将Ollama连接到Pot时出现报错“测试失败Type Error：Faild to fetch”.

[BurningSky0306]

Description

在启动Ollama之后，我能够直接在Windows PowerShell中与模型对话。同时，我也能够在Logseq中使用“Ollama-Logseq-Plugin”来调用模型进行对话，但是我无法将Ollama添加到Pot中。在这个过程中，我尝试了qwen:7b, mistral:7b, gemma:7b, llama2:7b.这些模型，都出现了同样的问题。

Ollama版本：0.1.28
CPU：AMD R5-5600H
GPU：NVIDIA GTX1650

我在Windows PowerShell中查看了对应的报错信息，具体如下：

PS C:\Users\Lenovo> ollama serve
time=2024-03-05T11:25:49.684+08:00 level=INFO source=images.go:710 msg="total blobs: 25"
time=2024-03-05T11:25:49.711+08:00 level=INFO source=images.go:717 msg="total unused blobs removed: 0"
time=2024-03-05T11:25:49.714+08:00 level=INFO source=routes.go:1021 msg="Listening on 127.0.0.1:11434 (version 0.1.28)"
time=2024-03-05T11:25:49.714+08:00 level=INFO source=payload_common.go:107 msg="Extracting dynamic libraries..."
time=2024-03-05T11:25:49.883+08:00 level=INFO source=payload_common.go:146 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cpu cuda_v11.3]"
[GIN] 2024/03/05 - 11:25:56 | 200 |     12.9131ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/03/05 - 11:25:57 | 200 |       9.464ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/03/05 - 11:25:57 | 200 |     10.3098ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/03/05 - 11:25:58 | 200 |     10.6555ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2024/03/05 - 11:25:58 | 200 |     10.2732ms |       127.0.0.1 | GET      "/api/tags"
time=2024-03-05T11:26:04.714+08:00 level=INFO source=gpu.go:94 msg="Detecting GPU type"
time=2024-03-05T11:26:04.714+08:00 level=INFO source=gpu.go:265 msg="Searching for GPU management library nvml.dll"
time=2024-03-05T11:26:04.722+08:00 level=INFO source=gpu.go:311 msg="Discovered GPU libraries: [c:\\Windows\\System32\\nvml.dll C:\\Windows\\system32\\nvml.dll]"
time=2024-03-05T11:26:05.548+08:00 level=INFO source=gpu.go:99 msg="Nvidia GPU detected"
time=2024-03-05T11:26:05.548+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-03-05T11:26:05.583+08:00 level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 7.5"
time=2024-03-05T11:26:05.583+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-03-05T11:26:05.596+08:00 level=INFO source=gpu.go:146 msg="CUDA Compute Capability detected: 7.5"
time=2024-03-05T11:26:05.596+08:00 level=INFO source=cpu_common.go:11 msg="CPU has AVX2"
time=2024-03-05T11:26:05.596+08:00 level=INFO source=dyn_ext_server.go:385 msg="Updating PATH to C:\\Users\\Lenovo\\AppData\\Local\\Temp\\ollama868531629\\cuda_v11.3;C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Windows\\System32\\OpenSSH\\;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR;C:\\Program Files\\dotnet\\;D:\\MPlusEMM\\;D:\\MATLAB2023aEMM\\bin;C:\\Users\\Lenovo\\AppData\\Local\\Microsoft\\WindowsApps;D:\\ffmpegEMM\\ffmpeg\\bin;C:\\Users\\Lenovo\\AppData\\Local\\Pandoc\\;C:\\Users\\Lenovo\\AppData\\Local\\Programs\\Ollama"
loading library C:\Users\Lenovo\AppData\Local\Temp\ollama868531629\cuda_v11.3\ext_server.dll
time=2024-03-05T11:26:05.620+08:00 level=INFO source=dyn_ext_server.go:90 msg="Loading Dynamic llm server: C:\\Users\\Lenovo\\AppData\\Local\\Temp\\ollama868531629\\cuda_v11.3\\ext_server.dll"
time=2024-03-05T11:26:05.620+08:00 level=INFO source=dyn_ext_server.go:150 msg="Initializing llama server"
ggml_init_cublas: GGML_CUDA_FORCE_MMQ:   no
ggml_init_cublas: CUDA_USE_TENSOR_CORES: yes
ggml_init_cublas: found 1 CUDA devices:
  Device 0: GeForce GTX 1650, compute capability 7.5, VMM: yes
llama_model_loader: loaded meta data with 20 key-value pairs and 387 tensors from C:\Users\Lenovo\.ollama\models\blobs\sha256-87f26aae09c7f052de93ff98a2282f05822cc6de4af1a2a159c5bd1acbd10ec4 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen2
llama_model_loader: - kv   1:                               general.name str              = Qwen2-beta-7B-Chat
llama_model_loader: - kv   2:                          qwen2.block_count u32              = 32
llama_model_loader: - kv   3:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 4096
llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 11008
llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 32
llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 32
llama_model_loader: - kv   8:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv   9:                qwen2.use_parallel_residual bool             = true
llama_model_loader: - kv  10:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  11:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  12:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  13:                      tokenizer.ggml.merges arr[str,151387]  = ["臓 臓", "臓臓 臓臓", "i n", "臓 t",...
llama_model_loader: - kv  14:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  15:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  17:                    tokenizer.chat_template str              = {% for message in messages %}{{'<|im_...
llama_model_loader: - kv  18:               general.quantization_version u32              = 2
llama_model_loader: - kv  19:                          general.file_type u32              = 2
llama_model_loader: - type  f32:  161 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
llm_load_vocab: special tokens definition check successful ( 293/151936 ).
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 151936
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 32
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 4096
llm_load_print_meta: n_embd_v_gqa     = 4096
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: n_ff             = 11008
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 2
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_yarn_orig_ctx  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = Q4_0
llm_load_print_meta: model params     = 7.72 B
llm_load_print_meta: model size       = 4.20 GiB (4.67 BPW)
llm_load_print_meta: general.name     = Qwen2-beta-7B-Chat
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 30 '?'
llm_load_tensors: ggml ctx size =    0.30 MiB
llm_load_tensors: offloading 17 repeating layers to GPU
llm_load_tensors: offloaded 17/33 layers to GPU
llm_load_tensors:        CPU buffer size =  4297.21 MiB
llm_load_tensors:      CUDA0 buffer size =  1846.89 MiB
...................................................................................
llama_new_context_with_model: n_ctx      = 2048
llama_new_context_with_model: freq_base  = 10000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:  CUDA_Host KV buffer size =   480.00 MiB
llama_kv_cache_init:      CUDA0 KV buffer size =   544.00 MiB
llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB
llama_new_context_with_model:  CUDA_Host input buffer size   =    13.02 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   148.00 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =   320.75 MiB
llama_new_context_with_model: graph splits (measure): 3
{"function":"initialize","level":"INFO","line":433,"msg":"initializing slots","n_slots":1,"tid":"20388","timestamp":1709609168}
{"function":"initialize","level":"INFO","line":445,"msg":"new slot","n_ctx_slot":2048,"slot_id":0,"tid":"20388","timestamp":1709609168}
time=2024-03-05T11:26:08.854+08:00 level=INFO source=dyn_ext_server.go:161 msg="Starting llama main loop"
{"function":"update_slots","level":"INFO","line":1565,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"21248","timestamp":1709609168}
{"function":"launch_slot_with_data","level":"INFO","line":826,"msg":"slot is processing task","slot_id":0,"task_id":0,"tid":"21248","timestamp":1709609168}
{"function":"update_slots","level":"INFO","line":1801,"msg":"slot progression","n_past":0,"n_prompt_tokens_processed":67,"slot_id":0,"task_id":0,"tid":"21248","timestamp":1709609168}
{"function":"update_slots","level":"INFO","line":1825,"msg":"kv cache rm [p0, end)","p0":0,"slot_id":0,"task_id":0,"tid":"21248","timestamp":1709609168}
CUDA error: out of memory
  current device: 0, in function ggml_cuda_pool_malloc_vmm at C:\Users\jmorg\git\ollama\llm\llama.cpp\ggml-cuda.cu:8583
  cuMemCreate(&handle, reserve_size, &prop, 0)
GGML_ASSERT: C:\Users\jmorg\git\ollama\llm\llama.cpp\ggml-cuda.cu:256: !"CUDA error"
PS C:\Users\Lenovo>

我在Windows PowerShell中启动了Ollama服务后，在Pot中尝试进行连接，随后就出现了“CUDA error: out of memory”的错误。我查询了Ollama有关这个问题的issue，发现有人提到更新Ollama到0.1.28版本后就没有这个问题了。我更新到了0.1.28版本后，在将Ollama连接到Pot时仍然存在该问题，但是在将Ollama通过"Ollama-Logseq-Plugin"连接到Logseq中就没有出现该问题。

Reproduction

1.通过Windows PowerShell启动Ollama或通过快捷方式启动Ollama
2. 打开Pot
3. 服务设置
4. 添加内置服务“Ollama”
5. 模型设置为“qwen:7b"（我已经将该模型下载到电脑）
6. Pot能够检测到Ollama

7. 点击”保存“
8. 出现报错”测试失败Type Error: Faild fetch"

Platform

Windows

System Version

Windows 10 家庭中文版 22H2

Window System (Linux Only)

None

Software Version

Pot 2.7.9

Log File

No response

Additional Information

其实在最开始我更新Pot到2.7.9，第一次安装Ollama，并通过Pot下载Gemma:2b模型时，我能够正常将Ollama连接到Pot中并在Pot中调用模型进行翻译，但是后续我自行在Windows PowerShell中通过命令行安装更多的模型后，我就无法再将更多模型连接到Pot中去了，我尝试了重装Ollama并在Pot中重新添加内置服务“Ollama”，但是在这之后就一直无法将Ollama连接到Pot中了。
我在Logseq中能够通过“Ollama-Logseq-Plugin"来调用模型进行对话，这是该插件的Github页面：Ollama-Logseq-Plugin