feat(aio): update AIO image defaults (#5002)

* feat(aio): update AIO image defaults

cpu:
 - text-to-text: llama3.1
 - embeddings: granite-embeddings
 - vision: moonream2

gpu/intel:
 - text-to-text: localai-functioncall-qwen2.5-7b-v0.5
 - embeddings: granite-embeddings
 - vision: minicpm

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(aio): use minicpm as moondream2 stopped working

https://github.com/ggml-org/llama.cpp/pull/12322#issuecomment-2717483759

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

aio/intel/text-to-text.yaml

@@ -1,103 +1,53 @@
-name: gpt-4
-mmap: false
-context_size: 8192
-
-f16: false
-parameters:
-  model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
-
-stopwords:
-- "<|im_end|>"
-- "<dummy32000>"
-- "</tool_call>"
-- "<|eot_id|>"
-- "<|end_of_text|>"
-
+context_size: 4096
+f16: true
 function:
-  # disable injecting the "answer" tool
-  disable_no_action: true
-
+  capture_llm_results:
+  - (?s)<Thought>(.*?)</Thought>
   grammar:
-    # This allows the grammar to also return messages
-    mixed_mode: true
-    # Suffix to add to the grammar
-    #prefix: '<tool_call>\n'
-    # Force parallel calls in the grammar
-    # parallel_calls: true
-
-  return_name_in_function_response: true
-  # Without grammar uncomment the lines below
-  # Warning: this is relying only on the capability of the
-  # LLM model to generate the correct function call.
-  json_regex_match: 
-   - "(?s)<tool_call>(.*?)</tool_call>"
-   - "(?s)<tool_call>(.*?)"
+    properties_order: name,arguments
+  json_regex_match:
+  - (?s)<Output>(.*?)</Output>
   replace_llm_results:
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
+  - key: (?s)<Thought>(.*?)</Thought>
     value: ""
-  replace_function_results: 
-  # Replace everything that is not JSON array or object
-  # 
-  - key: '(?s)^[^{\[]*'
-    value: ""
-  - key: '(?s)[^}\]]*$'
-    value: ""
-  - key: "'([^']*?)'"
-    value: "_DQUOTE_${1}_DQUOTE_"
-  - key: '\\"'
-    value: "__TEMP_QUOTE__"
-  - key: "\'"
-    value: "'"
-  - key: "_DQUOTE_"
-    value: '"'
-  - key: "__TEMP_QUOTE__"
-    value: '"'
-  # Drop the scratchpad content from responses
-  - key: "(?s)<scratchpad>.*</scratchpad>"
-    value: ""
-
+mmap: true
+name: gpt-4
+parameters:
+  model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
+stopwords:
+- <|im_end|>
+- <dummy32000>
+- </s>
 template:
   chat: |
     {{.Input -}}
     <|im_start|>assistant
   chat_message: |
-    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
-    {{- if .FunctionCall }}
-    <tool_call>
-    {{- else if eq .RoleName "tool" }}
-    <tool_response>
-    {{- end }}
-    {{- if .Content}}
+    <|im_start|>{{ .RoleName }}
+    {{ if .FunctionCall -}}
+    Function call:
+    {{ else if eq .RoleName "tool" -}}
+    Function response:
+    {{ end -}}
+    {{ if .Content -}}
     {{.Content }}
-    {{- end }}
-    {{- if .FunctionCall}}
+    {{ end -}}
+    {{ if .FunctionCall -}}
     {{toJson .FunctionCall}}
-    {{- end }}
-    {{- if .FunctionCall }}
-    </tool_call>
-    {{- else if eq .RoleName "tool" }}
-    </tool_response>
-    {{- end }}<|im_end|>
+    {{ end -}}<|im_end|>
   completion: |
     {{.Input}}
-  function: |-
+  function: |
     <|im_start|>system
-    You are a function calling AI model.
-    Here are the available tools:
-    <tools>
+    You are an AI assistant that executes function calls, and these are the tools at your disposal:
     {{range .Functions}}
     {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
     {{end}}
-    </tools>
-    You should call the tools provided to you sequentially
-    Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
-    <scratchpad>
-    {step-by-step reasoning and plan in bullet points}
-    </scratchpad>
-    For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
-    <tool_call>
-    {"arguments": <args-dict>, "name": <function-name>}
-    </tool_call><|im_end|>
+    <|im_end|>
     {{.Input -}}
     <|im_start|>assistant
+
+download_files:
+- filename: localai-functioncall-phi-4-v0.3-q4_k_m.gguf
+  sha256: 23fee048ded2a6e2e1a7b6bbefa6cbf83068f194caa9552aecbaa00fec8a16d5
+  uri: huggingface://mudler/LocalAI-functioncall-phi-4-v0.3-Q4_K_M-GGUF/localai-functioncall-phi-4-v0.3-q4_k_m.gguf