Cleaning up examples/ models and starter .env files (#1124)

Closes https://github.com/go-skynet/LocalAI/issues/1066 and
https://github.com/go-skynet/LocalAI/issues/1065

Standardizes all `examples/`:
- Models in one place (other than `rwkv`, which was one-offy)
- Env files as `.env.example` with `cp`
    - Also standardizes comments and links docs

examples/autoGPT/.env.example

@@ -1,5 +1,9 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 OPENAI_API_KEY=sk---anystringhere
 OPENAI_API_BASE=http://api:8080/v1
 # Models to preload at start
-# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings
+# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings,
+# see other options in the model gallery at https://github.com/go-skynet/model-gallery
 PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/gpt4all-j.yaml", "name": "gpt-3.5-turbo"}, { "url": "github:go-skynet/model-gallery/bert-embeddings.yaml", "name": "text-embedding-ada-002"}]

examples/autoGPT/README.md

@@ -10,12 +10,16 @@ git clone https://github.com/go-skynet/LocalAI
 
 cd LocalAI/examples/autoGPT
 
+cp -rfv .env.example .env
+
+# Edit the .env file to set a different model by editing `PRELOAD_MODELS`.
+vim .env
+
 docker-compose run --rm auto-gpt
 ```
 
 Note: The example automatically downloads the `gpt4all` model as it is under a permissive license. The GPT4All model does not seem to be enough to run AutoGPT. WizardLM-7b-uncensored seems to perform better (with `f16: true`).
 
-See the `.env` configuration file to set a different model with the [model-gallery](https://github.com/go-skynet/model-gallery) by editing `PRELOAD_MODELS`.
 
 ## Without docker
 

examples/chatbot-ui-manual/models

@@ -0,0 +1 @@
+../models

examples/discord-bot/.env.example

@@ -1,3 +1,6 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 OPENAI_API_KEY=x
 DISCORD_BOT_TOKEN=x
 DISCORD_CLIENT_ID=x

examples/discord-bot/models

@@ -1 +1 @@
-../chatbot-ui/models/
+../models

examples/functions/.env.example

@@ -1,7 +1,11 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 OPENAI_API_KEY=sk---anystringhere
 OPENAI_API_BASE=http://api:8080/v1
 # Models to preload at start
-# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings
+# Here we configure gpt4all as gpt-3.5-turbo and bert as embeddings,
+# see other options in the model gallery at https://github.com/go-skynet/model-gallery
 PRELOAD_MODELS=[{"url": "github:go-skynet/model-gallery/openllama-7b-open-instruct.yaml", "name": "gpt-3.5-turbo"}]
 
 ## Change the default number of threads

examples/functions/README.md

@@ -10,9 +10,12 @@ git clone https://github.com/go-skynet/LocalAI
 
 cd LocalAI/examples/functions
 
+cp -rfv .env.example .env
+
+# Edit the .env file to set a different model by editing `PRELOAD_MODELS`.
+vim .env
+
 docker-compose run --rm functions
 ```
 
 Note: The example automatically downloads the `openllama` model as it is under a permissive license.
-
-See the `.env` configuration file to set a different model with the [model-gallery](https://github.com/go-skynet/model-gallery) by editing `PRELOAD_MODELS`.

examples/langchain-chroma/.env.example

@@ -1,3 +1,6 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 THREADS=4
 CONTEXT_SIZE=512
 MODELS_PATH=/models

examples/langchain-chroma/models

@@ -0,0 +1 @@
+../models

examples/langchain-chroma/models/completion.tmpl

@@ -1 +0,0 @@
-{{.Input}}

examples/langchain-chroma/models/gpt-3.5-turbo.yaml

@@ -1,16 +0,0 @@
-name: gpt-3.5-turbo
-parameters:
-  model: ggml-gpt4all-j
-  top_k: 80
-  temperature: 0.2
-  top_p: 0.7
-context_size: 1024
-stopwords:
-- "HUMAN:"
-- "GPT:"
-roles:
-  user: " "
-  system: " "
-template:
-  completion: completion
-  chat: gpt4all

examples/langchain-chroma/models/gpt4all.tmpl

@@ -1,4 +0,0 @@
-The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
-### Prompt:
-{{.Input}}
-### Response:

examples/langchain-huggingface/models

@@ -0,0 +1 @@
+../models

examples/langchain-huggingface/models/completion.tmpl

@@ -1 +0,0 @@
-{{.Input}}

examples/langchain-huggingface/models/gpt-3.5-turbo.yaml

@@ -1,17 +0,0 @@
-name: gpt-3.5-turbo
-parameters:
-  model: gpt2
-  top_k: 80
-  temperature: 0.2
-  top_p: 0.7
-context_size: 1024
-backend: "langchain-huggingface"
-stopwords:
-- "HUMAN:"
-- "GPT:"
-roles:
-  user: " "
-  system: " "
-template:
-  completion: completion
-  chat: gpt4all

examples/langchain-huggingface/models/gpt4all.tmpl

@@ -1,4 +0,0 @@
-The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
-### Prompt:
-{{.Input}}
-### Response:

examples/langchain/models

@@ -0,0 +1 @@
+../models

examples/langchain/models/completion.tmpl

@@ -1 +0,0 @@
-{{.Input}}

examples/langchain/models/gpt-3.5-turbo.yaml

@@ -1,17 +0,0 @@
-name: gpt-3.5-turbo
-parameters:
-  model: ggml-gpt4all-j # ggml-koala-13B-4bit-128g
-  top_k: 80
-  temperature: 0.2
-  top_p: 0.7
-context_size: 1024
-stopwords:
-- "HUMAN:"
-- "GPT:"
-roles:
-  user: " "
-  system: " "
-backend: "gptj"
-template:
-  completion: completion
-  chat: gpt4all

examples/langchain/models/gpt4all.tmpl

@@ -1,4 +0,0 @@
-The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
-### Prompt:
-{{.Input}}
-### Response:

examples/localai-webui/docker-compose.yml

@@ -8,8 +8,6 @@ services:
       dockerfile: Dockerfile
     ports:
       - 8080:8080
-    env_file:
-      - .env
     volumes:
       - ./models:/models:cached
     command: ["/usr/bin/local-ai"]

examples/models/.gitignore

@@ -0,0 +1,7 @@
+# Ignore everything but predefined models
+*
+!.gitignore
+!completion.tmpl
+!embeddings.yaml
+!gpt4all.tmpl
+!gpt-3.5-turbo.yaml

examples/query_data/models

@@ -0,0 +1 @@
+../models

examples/query_data/models/completion.tmpl

@@ -1 +0,0 @@
-{{.Input}}

examples/query_data/models/embeddings.yaml

@@ -1,6 +0,0 @@
-name: text-embedding-ada-002
-parameters:
-  model: bert
-threads: 14
-backend: bert-embeddings
-embeddings: true

examples/query_data/models/gpt-3.5-turbo.yaml

@@ -1,16 +0,0 @@
-name: gpt-3.5-turbo
-parameters:
-  model: ggml-gpt4all-j
-  top_k: 80
-  temperature: 0.2
-  top_p: 0.7
-context_size: 1024
-stopwords:
-- "HUMAN:"
-- "GPT:"
-roles:
-  user: " "
-  system: " "
-template:
-  completion: completion
-  chat: gpt4all

examples/slack-bot/.env.example

@@ -1,3 +1,6 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 SLACK_APP_TOKEN=xapp-1-...
 SLACK_BOT_TOKEN=xoxb-...
 OPENAI_API_KEY=sk-...

examples/slack-bot/README.md

@@ -18,7 +18,7 @@ git clone https://github.com/seratch/ChatGPT-in-Slack
 # Download gpt4all-j to models/
 wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j
 
-# Set the discord bot options (see: https://github.com/seratch/ChatGPT-in-Slack)
+# Set the Slack bot options (see: https://github.com/seratch/ChatGPT-in-Slack)
 cp -rfv .env.example .env
 vim .env
 

examples/slack-bot/models

@@ -1 +1 @@
-../chatbot-ui/models
+../models

examples/slack-qa-bot/.env.example

@@ -1,3 +1,6 @@
+# CPU .env docs: https://localai.io/howtos/easy-setup-docker-cpu/
+# GPU .env docs: https://localai.io/howtos/easy-setup-docker-gpu/
+
 # Create an app-level token with connections:write scope
 SLACK_APP_TOKEN=xapp-1-...
 # Install the app into your workspace to grab this token