Update Chat completion api docs for llama-cpp supported params

Author: nguyenhoangthuan99

docs/docs/capabilities/models/model-yaml.mdx

@@ -206,7 +206,8 @@ model_path: string
 |------------------------|--------------------------------------------------------------------------------------|--------------|
 | `cache_type`           | Data type of the KV cache in llama.cpp models. Supported types are `f16`, `q8_0`, and `q4_0`, default is `f16`.  | No          |
 | `cache_enabled`           |Enables caching of conversation history for reuse in subsequent requests. Default is `false`  | No          |
-
+| `mmproj`           |  path to mmproj GGUF model, support for llava model   | No          |
+| `llama_model_path` | path to llm GGUF model  | No          |
 
 These parameters will override the `model.yml` parameters when starting model through the API.
 

docs/docs/guides/function-calling.md

@@ -438,14 +438,10 @@ User can also specify the function with enum field to the tool definition to mak
 
 (*) Note that the accuracy of function calling heavily depends on the quality of the model. For small models like 8B or 12B, we should only use function calling with simple cases.
 
+ The function calling feature from cortex.cpp is primarily an application of prompt engineering. When tools are specified, we inject a system prompt into the conversation to facilitate this functionality.
 
-
-<!--
- Note: The function calling feature from cortex.cpp is primarily an application of prompt engineering. When tools are specified, we inject a system prompt into the conversation to facilitate this functionality.
- 
  Compatibility: This feature works best with models like llama3.1 and its derivatives, such as mistral-nemo or qwen.
 
  Customization: Users have the option to manually update the system prompt to fine-tune it for specific problems or use cases. The detail implementation is in this [PR](https://github.com/janhq/cortex.cpp/pull/1472/files).
 
- The full steps to mimic the function calling feature in Python using openai lib can be found [here](https://github.com/janhq/models/issues/16#issuecomment-2381129322)
--->
+ The full steps to mimic the function calling feature in Python using openai lib can be found [here](https://github.com/janhq/models/issues/16#issuecomment-2381129322).

docs/static/openapi/cortex.json

@@ -227,7 +227,9 @@
             }
           }
         },
-        "tags": ["Chat"]
+        "tags": [
+          "Chat"
+        ]
       }
     },
     "/v1/models/pull": {
@@ -664,7 +666,9 @@
             }
           }
         },
-        "tags": ["Models"]
+        "tags": [
+          "Models"
+        ]
       }
     },
     "/v1/threads": {
@@ -2235,6 +2239,66 @@
           "user": {
             "type": "string",
             "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. We are actively working on this feature to bring cortex as fully OpenAI compatible platform. Planning and roadmap for this feature can be found [**here**](https://github.com/janhq/cortex.cpp/issues/1582)."
+          },
+          "dynatemp_range": {
+            "type": "number",
+            "description": "Dynamic temperature range. This parameter only supported by `llama-cpp` engine."
+          },
+          "dynatemp_exponent": {
+            "type": "number",
+            "description": "Dynamic temperature exponent. This parameter only supported by `llama-cpp` engine."
+          },
+          "top_k": {
+            "type": "integer",
+            "description": "The number of most likely tokens to consider at each step. This parameter only supported by `llama-cpp` engine."
+          },
+          "min_p": {
+            "type": "number",
+            "description": "Minimum probability threshold for token sampling. This parameter only supported by `llama-cpp` engine."
+          },
+          "tfs_z": {
+            "type": "number",
+            "description": "The z-score used for Typical token sampling. This parameter only supported by `llama-cpp` engine."
+          },
+          "typ_p": {
+            "type": "number",
+            "description": "The cumulative probability threshold used for Typical token sampling. This parameter only supported by `llama-cpp` engine."
+          },
+          "repeat_last_n": {
+            "type": "integer",
+            "description": "Number of previous tokens to penalize for repeating. This parameter only supported by `llama-cpp` engine."
+          },
+          "repeat_penalty": {
+            "type": "number",
+            "description": "Penalty for repeating tokens. This parameter only supported by `llama-cpp` engine."
+          },
+          "mirostat": {
+            "type": "boolean",
+            "description": "Enables or disables Mirostat sampling (true or false). This parameter only supported by `llama-cpp` engine."
+          },
+          "mirostat_tau": {
+            "type": "number",
+            "description": "Target entropy value for Mirostat sampling. This parameter only supported by `llama-cpp` engine."
+          },
+          "mirostat_eta": {
+            "type": "number",
+            "description": "Learning rate for Mirostat sampling. This parameter only supported by `llama-cpp` engine."
+          },
+          "penalize_nl": {
+            "type": "boolean",
+            "description": "Penalizes newline tokens (true or false). This parameter only supported by `llama-cpp` engine."
+          },
+          "ignore_eos": {
+            "type": "boolean",
+            "description": "Ignores the end-of-sequence token (true or false). This parameter only supported by `llama-cpp` engine."
+          },
+          "n_probs": {
+            "type": "integer",
+            "description": "Number of probabilities to return. This parameter only supported by `llama-cpp` engine."
+          },
+          "min_keep": {
+            "type": "integer",
+            "description": "Minimum number of tokens to keep. This parameter only supported by `llama-cpp` engine."
           }
         },
         "required": [
@@ -3189,7 +3253,10 @@
             "description": "The display name of the model."
           }
         },
-        "required": ["model", "modelPath"]
+        "required": [
+          "model",
+          "modelPath"
+        ]
       },
       "ImportModelResponse": {
         "type": "object",
@@ -3208,7 +3275,11 @@
             "example": "OK"
           }
         },
-        "required": ["message", "modelHandle", "result"]
+        "required": [
+          "message",
+          "modelHandle",
+          "result"
+        ]
       },
       "CommonResponseDto": {
         "type": "object",