Improve interface compatibility (#954)

* Improve interface compatibility

    Add Dockerfile for Linux platform

* del unimportant comments

* Update README.md

Author: zhaohb

modules/ollama_openvino/Dockerfile_genai

@@ -0,0 +1,46 @@
+FROM ubuntu:20.04
+
+SHELL ["/bin/bash", "-c"]
+
+ENV no_proxy=http://Child-mu.intel.com:912
+ENV ftp_proxy=http://Child-mu.intel.com:912
+ENV http_proxy=http://Child-mu.intel.com:912
+ENV https_proxy=http://Child-mu.intel.com:912
+
+RUN apt-get update && apt install -y software-properties-common
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.10
+RUN ln -sf /usr/bin/python3.10 /usr/bin/python3
+
+RUN apt-get install -y ca-certificates git wget curl gcc g++ \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /home/ollama_ov_server
+ARG GOVERSION=1.24.1
+RUN curl -fsSL https://golang.org/dl/go${GOVERSION}.linux-$(case $(uname -m) in x86_64) echo amd64 ;; aarch64) echo arm64 ;; esac).tar.gz | tar xz -C /usr/local
+ENV PATH=/usr/local/go/bin:$PATH
+
+RUN wget https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_ubuntu20_2025.2.0.0.dev20250320_x86_64.tar.gz
+RUN tar -xzf openvino_genai_ubuntu20_2025.2.0.0.dev20250320_x86_64.tar.gz
+ENV GENAI_DIR=/home/ollama_ov_server/openvino_genai_ubuntu20_2025.2.0.0.dev20250320_x86_64
+
+ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$GENAI_DIR/runtime/3rdparty/tbb/lib:$GENAI_DIR/runtime/lib/intel64
+
+ENV CGO_ENABLED=1
+ENV GODEBUG=cgocheck=0
+
+ENV CGO_LDFLAGS=-L$GENAI_DIR/runtime/lib/intel64
+ENV CGO_CFLAGS=-I$GENAI_DIR/runtime/include
+
+WORKDIR /home/ollama_ov_server
+RUN git clone https://github.com/zhaohb/ollama_ov.git
+WORKDIR /home/ollama_ov_server/ollama_ov
+
+RUN go build -o /bin/ollama .
+
+ENV OLLAMA_HOST=0.0.0.0:11434
+EXPOSE 11434
+ENTRYPOINT ["/bin/ollama"]
+CMD ["serve"]

modules/ollama_openvino/README.md

@@ -578,7 +578,7 @@ See the [API documentation](./docs/api.md) for all endpoints.
 Getting started with large language models and using the [GenAI](https://github.com/openvinotoolkit/openvino.genai) backend.
 
 <div style="text-align:center;">
-  <img src="./images/ollama_ov_streaming.gif" alt="Ollama-OV" width="900" height="400">
+  <img src="./images/ollama_openvino_new.gif" alt="Ollama-OV" width="900" height="400">
 </div>
 
 We provide two ways to download the executable file of Ollama, one is to download it from Google Drive, and the other is to download it from Baidu Drive:
@@ -591,11 +591,21 @@ We provide two ways to download the executable file of Ollama, one is to downloa
 
 ## 百度云盘
 ### Windows
-[Download exe](https://pan.baidu.com/s/1jwolOPTnt48hX_C0f3oUlQ?pwd=awy4) + [Download OpenVINO GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_windows_2025.2.0.0.dev20250320_x86_64.zip)
+[Download exe](https://pan.baidu.com/s/10SQLKaGOYIR3NrIhig1xgQ?pwd=8v8w) + [Download OpenVINO GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_windows_2025.2.0.0.dev20250320_x86_64.zip)
 
 ### Linux(Ubuntu 22.04)
-[Download](https://pan.baidu.com/s/11oTt0UIuuNGNffcC0NLk5g?pwd=1pa3) + [Donwload OpenVINO GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64.tar.gz)
+[Download](https://pan.baidu.com/s/1WhzcKRQY_KVLZhy5oa0UIA?pwd=zxgx) + [Donwload OpenVINO GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64.tar.gz)
 
+## Docker
+### Linux
+We also prepared a Dockerfile to help developers quickly build Docker images: [Dockerfile](./Dockerfile_genai)
+```shell
+docker build -t ollama_openvino:v1 -f Dockerfile_genai .
+```
+then
+```shell
+docker run --rm -it ollama_openvino:v1
+```
 
 ## Model library
 The native Ollama only supports models in the GGUF format, the Ollama-OV invoke OpenVINO GenAI which requires models in the OpenVINO format. Therefore, we have enabled support for OpenVINO model files in Ollama. For public LLMs, you can access and download OpenVINO IR model from HuggingFace or ModelScope:
@@ -630,10 +640,10 @@ The native Ollama only supports models in the GGUF format, the Ollama-OV invoke
 
 Just provide above model link as example for part models, for other LLMs, you can check [OpenVINO GenAI model support list](https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md). If you have customized LLM, please follow [model conversion step of GenAI](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#converting-and-compressing-text-generation-model-from-hugging-face-library). 
 
-## Performance to reference
+<!-- ## Performance to reference
 | Model                   | Ollama-OV with GPU (Driver version：32.0.101.6042)    | Ollama-OV with NPU (Driver version：32.0.100.3104)  | Device
 |-------------------------|---------------|-----------------|-----------------|
-| DeepSeek-R1-Distill-Qwen-7B | 19.58 tokens/s | 11.73 tokens/s | Intel(R) Core(TM) Ultra 7 268V 2.20GHz + 32G MEM |
+| DeepSeek-R1-Distill-Qwen-7B | 19.58 tokens/s | 11.73 tokens/s | Intel(R) Core(TM) Ultra 7 268V 2.20GHz + 32G MEM | -->
 
 
 
@@ -645,6 +655,7 @@ We added two new parameters to Modelfile based on the original parameters:
 | max_new_token          | The maximum number of tokens generated by genai (Default: 2048)    | int        | max_new_token 4096          
 
 ## Quick start
+
 ### Start Ollama
 
 1. First, set GODEGUG=cgocheck=0 env:
@@ -659,7 +670,7 @@ We added two new parameters to Modelfile based on the original parameters:
    set GODEBUG=cgocheck=0
    ```
 
-2. Next, `ollama serve` is used when you want to start ollama without running the desktop application:
+2. Next, `ollama serve` is used when you want to start ollama (You must use the Ollama compiled by ollama_ov to start the serve):
 
    ```shell
    ollama serve
@@ -712,17 +723,26 @@ Let's take [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://hf-mirror.com/deeps
    ```shell
    cd openvino_genai_windows_2025.2.0.0.dev20250320_x86_64
    setupvars.bat
-   
-   set GODEBUG=cgocheck=0
    ```
 
 5. Create the model in Ollama
 
    ```shell
    ollama create DeepSeek-R1-Distill-Qwen-7B-int4-ov:v1 -f Modelfile
    ```
+   You will see output similar to the following:
+   ```shell
+      gathering model components 
+      copying file sha256:77acf6474e4cafb67e57fe899264e9ca39a215ad7bb8f5e6b877dcfa0fabf919 100% 
+      using existing layer sha256:77acf6474e4cafb67e57fe899264e9ca39a215ad7bb8f5e6b877dcfa0fabf919 
+      creating new layer sha256:9b345e4ef9f87ebc77c918a4a0cee4a83e8ea78049c0ee2dc1ddd2a337cf7179 
+      creating new layer sha256:ea49523d744c40bc900b4462c43132d1c8a8de5216fa8436cc0e8b3e89dddbe3 
+      creating new layer sha256:b6bf5bcca7a15f0a06e22dcf5f41c6c0925caaab85ec837067ea98b843bf917a 
+      writing manifest 
+      success 
+   ```
 
-6. Run the model
+6. Run the model                     
 
    ```shell
    ollama run DeepSeek-R1-Distill-Qwen-7B-int4-ov:v1
@@ -754,10 +774,6 @@ ollama ps
 ollama stop DeepSeek-R1-Distill-Qwen-7B-int4-ov:v1 
 ```
 
-### Start Ollama
-
-`ollama serve` is used when you want to start ollama without running the desktop application.
-
 ## Building from source
 
 Install prerequisites:
@@ -782,12 +798,10 @@ Then build and run Ollama from the root directory of the repository:
 
 3. Initialize the GenAI environment
 
-   Download GenAI runtime from [GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_windows_2025.2.0.0.dev20250320_x86_64.zip), then extract it to a directory openvino_genai_windows_2025.2.0.0.dev20250320_x86_64.
+   Download GenAI runtime from [GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_windows_2025.2.0.0.dev20250320_x86_64.zip), then extract it to a directory openvino_genai_windows_2025.2.0.0.dev20250320_x86_64 .
    ```shell
    cd openvino_genai_windows_2025.2.0.0.dev20250320_x86_64
    setupvars.bat
-
-   set GODEBUG=cgocheck=0
    ```
 
 4. Setting cgo environment variables
@@ -801,7 +815,7 @@ Then build and run Ollama from the root directory of the repository:
    go build -o ollama.exe
    ```
 
-6. If you don't want to recompile ollama, you can choose to directly use the compiled executable file, and then initialize the genai environment in `step 3` to run ollama directly. The compiled executable file is placed in the `dist` directory: [ollama](dist/windows/ollama.exe).
+6. If you don't want to recompile ollama, you can choose to directly use the compiled executable file, and then initialize the genai environment in `step 3` to run ollama directly [ollama](https://drive.google.com/file/d/1iizO9iLhSJGFUu6BgY3EwOchrCyzImUN/view?usp=drive_link).
    
    But if you encounter the error when executing ollama.exe, it is recommended that you recompile from source code.
    ```shell
@@ -822,12 +836,10 @@ Then build and run Ollama from the root directory of the repository:
 
 3. Initialize the GenAI environment
 
-   Download GenAI runtime from [GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_ubuntu20_2025.2.0.0.dev20250320_x86_64.tar.gz), then extract it to a directory openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64.dev20250308_x86_64.
+   Download GenAI runtime from [GenAI](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/nightly/2025.2.0.0.dev20250320/openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64.tar.gz), then extract it to a directory openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64.
    ```shell
    cd openvino_genai_ubuntu22_2025.2.0.0.dev20250320_x86_64 
    source setupvars.sh
-
-   export GODEBUG=cgocheck=0
    ```
 
 4. Setting cgo environment variables
@@ -841,24 +853,44 @@ Then build and run Ollama from the root directory of the repository:
    go build -o ollama
    ```
 
-6. If you don't want to recompile ollama, you can choose to directly use the compiled executable file, and then initialize the genai environment in `step 3` to run ollama directly. The compiled executable file is placed in the `dist` directory: [ollama](dist/linux/ollama).
+6. If you don't want to recompile ollama, you can choose to directly use the compiled executable file, and then initialize the genai environment in `step 3` to run ollama directly [ollama](https://drive.google.com/file/d/1HEyZNNCbWSidKNQl4MRsD8FuwEZtdyew/view?usp=drive_link). 
 
    If you encounter problems during use, it is recommended to rebuild from source.
 
 
 ### Running local builds
 
-Next, start the server:
+1. First, set GODEGUG=cgocheck=0 env:
 
-```shell
-ollama serve
-```
+   #### Linux
+   ```shell
+   export GODEGUG=cgocheck=0
+   ```
 
-Finally, in a separate shell, run a model:
+   #### Windows 
+   ```shell
+   set GODEBUG=cgocheck=0
+   ```
 
-```shell
-ollama run DeepSeek-R1-Distill-Qwen-7B-int4-ov:v1 
-```
+2. Next, start the server:
+
+   ```shell
+   ollama serve
+   ```
+
+3. Finally, in a separate shell, run a model:
+
+   ```shell
+   ollama run DeepSeek-R1-Distill-Qwen-7B-int4-ov:v1 
+   ```
+
+## Community Integrations
+### Terminal
+
+- [oterm](https://github.com/ggozad/oterm)
+   <div style="text-align:center;">
+      <img src="./images/oterm_demo.gif" alt="Ollama-OV" width="900" height="400">
+   </div>
 
 ## Future Development Plan
 Here are some features and improvements planned for future releases:

modules/ollama_openvino/api/types.go

@@ -3,7 +3,6 @@ package api
 import (
 	"encoding/json"
 	"fmt"
-	"log"
 	"log/slog"
 	"math"
 	"os"
@@ -691,7 +690,7 @@ func FormatParams(params map[string][]string) (map[string]interface{}, error) {
 	out := make(map[string]interface{})
 	// iterate params and set values based on json struct tags
 	for key, vals := range params {
-		log.Printf("-----%s: %s", key, vals)
+		// log.Printf("-----%s: %s", key, vals)
 		if opt, ok := jsonOpts[key]; !ok {
 			return nil, fmt.Errorf("unknown parameter '%s'", key)
 		} else {

modules/ollama_openvino/cmd/cmd.go

@@ -96,13 +96,13 @@ func CreateHandler(cmd *cobra.Command, args []string) error {
 	if err != nil {
 		return err
 	}
-	log.Printf(modelfile.String())
+	// log.Printf(modelfile.String())
 
 	status := "gathering model components"
 	spinner := progress.NewSpinner(status)
 	p.Add(status, spinner)
 
-	log.Printf("filepath.Dir(filename): %s", filepath.Dir(filename))
+	// log.Printf("filepath.Dir(filename): %s", filepath.Dir(filename))
 	req, err := modelfile.CreateRequest(filepath.Dir(filename))
 	if err != nil {
 		return err
@@ -667,9 +667,11 @@ func showInfo(resp *api.ShowResponse, w io.Writer) error {
 		if resp.ModelInfo != nil {
 			arch := resp.ModelInfo["general.architecture"].(string)
 			rows = append(rows, []string{"", "architecture", arch})
-			rows = append(rows, []string{"", "parameters", format.HumanNumber(uint64(resp.ModelInfo["general.parameter_count"].(float64)))})
-			rows = append(rows, []string{"", "context length", strconv.FormatFloat(resp.ModelInfo[fmt.Sprintf("%s.context_length", arch)].(float64), 'f', -1, 64)})
-			rows = append(rows, []string{"", "embedding length", strconv.FormatFloat(resp.ModelInfo[fmt.Sprintf("%s.embedding_length", arch)].(float64), 'f', -1, 64)})
+			if arch != "OpenVINO" {
+				rows = append(rows, []string{"", "parameters", format.HumanNumber(uint64(resp.ModelInfo["general.parameter_count"].(float64)))})
+				rows = append(rows, []string{"", "context length", strconv.FormatFloat(resp.ModelInfo[fmt.Sprintf("%s.context_length", arch)].(float64), 'f', -1, 64)})
+				rows = append(rows, []string{"", "embedding length", strconv.FormatFloat(resp.ModelInfo[fmt.Sprintf("%s.embedding_length", arch)].(float64), 'f', -1, 64)})
+			}
 		} else {
 			rows = append(rows, []string{"", "architecture", resp.Details.Family})
 			rows = append(rows, []string{"", "parameters", resp.Details.ParameterSize})

modules/ollama_openvino/images/ollama_openvino_new.gif

@@ -7,7 +7,6 @@ import (
 	"errors"
 	"fmt"
 	"io"
-	"log"
 	"net/http"
 	"os"
 	"os/user"
@@ -48,7 +47,7 @@ func (f Modelfile) CreateRequest(relativeDir string) (*api.CreateRequest, error)
 	params := make(map[string]any)
 
 	for _, c := range f.Commands {
-		log.Printf("c.Name: %s", c.Name)
+		// log.Printf("c.Name: %s", c.Name)
 		switch c.Name {
 		case "model":
 			path, err := expandPath(c.Args, relativeDir)

modules/ollama_openvino/images/oterm_demo.gif

@@ -1040,6 +1040,9 @@ func GetModelInfo(req api.ShowRequest) (*api.ShowResponse, error) {
 	if m.Type == "OpenVINO" {
 		resp.ModelType = m.Type
 		resp.InferDevice = m.InferDevice
+		modelinfo_map := make(map[string]any)
+		modelinfo_map["general.architecture"] = m.Type
+		resp.ModelInfo = modelinfo_map
 		return resp, nil
 	} else {
 		kvData, err := getKVData(m.ModelPath, req.Verbose)