LLM_API_KEY='sk-123abc'
+
+# EMBEDDING_ENGINE='generic-openai'
+# EMBEDDING_MODEL_PREF='text-embedding-ada-002'
+# EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
+# EMBEDDING_BASE_PATH='http://127.0.0.1:4000'
+# GENERIC_OPEN_AI_EMBEDDING_API_KEY='sk-123abc'
+# GENERIC_OPEN_AI_EMBEDDING_MAX_CONCURRENT_CHUNKS=500
+
+# EMBEDDING_ENGINE='gemini'
+# GEMINI_EMBEDDING_API_KEY=
+# EMBEDDING_MODEL_PREF='text-embedding-004'
+
+###########################################
+######## Vector Database Selection ########
+###########################################
+# Enable all below if you are using vector database: Chroma.
+# VECTOR_DB="chroma"
+# CHROMA_ENDPOINT='http://host.docker.internal:8000'
+# CHROMA_API_HEADER="X-Api-Key"
+# CHROMA_API_KEY="sk-123abc"
+
+# Enable all below if you are using vector database: Pinecone.
+# VECTOR_DB="pinecone"
+# PINECONE_API_KEY=
+# PINECONE_INDEX=
+
+# Enable all below if you are using vector database: LanceDB.
+# VECTOR_DB="lancedb"
+
+# Enable all below if you are using vector database: Weaviate.
+# VECTOR_DB="weaviate"
+# WEAVIATE_ENDPOINT="http://localhost:8080"
+# WEAVIATE_API_KEY=
+
+# Enable all below if you are using vector database: Qdrant.
+# VECTOR_DB="qdrant"
+# QDRANT_ENDPOINT="http://localhost:6333"
+# QDRANT_API_KEY=
+
+# Enable all below if you are using vector database: Milvus.
+# VECTOR_DB="milvus"
+# MILVUS_ADDRESS="http://localhost:19530"
+# MILVUS_USERNAME=
+# MILVUS_PASSWORD=
+
+# Enable all below if you are using vector database: Zilliz Cloud.
+# VECTOR_DB="zilliz"
+# ZILLIZ_ENDPOINT="https://sample.api.gcp-us-west1.zillizcloud.com"
+# ZILLIZ_API_TOKEN=api-token-here
+
+# Enable all below if you are using vector database: Astra DB.
+# VECTOR_DB="astra"
+# ASTRA_DB_APPLICATION_TOKEN=
+# ASTRA_DB_ENDPOINT=
+
+###########################################
+######## Audio Model Selection ############
+###########################################
+# (default) use built-in whisper-small model.
+# WHISPER_PROVIDER="local"
+
+# use openai hosted whisper model.
+# WHISPER_PROVIDER="openai"
+# OPEN_AI_KEY=sk-xxxxxxxx
+
+###########################################
+######## TTS/STT Model Selection ##########
+###########################################
+# TTS_PROVIDER="native"
+
+# TTS_PROVIDER="openai"
+# TTS_OPEN_AI_KEY=sk-example
+# TTS_OPEN_AI_VOICE_MODEL=nova
+
+# TTS_PROVIDER="generic-openai"
+# TTS_OPEN_AI_COMPATIBLE_KEY=sk-example
+# TTS_OPEN_AI_COMPATIBLE_VOICE_MODEL=nova
+# TTS_OPEN_AI_COMPATIBLE_ENDPOINT="https://api.openai.com/v1"
+
+# TTS_PROVIDER="elevenlabs"
+# TTS_ELEVEN_LABS_KEY=
+# TTS_ELEVEN_LABS_VOICE_MODEL=21m00Tcm4TlvDq8ikWAM # Rachel
+
+# CLOUD DEPLOYMENT VARIRABLES ONLY
+# AUTH_TOKEN="hunter2" # This is the password to your application if remote hosting.
+# DISABLE_TELEMETRY="false"
+
+###########################################
+######## PASSWORD COMPLEXITY ##############
+###########################################
+# Enforce a password schema for your organization users.
+# Documentation on how to use https://github.com/kamronbatman/joi-password-complexity
+# Default is only 8 char minimum
+# PASSWORDMINCHAR=8
+# PASSWORDMAXCHAR=250
+# PASSWORDLOWERCASE=1
+# PASSWORDUPPERCASE=1
+# PASSWORDNUMERIC=1
+# PASSWORDSYMBOL=1
+# PASSWORDREQUIREMENTS=4
+
+###########################################
+######## ENABLE HTTPS SERVER ##############
+###########################################
+# By enabling this and providing the path/filename for the key and cert,
+# the server will use HTTPS instead of HTTP.
+#ENABLE_HTTPS="true"
+#HTTPS_CERT_PATH="sslcert/cert.pem"
+#HTTPS_KEY_PATH="sslcert/key.pem"
+
+###########################################
+######## AGENT SERVICE KEYS ###############
+###########################################
+
+#------ SEARCH ENGINES -------
+#=============================
+#------ Google Search -------- https://programmablesearchengine.google.com/controlpanel/create
+# AGENT_GSE_KEY=
+# AGENT_GSE_CTX=
+
+#------ SearchApi.io ----------- https://www.searchapi.io/
+# AGENT_SEARCHAPI_API_KEY=
+# AGENT_SEARCHAPI_ENGINE=google
+
+#------ Serper.dev ----------- https://serper.dev/
+# AGENT_SERPER_DEV_KEY=
+
+#------ Bing Search ----------- https://portal.azure.com/
+# AGENT_BING_SEARCH_API_KEY=
+
+#------ Serply.io ----------- https://serply.io/
+# AGENT_SERPLY_API_KEY=
+
+#------ SearXNG ----------- https://github.com/searxng/searxng
+# AGENT_SEARXNG_API_URL=
+
+#------ Tavily ----------- https://www.tavily.com/
+# AGENT_TAVILY_API_KEY=
+
+###########################################
+######## Other Configurations ############
+###########################################
+
+# Disable viewing chat history from the UI and frontend APIs.
+# See https://docs.anythingllm.com/configuration#disable-view-chat-history for more information.
+# DISABLE_VIEW_CHAT_HISTORY=1
+
+# Enable simple SSO passthrough to pre-authenticate users from a third party service.
+# See https://docs.anythingllm.com/configuration#simple-sso-passthrough for more information.
+# SIMPLE_SSO_ENABLED=1
+
+# Specify the target languages for when using OCR to parse images and PDFs.
+# This is a comma separated list of language codes as a string. Unsupported languages will be ignored.
+# Default is English. See https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html for a list of valid language codes.
+# TARGET_OCR_LANG=eng,deu,ita,spa,fra,por,rus,nld,tur,hun,pol,ita,spa,fra,por,rus,nld,tur,hun,pol
\ No newline at end of file
diff --git a/README.md b/README.md
index cc2df84..6db3a6e 100644
--- a/README.md
+++ b/README.md
@@ -27,6 +27,18 @@ Modification des labels pour traefik
   nano docker-compose.yml
 ~~~
 
+~~~bash
+export STORAGE_LOCATION=$HOME/anythingllm && \
+mkdir -p $STORAGE_LOCATION && \
+touch "$STORAGE_LOCATION/.env" && \
+docker run -d -p 3001:3001 \
+--cap-add SYS_ADMIN \
+-v ${STORAGE_LOCATION}:/app/server/storage \
+-v ${STORAGE_LOCATION}/.env:/app/server/.env \
+-e STORAGE_DIR="/app/server/storage" \
+mintplexlabs/anythingllm
+~~~
+
 ## Lancement
 
 ~~~bash
diff --git a/docker-compose.yml b/docker-compose.yml
index 4054566..42575a6 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -2,41 +2,65 @@
 networks:
   traefik_front_network:
     external: true
-  back_network_:
+  back_network_anythingllm:
     driver: bridge
     attachable: true
 
 #### SERVICES
 services:
-### hello_world
-  hello_world:
-    container_name: gitea-app
-    hostname: gitea-app
-    image: hello-world
-    environment:
-    restart: always
+  anythingllm:
+    image: mintplexlabs/anythingllm
+    container_name: anythingllm
+    ports:
+    - "3001:3001"
     networks:
-#      - back_network_gitea
-      - traefik_front_network
+    - traefik_front_network
+    cap_add:
+      - SYS_ADMIN
+    environment:
+    # Adjust for your environment
+      - STORAGE_DIR=/app/server/storage
+      - JWT_SECRET="make this a large list of random numbers and letters 20+"
+      - LLM_PROVIDER=openai
+#      - LLM_PROVIDER=ollama
+#      - OLLAMA_BASE_PATH=http://127.0.0.1:11434
+#      - OLLAMA_MODEL_PREF=llama2
+#      - OLLAMA_MODEL_TOKEN_LIMIT=4096
+      - OPEN_AI_KEY=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
+      - OPEN_MODEL_PREF=gpt-4o-mini
+      - EMBEDDING_ENGINE=ollama
+      - EMBEDDING_BASE_PATH=http://127.0.0.1:11434
+      - EMBEDDING_MODEL_PREF=nomic-embed-text:latest
+      - EMBEDDING_MODEL_MAX_CHUNK_LENGTH=8192
+      - VECTOR_DB=lancedb
+      - WHISPER_PROVIDER=local
+      - TTS_PROVIDER=native
+      - PASSWORDMINCHAR=8
+      # Add any other keys here for services or settings
+      # you can find in the docker/.env.example file
     volumes:
+      - anythingllm_storage:/app/server/storage
+    restart: always
     labels:
+      - "com.centurylinklabs.watchtower.enable=true"
       - "traefik.enable=true"
       - "traefik.docker.network=traefik_front_network"
-# HTTP
-      - "traefik.http.routers.hello-world-http.rule=Host(`hello-world.tips-of-mine.com`)"
-      - "traefik.http.routers.hello-world-http.entrypoints=http"
-      - "traefik.http.routers.hello-world-http.priority=49"
-# HTTPS
-      - "traefik.http.routers.hello-world-https.rule=Host(`hello-world.tips-of-mine.com`)"
-      - "traefik.http.routers.hello-world-https.entrypoints=https"
-      - "traefik.http.routers.hello-world-https.tls=true"
-      - "traefik.http.routers.hello-world-https.priority=50"
-      - "traefik.http.routers.gitea.service=gitea-https-service"
-# Middleware
-# Service
-#      - "traefik.http.services.gitea-https-service.loadbalancer.server.port=3000"
-#      - "traefik.http.services.gitea-https-service.loadbalancer.server.scheme=https"
-#      - "traefik.http.services.gitea-https-service.loadbalancer.healthcheck.hostname=gitea.traefik.me"
-#      - "traefik.http.services.gitea-https-service.loadbalancer.healthcheck.method=foobar"
-#      - "traefik.http.services.gitea-https-service.loadbalancer.healthcheck.timeout=10"
-#      - "traefik.http.services.gitea-https-service.loadbalancer.healthcheck.interval=30"
+## HTTP
+      - "traefik.http.routers.anythingllm-http.rule=Host(`anythingllm.tips-of-mine.com`)"
+      - "traefik.http.routers.anythingllm-http.entrypoints=http"
+## HTTPS
+      - "traefik.http.routers.anythingllm-https.rule=Host(`anythingllm.tips-of-mine.com`)"
+      - "traefik.http.routers.anythingllm-https.entrypoints=https"
+      - "traefik.http.routers.anythingllm-https.tls=true"
+      - "traefik.http.routers.anythingllm.service=anythingllm-service"
+## Middleware
+## Service
+      - "traefik.http.services.anythingllm-service.loadbalancer.server.port=3001"
+
+volumes:
+  anythingllm_storage:
+    driver: local
+    driver_opts:
+      type: none
+      o: bind
+      device: ./storage
\ No newline at end of file