From 0afdee4a9856d419499c74099b7dbe986d941c8b Mon Sep 17 00:00:00 2001
From: hieu-jan <150573299+hieu-jan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 01:40:08 +0900
Subject: [PATCH 1/5] docs: update API Reference page

---
 docs/openapi/jan.yaml          |  55 +++--
 docs/openapi/specs/models.yaml | 370 ++++++++++-----------------------
 2 files changed, 150 insertions(+), 275 deletions(-)

diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml
index bfff0ad73..9981f7308 100644
--- a/docs/openapi/jan.yaml
+++ b/docs/openapi/jan.yaml
@@ -67,21 +67,32 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: |
-            curl http://localhost:1337/v1/chat/completions \
-              -H "Content-Type: application/json" \
+            curl -X 'POST' \
+              'http://127.0.0.1:1337/v1/chat/completions' \
+              -H 'accept: application/json' \
+              -H 'Content-Type: application/json' \
               -d '{
-                "model": "tinyllama-1.1b",
-                "messages": [
-                  {
-                    "role": "system",
-                    "content": "You are a helpful assistant."
-                  },
-                  {
-                    "role": "user",
-                    "content": "Hello!"
-                  }
-                ]
-              }'
+              "messages": [
+                {
+                  "content": "You are a helpful assistant.",
+                  "role": "system"
+                },
+                {
+                  "content": "Hello!",
+                  "role": "user"
+                }
+              ],
+              "model": "tinyllama-1.1b",
+              "stream": true,
+              "max_tokens": 2048,
+              "stop": [
+                "hello"
+              ],
+              "frequency_penalty": 0,
+              "presence_penalty": 0,
+              "temperature": 0.7,
+              "top_p": 0.95
+            }'
   /models:
     get:
       operationId: listModels
@@ -103,7 +114,9 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: |
-            curl http://localhost:1337/v1/models
+            curl -X 'GET' \
+              'http://127.0.0.1:1337/v1/models' \
+              -H 'accept: application/json'
   "/models/download/{model_id}":
     get:
       operationId: downloadModel
@@ -131,7 +144,9 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: |
-            curl -X POST http://localhost:1337/v1/models/download/{model_id}
+            curl -X 'GET' \
+              'http://127.0.0.1:1337/v1/models/download/{model_id}' \
+              -H 'accept: application/json'
   "/models/{model_id}":
     get:
       operationId: retrieveModel
@@ -162,7 +177,9 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: |
-            curl http://localhost:1337/v1/models/{model_id}
+            curl -X 'GET' \
+              'http://127.0.0.1:1337/v1/models/{model_id}' \
+              -H 'accept: application/json'
     delete:
       operationId: deleteModel
       tags:
@@ -191,7 +208,9 @@ paths:
       x-codeSamples:
         - lang: cURL
           source: |
-            curl -X DELETE http://localhost:1337/v1/models/{model_id}
+            curl -X 'DELETE' \
+              'http://127.0.0.1:1337/v1/models/{model_id}' \
+              -H 'accept: application/json'
   /threads:
     post:
       operationId: createThread
diff --git a/docs/openapi/specs/models.yaml b/docs/openapi/specs/models.yaml
index 418be9563..791d14880 100644
--- a/docs/openapi/specs/models.yaml
+++ b/docs/openapi/specs/models.yaml
@@ -18,106 +18,77 @@ components:
     Model:
       type: object
       properties:
-        type:
-          type: string
-          default: model
-          description: The type of the object.
-        version:
-          type: string
-          default: "1"
-          description: The version number of the model.
-        id:
-          type: string
-          description: Unique identifier used in chat-completions model_name, matches
-            folder name.
-          example: zephyr-7b
-        name:
-          type: string
-          description: Name of the model.
-          example: Zephyr 7B
-        owned_by:
-          type: string
-          description: Compatibility field for OpenAI.
-          default: ""
-        created:
-          type: integer
-          format: int64
-          description: Unix timestamp representing the creation time.
-        description:
-          type: string
-          description: Description of the model.
-        state:
-          type: string
-          enum:
-            - null
-            - downloading
-            - ready
-            - starting
-            - stopping
-          description: Current state of the model.
-        format:
-          type: string
-          description: State format of the model, distinct from the engine.
-          example: ggufv3
         source_url:
           type: string
           format: uri
           description: URL to the source of the model.
-          example: https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
+          example: https://huggingface.co/janhq/trinity-v1.2-GGUF/resolve/main/trinity-v1.2.Q4_K_M.gguf
+        id:
+          type: string
+          description:
+            Unique identifier used in chat-completions model_name, matches
+            folder name.
+          example: trinity-v1.2-7b
+        object:
+          type: string
+          example: model
+        name:
+          type: string
+          description: Name of the model.
+          example: Trinity-v1.2 7B Q4
+        version:
+          type: string
+          default: "1.0"
+          description: The version number of the model.
+        description:
+          type: string
+          description: Description of the model.
+          example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
+        format:
+          type: string
+          description: State format of the model, distinct from the engine.
+          example: gguf
         settings:
           type: object
           properties:
             ctx_len:
-              type: string
+              type: integer
               description: Context length.
-              example: "2048"
-            ngl:
+              example: 4096
+            prompt_template:
               type: string
-              description: Number of layers.
-              example: "100"
-            embedding:
-              type: string
-              description: Indicates if embedding is enabled.
-              example: "true"
-            n_parallel:
-              type: string
-              description: Number of parallel processes.
-              example: "4"
+              example: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
           additionalProperties: false
         parameters:
           type: object
           properties:
             temperature:
-              type: string
-              description: Temperature setting for the model.
-              example: "0.7"
-            token_limit:
-              type: string
-              description: Token limit for the model.
-              example: "2048"
-            top_k:
-              type: string
-              description: Top-k setting for the model.
-              example: "0"
+              example: 0.7
             top_p:
-              type: string
-              description: Top-p setting for the model.
-              example: "1"
+              example: 0.95
             stream:
-              type: string
-              description: Indicates if streaming is enabled.
-              example: "true"
+              example: true
+            max_tokens:
+              example: 4096
+            stop:
+              example: []
+            frequency_penalty:
+              example: 0
+            presence_penalty:
+              example: 0
           additionalProperties: false
         metadata:
-          type: object
-          description: Additional metadata.
-        assets:
-          type: array
-          items:
+          author:
             type: string
-          description: List of assets related to the model.
-      required:
-        - source_url
+            example: Jan
+          tags:
+            example: ["7B", "Merged", "Featured"]
+          size:
+            example: 4370000000,
+          cover:
+            example: "https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png"
+        engine:
+          example: nitro
     ModelObject:
       type: object
       properties:
@@ -125,7 +96,7 @@ components:
           type: string
           description: |
             The identifier of the model.
-          example: zephyr-7b
+          example: ztrinity-v1.2-7b
         object:
           type: string
           description: |
@@ -145,197 +116,82 @@ components:
     GetModelResponse:
       type: object
       properties:
-        id:
-          type: string
-          description: The identifier of the model.
-          example: zephyr-7b
-        object:
-          type: string
-          description: Type of the object, indicating it's a model.
-          default: model
-        created:
-          type: integer
-          format: int64
-          description: Unix timestamp representing the creation time of the model.
-        owned_by:
-          type: string
-          description: The entity that owns the model.
-          example: _
-        state:
-          type: string
-          enum:
-            - not_downloaded
-            - downloaded
-            - running
-            - stopped
-          description: The current state of the model.
         source_url:
           type: string
           format: uri
           description: URL to the source of the model.
-          example: https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/blob/main/zephyr-7b-beta.Q4_K_M.gguf
-        engine_parameters:
-          type: object
-          properties:
-            pre_prompt:
-              type: string
-              description: Predefined prompt used for setting up internal configurations.
-              default: ""
-              example: Initial setup complete.
-            system_prompt:
-              type: string
-              description: Prefix used for system-level prompts.
-              default: "SYSTEM: "
-            user_prompt:
-              type: string
-              description: Prefix used for user prompts.
-              default: "USER: "
-            ai_prompt:
-              type: string
-              description: Prefix used for assistant prompts.
-              default: "ASSISTANT: "
-            ngl:
-              type: integer
-              description: Number of neural network layers loaded onto the GPU for
-                acceleration.
-              minimum: 0
-              maximum: 100
-              default: 100
-              example: 100
-            ctx_len:
-              type: integer
-              description: Context length for model operations, varies based on the specific
-                model.
-              minimum: 128
-              maximum: 4096
-              default: 2048
-              example: 2048
-            n_parallel:
-              type: integer
-              description: Number of parallel operations, relevant when continuous batching is
-                enabled.
-              minimum: 1
-              maximum: 10
-              default: 1
-              example: 4
-            cont_batching:
-              type: boolean
-              description: Indicates if continuous batching is used for processing.
-              default: false
-              example: false
-            cpu_threads:
-              type: integer
-              description: Number of threads allocated for CPU-based inference.
-              minimum: 1
-              example: 8
-            embedding:
-              type: boolean
-              description: Indicates if embedding layers are enabled in the model.
-              default: true
-              example: true
-        model_parameters:
+          example: https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/resolve/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf
+        id:
+          type: string
+          description:
+            Unique identifier used in chat-completions model_name, matches
+            folder name.
+          example: mistral-ins-7b-q4
+        object:
+          type: string
+          example: model
+        name:
+          type: string
+          description: Name of the model.
+          example: Mistral Instruct 7B Q4
+        version:
+          type: string
+          default: "1.0"
+          description: The version number of the model.
+        description:
+          type: string
+          description: Description of the model.
+          example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
+        format:
+          type: string
+          description: State format of the model, distinct from the engine.
+          example: gguf
+        settings:
           type: object
           properties:
             ctx_len:
               type: integer
-              description: Maximum context length the model can handle.
-              minimum: 0
-              maximum: 4096
-              default: 2048
-              example: 2048
-            ngl:
-              type: integer
-              description: Number of layers in the neural network.
-              minimum: 1
-              maximum: 100
-              default: 100
-              example: 100
-            embedding:
-              type: boolean
-              description: Indicates if embedding layers are used.
-              default: true
-              example: true
-            n_parallel:
-              type: integer
-              description: Number of parallel processes the model can run.
-              minimum: 1
-              maximum: 10
-              default: 1
-              example: 4
+              description: Context length.
+              example: 4096
+            prompt_template:
+              type: string
+              example: "[INST] {prompt} [/INST]"
+          additionalProperties: false
+        parameters:
+          type: object
+          properties:
             temperature:
-              type: number
-              description: Controls randomness in model's responses. Higher values lead to
-                more random responses.
-              minimum: 0
-              maximum: 2
-              default: 0.7
               example: 0.7
-            token_limit:
-              type: integer
-              description: Maximum number of tokens the model can generate in a single
-                response.
-              minimum: 1
-              maximum: 4096
-              default: 2048
-              example: 2048
-            top_k:
-              type: integer
-              description: Limits the model to consider only the top k most likely next tokens
-                at each step.
-              minimum: 0
-              maximum: 100
-              default: 0
-              example: 0
             top_p:
-              type: number
-              description: Nucleus sampling parameter. The model considers the smallest set of
-                tokens whose cumulative probability exceeds the top_p value.
-              minimum: 0
-              maximum: 1
-              default: 1
-              example: 1
+              example: 0.95
+            stream:
+              example: true
+            max_tokens:
+              example: 4096
+            stop:
+              example: []
+            frequency_penalty:
+              example: 0
+            presence_penalty:
+              example: 0
+          additionalProperties: false
         metadata:
-          type: object
-          properties:
-            engine:
-              type: string
-              description: The engine used by the model.
-              enum:
-                - nitro
-                - openai
-                - hf_inference
-            quantization:
-              type: string
-              description: Quantization parameter of the model.
-              example: Q3_K_L
-            size:
-              type: string
-              description: Size of the model.
-              example: 7B
-      required:
-        - id
-        - object
-        - created
-        - owned_by
-        - state
-        - source_url
-        - parameters
-        - metadata
+          author:
+            type: string
+            example: MistralAI
+          tags:
+            example: ["7B", "Featured", "Foundation Model"]
+          size:
+            example: 4370000000,
+          cover:
+            example: "https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png"
+        engine:
+          example: nitro
     DeleteModelResponse:
       type: object
       properties:
-        id:
-          type: string
-          description: The identifier of the model that was deleted.
-          example: model-zephyr-7B
-        object:
-          type: string
-          description: Type of the object, indicating it's a model.
-          default: model
-        deleted:
-          type: boolean
-          description: Indicates whether the model was successfully deleted.
-          example: true
+        message:
+          example: Not found
     StartModelResponse:
       type: object
       properties:

From ce68ccf178c776dbdcda68132b95539fad93c383 Mon Sep 17 00:00:00 2001
From: hieu-jan <150573299+hieu-jan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 01:47:49 +0900
Subject: [PATCH 2/5] docs: change 127.0.0.1 to localhost

---
 docs/openapi/jan.yaml | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml
index 9981f7308..90e6b9945 100644
--- a/docs/openapi/jan.yaml
+++ b/docs/openapi/jan.yaml
@@ -68,7 +68,7 @@ paths:
         - lang: cURL
           source: |
             curl -X 'POST' \
-              'http://127.0.0.1:1337/v1/chat/completions' \
+              'http://localhost:1337/v1/chat/completions' \
               -H 'accept: application/json' \
               -H 'Content-Type: application/json' \
               -d '{
@@ -115,7 +115,7 @@ paths:
         - lang: cURL
           source: |
             curl -X 'GET' \
-              'http://127.0.0.1:1337/v1/models' \
+              'http://localhost:1337/v1/models' \
               -H 'accept: application/json'
   "/models/download/{model_id}":
     get:
@@ -145,7 +145,7 @@ paths:
         - lang: cURL
           source: |
             curl -X 'GET' \
-              'http://127.0.0.1:1337/v1/models/download/{model_id}' \
+              'http://localhost:1337/v1/models/download/{model_id}' \
               -H 'accept: application/json'
   "/models/{model_id}":
     get:
@@ -178,7 +178,7 @@ paths:
         - lang: cURL
           source: |
             curl -X 'GET' \
-              'http://127.0.0.1:1337/v1/models/{model_id}' \
+              'http://localhost:1337/v1/models/{model_id}' \
               -H 'accept: application/json'
     delete:
       operationId: deleteModel
@@ -209,7 +209,7 @@ paths:
         - lang: cURL
           source: |
             curl -X 'DELETE' \
-              'http://127.0.0.1:1337/v1/models/{model_id}' \
+              'http://localhost:1337/v1/models/{model_id}' \
               -H 'accept: application/json'
   /threads:
     post:

From 45c08597fefadf35d76d187e05578b72a77288ea Mon Sep 17 00:00:00 2001
From: hieu-jan <150573299+hieu-jan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 10:52:48 +0900
Subject: [PATCH 3/5] docs: update DeleteModelResponse

---
 docs/openapi/specs/models.yaml | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/docs/openapi/specs/models.yaml b/docs/openapi/specs/models.yaml
index 791d14880..776ffbd6d 100644
--- a/docs/openapi/specs/models.yaml
+++ b/docs/openapi/specs/models.yaml
@@ -190,8 +190,18 @@ components:
     DeleteModelResponse:
       type: object
       properties:
-        message:
-          example: Not found
+        id:
+          type: string
+          description: The identifier of the model that was deleted.
+          example: mistral-ins-7b-q4
+        object:
+          type: string
+          description: Type of the object, indicating it's a model.
+          default: model
+        deleted:
+          type: boolean
+          description: Indicates whether the model was successfully deleted.
+          example: true
     StartModelResponse:
       type: object
       properties:

From b4ffe006fed494f610c3248892c57ec711b6799f Mon Sep 17 00:00:00 2001
From: hieu-jan <150573299+hieu-jan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 10:55:24 +0900
Subject: [PATCH 4/5] docs: format .yaml

---
 docs/openapi/specs/assistants.yaml |  2 +-
 docs/openapi/specs/chat.yaml       | 17 +++++++++++------
 docs/openapi/specs/messages.yaml   |  2 +-
 docs/openapi/specs/models.yaml     |  2 +-
 docs/openapi/specs/threads.yaml    |  2 +-
 5 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/docs/openapi/specs/assistants.yaml b/docs/openapi/specs/assistants.yaml
index d784c315a..5db1f6a97 100644
--- a/docs/openapi/specs/assistants.yaml
+++ b/docs/openapi/specs/assistants.yaml
@@ -316,4 +316,4 @@ components:
         deleted:
           type: boolean
           description: Indicates whether the assistant was successfully deleted.
-          example: true
\ No newline at end of file
+          example: true
diff --git a/docs/openapi/specs/chat.yaml b/docs/openapi/specs/chat.yaml
index b324501a8..3aeff380f 100644
--- a/docs/openapi/specs/chat.yaml
+++ b/docs/openapi/specs/chat.yaml
@@ -16,7 +16,8 @@ components:
         stream:
           type: boolean
           default: true
-          description: Enables continuous output generation, allowing for streaming of
+          description:
+            Enables continuous output generation, allowing for streaming of
             model responses.
         model:
           type: string
@@ -25,23 +26,27 @@ components:
         max_tokens:
           type: number
           default: 2048
-          description: The maximum number of tokens the model will generate in a single
+          description:
+            The maximum number of tokens the model will generate in a single
             response.
         stop:
           type: arrays
           example:
             - hello
-          description: Defines specific tokens or phrases at which the model will stop
+          description:
+            Defines specific tokens or phrases at which the model will stop
             generating further output/
         frequency_penalty:
           type: number
           default: 0
-          description: Adjusts the likelihood of the model repeating words or phrases in
+          description:
+            Adjusts the likelihood of the model repeating words or phrases in
             its output.
         presence_penalty:
           type: number
           default: 0
-          description: Influences the generation of new and varied concepts in the model's
+          description:
+            Influences the generation of new and varied concepts in the model's
             output.
         temperature:
           type: number
@@ -188,4 +193,4 @@ components:
             total_tokens:
               type: integer
               example: 533
-              description: Total number of tokens used
\ No newline at end of file
+              description: Total number of tokens used
diff --git a/docs/openapi/specs/messages.yaml b/docs/openapi/specs/messages.yaml
index d9d7d87a4..9a0799f6a 100644
--- a/docs/openapi/specs/messages.yaml
+++ b/docs/openapi/specs/messages.yaml
@@ -309,4 +309,4 @@ components:
         data:
           type: array
           items:
-            $ref: "#/components/schemas/MessageFileObject"
\ No newline at end of file
+            $ref: "#/components/schemas/MessageFileObject"
diff --git a/docs/openapi/specs/models.yaml b/docs/openapi/specs/models.yaml
index 776ffbd6d..21276f899 100644
--- a/docs/openapi/specs/models.yaml
+++ b/docs/openapi/specs/models.yaml
@@ -96,7 +96,7 @@ components:
           type: string
           description: |
             The identifier of the model.
-          example: ztrinity-v1.2-7b
+          example: trinity-v1.2-7b
         object:
           type: string
           description: |
diff --git a/docs/openapi/specs/threads.yaml b/docs/openapi/specs/threads.yaml
index fe00f7588..825f166f1 100644
--- a/docs/openapi/specs/threads.yaml
+++ b/docs/openapi/specs/threads.yaml
@@ -224,4 +224,4 @@ components:
         deleted:
           type: boolean
           description: Indicates whether the thread was successfully deleted.
-          example: true
\ No newline at end of file
+          example: true

From 64cabe3d56c6759688cf71555a43b6d469d05818 Mon Sep 17 00:00:00 2001
From: hieu-jan <150573299+hieu-jan@users.noreply.github.com>
Date: Wed, 24 Jan 2024 11:37:08 +0900
Subject: [PATCH 5/5] chore: lint .yaml

---
 docs/openapi/jan.yaml            | 42 ++++++++++++++---------------
 docs/openapi/specs/chat.yaml     | 15 ++++-------
 docs/openapi/specs/messages.yaml | 45 ++++++++++++++++----------------
 docs/openapi/specs/models.yaml   | 22 +++++++++++-----
 docs/openapi/specs/threads.yaml  |  2 +-
 5 files changed, 66 insertions(+), 60 deletions(-)

diff --git a/docs/openapi/jan.yaml b/docs/openapi/jan.yaml
index 90e6b9945..864c80fdf 100644
--- a/docs/openapi/jan.yaml
+++ b/docs/openapi/jan.yaml
@@ -72,27 +72,27 @@ paths:
               -H 'accept: application/json' \
               -H 'Content-Type: application/json' \
               -d '{
-              "messages": [
-                {
-                  "content": "You are a helpful assistant.",
-                  "role": "system"
-                },
-                {
-                  "content": "Hello!",
-                  "role": "user"
-                }
-              ],
-              "model": "tinyllama-1.1b",
-              "stream": true,
-              "max_tokens": 2048,
-              "stop": [
-                "hello"
-              ],
-              "frequency_penalty": 0,
-              "presence_penalty": 0,
-              "temperature": 0.7,
-              "top_p": 0.95
-            }'
+                "messages": [
+                  {
+                    "content": "You are a helpful assistant.",
+                    "role": "system"
+                  },
+                  {
+                    "content": "Hello!",
+                    "role": "user"
+                  }
+                ],
+                "model": "tinyllama-1.1b",
+                "stream": true,
+                "max_tokens": 2048,
+                "stop": [
+                  "hello"
+                ],
+                "frequency_penalty": 0,
+                "presence_penalty": 0,
+                "temperature": 0.7,
+                "top_p": 0.95
+              }'
   /models:
     get:
       operationId: listModels
diff --git a/docs/openapi/specs/chat.yaml b/docs/openapi/specs/chat.yaml
index 3aeff380f..cfa391598 100644
--- a/docs/openapi/specs/chat.yaml
+++ b/docs/openapi/specs/chat.yaml
@@ -16,8 +16,7 @@ components:
         stream:
           type: boolean
           default: true
-          description:
-            Enables continuous output generation, allowing for streaming of
+          description: Enables continuous output generation, allowing for streaming of
             model responses.
         model:
           type: string
@@ -26,27 +25,23 @@ components:
         max_tokens:
           type: number
           default: 2048
-          description:
-            The maximum number of tokens the model will generate in a single
+          description: The maximum number of tokens the model will generate in a single
             response.
         stop:
           type: arrays
           example:
             - hello
-          description:
-            Defines specific tokens or phrases at which the model will stop
+          description: Defines specific tokens or phrases at which the model will stop
             generating further output/
         frequency_penalty:
           type: number
           default: 0
-          description:
-            Adjusts the likelihood of the model repeating words or phrases in
+          description: Adjusts the likelihood of the model repeating words or phrases in
             its output.
         presence_penalty:
           type: number
           default: 0
-          description:
-            Influences the generation of new and varied concepts in the model's
+          description: Influences the generation of new and varied concepts in the model's
             output.
         temperature:
           type: number
diff --git a/docs/openapi/specs/messages.yaml b/docs/openapi/specs/messages.yaml
index 9a0799f6a..6f5fe1a58 100644
--- a/docs/openapi/specs/messages.yaml
+++ b/docs/openapi/specs/messages.yaml
@@ -1,3 +1,4 @@
+---
 components:
   schemas:
     MessageObject:
@@ -75,7 +76,7 @@ components:
           example: msg_abc123
         object:
           type: string
-          description: "Type of the object, indicating it's a thread message."
+          description: Type of the object, indicating it's a thread message.
           default: thread.message
         created_at:
           type: integer
@@ -88,7 +89,7 @@ components:
           example: thread_abc123
         role:
           type: string
-          description: "Role of the sender, either 'user' or 'assistant'."
+          description: Role of the sender, either 'user' or 'assistant'.
           example: user
         content:
           type: array
@@ -97,7 +98,7 @@ components:
             properties:
               type:
                 type: string
-                description: "Type of content, e.g., 'text'."
+                description: Type of content, e.g., 'text'.
                 example: text
               text:
                 type: object
@@ -110,21 +111,21 @@ components:
                     type: array
                     items:
                       type: string
-                    description: "Annotations for the text content, if any."
+                    description: Annotations for the text content, if any.
                     example: []
         file_ids:
           type: array
           items:
             type: string
-          description: "Array of file IDs associated with the message, if any."
+          description: Array of file IDs associated with the message, if any.
           example: []
         assistant_id:
           type: string
-          description: "Identifier of the assistant involved in the message, if applicable."
+          description: Identifier of the assistant involved in the message, if applicable.
           example: null
         run_id:
           type: string
-          description: "Run ID associated with the message, if applicable."
+          description: Run ID associated with the message, if applicable.
           example: null
         metadata:
           type: object
@@ -139,7 +140,7 @@ components:
           example: msg_abc123
         object:
           type: string
-          description: "Type of the object, indicating it's a thread message."
+          description: Type of the object, indicating it's a thread message.
           example: thread.message
         created_at:
           type: integer
@@ -152,7 +153,7 @@ components:
           example: thread_abc123
         role:
           type: string
-          description: "Role of the sender, either 'user' or 'assistant'."
+          description: Role of the sender, either 'user' or 'assistant'.
           example: user
         content:
           type: array
@@ -161,7 +162,7 @@ components:
             properties:
               type:
                 type: string
-                description: "Type of content, e.g., 'text'."
+                description: Type of content, e.g., 'text'.
                 example: text
               text:
                 type: object
@@ -174,21 +175,21 @@ components:
                     type: array
                     items:
                       type: string
-                    description: "Annotations for the text content, if any."
+                    description: Annotations for the text content, if any.
                     example: []
         file_ids:
           type: array
           items:
             type: string
-          description: "Array of file IDs associated with the message, if any."
+          description: Array of file IDs associated with the message, if any.
           example: []
         assistant_id:
           type: string
-          description: "Identifier of the assistant involved in the message, if applicable."
+          description: Identifier of the assistant involved in the message, if applicable.
           example: null
         run_id:
           type: string
-          description: "Run ID associated with the message, if applicable."
+          description: Run ID associated with the message, if applicable.
           example: null
         metadata:
           type: object
@@ -199,7 +200,7 @@ components:
       properties:
         object:
           type: string
-          description: "Type of the object, indicating it's a list."
+          description: Type of the object, indicating it's a list.
           default: list
         data:
           type: array
@@ -226,7 +227,7 @@ components:
           example: msg_abc123
         object:
           type: string
-          description: "Type of the object, indicating it's a thread message."
+          description: Type of the object, indicating it's a thread message.
           example: thread.message
         created_at:
           type: integer
@@ -239,7 +240,7 @@ components:
           example: thread_abc123
         role:
           type: string
-          description: "Role of the sender, either 'user' or 'assistant'."
+          description: Role of the sender, either 'user' or 'assistant'.
           example: user
         content:
           type: array
@@ -248,7 +249,7 @@ components:
             properties:
               type:
                 type: string
-                description: "Type of content, e.g., 'text'."
+                description: Type of content, e.g., 'text'.
               text:
                 type: object
                 properties:
@@ -260,20 +261,20 @@ components:
                     type: array
                     items:
                       type: string
-                    description: "Annotations for the text content, if any."
+                    description: Annotations for the text content, if any.
         file_ids:
           type: array
           items:
             type: string
-          description: "Array of file IDs associated with the message, if any."
+          description: Array of file IDs associated with the message, if any.
           example: []
         assistant_id:
           type: string
-          description: "Identifier of the assistant involved in the message, if applicable."
+          description: Identifier of the assistant involved in the message, if applicable.
           example: null
         run_id:
           type: string
-          description: "Run ID associated with the message, if applicable."
+          description: Run ID associated with the message, if applicable.
           example: null
         metadata:
           type: object
diff --git a/docs/openapi/specs/models.yaml b/docs/openapi/specs/models.yaml
index 21276f899..40e6abaaf 100644
--- a/docs/openapi/specs/models.yaml
+++ b/docs/openapi/specs/models.yaml
@@ -43,7 +43,9 @@ components:
         description:
           type: string
           description: Description of the model.
-          example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
+          example:
+            Trinity is an experimental model merge using the Slerp method.
+            Recommended for daily assistance purposes.
         format:
           type: string
           description: State format of the model, distinct from the engine.
@@ -82,11 +84,14 @@ components:
             type: string
             example: Jan
           tags:
-            example: ["7B", "Merged", "Featured"]
+            example:
+              - 7B
+              - Merged
+              - Featured
           size:
             example: 4370000000,
           cover:
-            example: "https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png"
+            example: https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1.2-7b/cover.png
         engine:
           example: nitro
     ModelObject:
@@ -141,7 +146,9 @@ components:
         description:
           type: string
           description: Description of the model.
-          example: Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.
+          example:
+            Trinity is an experimental model merge using the Slerp method.
+            Recommended for daily assistance purposes.
         format:
           type: string
           description: State format of the model, distinct from the engine.
@@ -180,11 +187,14 @@ components:
             type: string
             example: MistralAI
           tags:
-            example: ["7B", "Featured", "Foundation Model"]
+            example:
+              - 7B
+              - Featured
+              - Foundation Model
           size:
             example: 4370000000,
           cover:
-            example: "https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png"
+            example: https://raw.githubusercontent.com/janhq/jan/main/models/mistral-ins-7b-q4/cover.png
         engine:
           example: nitro
     DeleteModelResponse:
diff --git a/docs/openapi/specs/threads.yaml b/docs/openapi/specs/threads.yaml
index 825f166f1..40b2463fa 100644
--- a/docs/openapi/specs/threads.yaml
+++ b/docs/openapi/specs/threads.yaml
@@ -142,7 +142,7 @@ components:
                 example: Jan
               instructions:
                 type: string
-                description: |
+                description: >
                   The instruction of assistant, defaults to "Be my grammar corrector"
               model:
                 type: object