There is a bug in urlopen() when using image_url with credentials.

Look at the urlopen() call in the code handling image_url, likely in the Llava15ChatHandler or related chat format module. The bug is parsing URLs with credentials (user:pass@host). Reproduce with the provided test.py, then trace how the URL is split. Check Python's urllib.parse or the custom parsing used. The fix should ensure credentials are handled before extracting the host/port.

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• I carefully followed the README.md.
• I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

Expect proper image recognition prompt behavior with image_url.

Current Behavior

When using image_url, urlopen() does not recognize the URL properly if the url contains credentials.
It fails to load the image_url because it incorrectly recognizes the common credential URL as a port.

Environment and Context

$ lscpu
Architecture:             x86_64
  CPU op-mode(s):         32-bit, 64-bit
  Address sizes:          39 bits physical, 48 bits virtual
  Byte Order:             Little Endian
CPU(s):                   4
  On-line CPU(s) list:    0-3
Vendor ID:                GenuineIntel
  Model name:             Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz
    CPU family:           6
    Model:                158
    Thread(s) per core:   1
    Core(s) per socket:   4
    Socket(s):            1
    Stepping:             9
    BogoMIPS:             6816.00
    Flags:                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_
                          known_freq pni pclmulqdq ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch pti ssbd ibrs ibpb stibp fsgsbase bmi1 hle avx2 smep 
                          bmi2 erms invpcid rtm rdseed adx smap clflushopt xsaveopt xsavec xgetbv1 xsaves md_clear flush_l1d arch_capabilities
Virtualization features:  
  Hypervisor vendor:      Microsoft
  Virtualization type:    full
Caches (sum of all):      
  L1d:                    128 KiB (4 instances)
  L1i:                    128 KiB (4 instances)
  L2:                     1 MiB (4 instances)
  L3:                     6 MiB (1 instance)
NUMA:                     
  NUMA node(s):           1
  NUMA node0 CPU(s):      0-3
Vulnerabilities:          
  Gather data sampling:   Unknown: Dependent on hypervisor status
  Itlb multihit:          KVM: Mitigation: VMX unsupported
  L1tf:                   Mitigation; PTE Inversion
  Mds:                    Mitigation; Clear CPU buffers; SMT Host state unknown
  Meltdown:               Mitigation; PTI
  Mmio stale data:        Mitigation; Clear CPU buffers; SMT Host state unknown
  Reg file data sampling: Not affected
  Retbleed:               Mitigation; IBRS
  Spec rstack overflow:   Not affected
  Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
  Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
  Spectre v2:             Mitigation; IBRS; IBPB conditional; STIBP disabled; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, KVM SW loop
  Srbds:                  Unknown: Dependent on hypervisor status
  Tsx async abort:        Mitigation; Clear CPU buffers; SMT Host state unknown

$ uname -a
Linux 6.6.87.2-microsoft-standard-WSL2 #1 SMP PREEMPT_DYNAMIC Thu Jun  5 18:30:46 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux

$ python3 --version
Python 3.12.3

$ make --version
GNU Make 4.3
Built for x86_64-pc-linux-gnu
Copyright (C) 1988-2020 Free Software Foundation, Inc.
License GPLv3+: GNU GPL version 3 or later <http://gnu.org/licenses/gpl.html>
This is free software: you are free to change and redistribute it.
There is NO WARRANTY, to the extent permitted by law.

$ g++ --version
g++ (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0
Copyright (C) 2023 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

Failure Information (for bugs)

PoC (Original Bug)

https://github.com/python/cpython/issues/140918

Steps to Reproduce

PoC file (test.py)

from llama_cpp import Llama
from llama_cpp.llama_chat_format import Llava15ChatHandler
chat_handler = Llava15ChatHandler(clip_model_path="./nanollava-mmproj-f16.gguf")
llm = Llama(
  model_path="./nanollava-text-model-f16.gguf",
  chat_handler=chat_handler,
  n_ctx=2048, # n_ctx should be increased to accommodate the imagepo embedding
)
llm.create_chat_completion(
    messages = [
        {"role": "system", "content": "You are an assistant who perfectly describes images."},
        {
            "role": "user",
            "content": [
                {"type" : "text", "text": "What's in this image?"},
                {"type": "image_url", "image_url": {"url": "http://test:test@example.com/image.jpg" } }
            ]
        }
    ]
)

1. Install llama-cpp-python with $ pip install llama-cpp-python
2. make test.py like above
3. Run with $ python3 test.py

Failure Logs

$ python3 test.py
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from ./nanollava-text-model-f16.gguf (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              = nanoLLaVA
llama_model_loader: - kv   2:                          qwen2.block_count u32              = 24
llama_model_loader: - kv   3:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv   4:                     qwen2.embedding_length u32              = 1024
llama_model_loader: - kv   5:                  qwen2.feed_forward_length u32              = 2816
llama_model_loader: - kv   6:                 qwen2.attention.head_count u32              = 16
llama_model_loader: - kv   7:              qwen2.attention.head_count_kv u32              = 16
llama_model_loader: - kv   8:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv   9:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  10:                          general.file_type u32              = 1
llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  12:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  15:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 151645
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  19:                    tokenizer.chat_template str              = {% for message in messages %}{% if lo...
llama_model_loader: - type  f32:  121 tensors
llama_model_loader: - type  f16:  170 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = F16
print_info: file size   = 1.15 GiB (16.00 BPW) 
init_tokenizer: initializing tokenizer for type 2
load: control token: 151644 '<|im_start|>' is not marked as EOG
load: printing all EOG tokens:
load:   - 151643 ('<|endoftext|>')
load:   - 151645 ('<|im_end|>')
load: special tokens cache size = 293
load: token to piece cache size = 0.9338 MB
print_info: arch             = qwen2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 32768
print_info: n_embd           = 1024
print_info: n_layer          = 24
print_info: n_head           = 16
print_info: n_head_kv        = 16
print_info: n_rot            = 64
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 64
print_info: n_embd_head_v    = 64
print_info: n_gqa            = 1
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 2816
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = -1
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 32768
print_info: rope_finetuned   = unknown
print_info: model type       = 0.5B
print_info: model params     = 619.57 M
print_info: general.name     = nanoLLaVA
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
print_info: n_merges         = 151387
print_info: BOS token        = 151645 '<|im_end|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: layer   0 assigned to device CPU, is_swa = 0
load_tensors: layer   1 assigned to device CPU, is_swa = 0
load_tensors: layer   2 assigned to device CPU, is_swa = 0
load_tensors: layer   3 assigned to device CPU, is_swa = 0
load_tensors: layer   4 assigned to device CPU, is_swa = 0
load_tensors: layer   5 assigned to device CPU, is_swa = 0
load_tensors: layer   6 assigned to device CPU, is_swa = 0
load_tensors: layer   7 assigned to device CPU, is_swa = 0
load_tensors: layer   8 assigned to device CPU, is_swa = 0
load_tensors: layer   9 assigned to device CPU, is_swa = 0
load_tensors: layer  10 assigned to device CPU, is_swa = 0
load_tensors: layer  11 assigned to device CPU, is_swa = 0
load_tensors: layer  12 assigned to device CPU, is_swa = 0
load_tensors: layer  13 assigned to device CPU, is_swa = 0
load_tensors: layer  14 assigned to device CPU, is_swa = 0
load_tensors: layer  15 assigned to device CPU, is_swa = 0
load_tensors: layer  16 assigned to device CPU, is_swa = 0
load_tensors: layer  17 assigned to device CPU, is_swa = 0
load_tensors: layer  18 assigned to device CPU, is_swa = 0
load_tensors: layer  19 assigned to device CPU, is_swa = 0
load_tensors: layer  20 assigned to device CPU, is_swa = 0
load_tensors: layer  21 assigned to device CPU, is_swa = 0
load_tensors: layer  22 assigned to device CPU, is_swa = 0
load_tensors: layer  23 assigned to device CPU, is_swa = 0
load_tensors: layer  24 assigned to device CPU, is_swa = 0
load_tensors: tensor 'token_embd.weight' (f16) (and 290 others) cannot be used with preferred buffer type CPU_REPACK, using CPU instead
load_tensors:   CPU_Mapped model buffer size =  1181.97 MiB
....................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 2048
llama_context: n_ctx_per_seq = 2048
llama_context: n_batch       = 512
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: kv_unified    = false
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (2048) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
set_abort_callback: call
llama_context:        CPU  output buffer size =     0.58 MiB
create_memory: n_ctx = 2048 (padded)
llama_kv_cache_unified: layer   0: dev = CPU
llama_kv_cache_unified: layer   1: dev = CPU
llama_kv_cache_unified: layer   2: dev = CPU
llama_kv_cache_unified: layer   3: dev = CPU
llama_kv_cache_unified: layer   4: dev = CPU
llama_kv_cache_unified: layer   5: dev = CPU
llama_kv_cache_unified: layer   6: dev = CPU
llama_kv_cache_unified: layer   7: dev = CPU
llama_kv_cache_unified: layer   8: dev = CPU
llama_kv_cache_unified: layer   9: dev = CPU
llama_kv_cache_unified: layer  10: dev = CPU
llama_kv_cache_unified: layer  11: dev = CPU
llama_kv_cache_unified: layer  12: dev = CPU
llama_kv_cache_unified: layer  13: dev = CPU
llama_kv_cache_unified: layer  14: dev = CPU
llama_kv_cache_unified: layer  15: dev = CPU
llama_kv_cache_unified: layer  16: dev = CPU
llama_kv_cache_unified: layer  17: dev = CPU
llama_kv_cache_unified: layer  18: dev = CPU
llama_kv_cache_unified: layer  19: dev = CPU
llama_kv_cache_unified: layer  20: dev = CPU
llama_kv_cache_unified: layer  21: dev = CPU
llama_kv_cache_unified: layer  22: dev = CPU
llama_kv_cache_unified: layer  23: dev = CPU
llama_kv_cache_unified:        CPU KV buffer size =   192.00 MiB
llama_kv_cache_unified: size =  192.00 MiB (  2048 cells,  24 layers,  1/1 seqs), K (f16):   96.00 MiB, V (f16):   96.00 MiB
llama_context: enumerating backends
llama_context: backend_ptrs.size() = 1
llama_context: max_nodes = 2328
llama_context: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 0
graph_reserve: reserving a graph for ubatch with n_tokens =  512, n_seqs =  1, n_outputs =  512
graph_reserve: reserving a graph for ubatch with n_tokens =    1, n_seqs =  1, n_outputs =    1
graph_reserve: reserving a graph for ubatch with n_tokens =  512, n_seqs =  1, n_outputs =  512
llama_context:        CPU compute buffer size =   300.75 MiB
llama_context: graph nodes  = 918
llama_context: graph splits = 1
CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 
Model metadata: {'tokenizer.ggml.bos_token_id': '151645', 'general.architecture': 'qwen2', 'qwen2.block_count': '24', 'qwen2.context_length': '32768', 'tokenizer.chat_template': "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAnswer the questions.<|im_end|>' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", 'qwen2.attention.head_count_kv': '16', 'tokenizer.ggml.padding_token_id': '151643', 'qwen2.embedding_length': '1024', 'qwen2.attention.layer_norm_rms_epsilon': '0.000001', 'qwen2.attention.head_count': '16', 'tokenizer.ggml.eos_token_id': '151645', 'qwen2.rope.freq_base': '1000000.000000', 'general.file_type': '1', 'qwen2.feed_forward_length': '2816', 'tokenizer.ggml.model': 'gpt2', 'general.name': 'nanoLLaVA', 'tokenizer.ggml.pre': 'qwen2'}
Available chat formats from metadata: chat_template.default
clip_model_loader: model name:   qnguyen3/nanoLLaVA
clip_model_loader: description:  image encoder for qnguyen3/nanoLLaVA
clip_model_loader: GGUF version: 3
clip_model_loader: alignment:    32
clip_model_loader: n_tensors:    457
clip_model_loader: n_kv:         19

clip_model_loader: has vision encoder
clip_ctx: CLIP using CPU backend
load_hparams: projector:          mlp
load_hparams: n_embd:             1152
load_hparams: n_head:             16
load_hparams: n_ff:               4304
load_hparams: n_layer:            28
load_hparams: ffn_op:             gelu
load_hparams: projection_dim:     2048

--- vision hparams ---
load_hparams: image_size:         378
load_hparams: patch_size:         14
load_hparams: has_llava_proj:     1
load_hparams: minicpmv_version:   0
load_hparams: proj_scale_factor:  0
load_hparams: n_wa_pattern:       0

load_hparams: model size:         821.83 MiB
load_hparams: metadata size:      0.16 MiB
alloc_compute_meta:        CPU compute buffer size =    46.89 MiB
You are an assistant who perfectly describes images.USER: <__media__>What's in this image?ASSISTANT: 
Traceback (most recent call last):
  File "/usr/lib/python3.12/http/client.py", line 930, in _get_hostport
    port = int(host[i+1:])
           ^^^^^^^^^^^^^^^
ValueError: invalid literal for int() with base 10: 'test@example.com'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/test.py", line 9, in <module>
    llm.create_chat_completion(
  File "/home/user/.local/lib/python3.12/site-packages/llama_cpp/llama.py", line 2003, in create_chat_completion
    return handler(
           ^^^^^^^^
  File "/home/user/.local/lib/python3.12/site-packages/llama_cpp/llama_chat_format.py", line 2847, in __call__
    image_bytes = self.load_image(image_url)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.12/site-packages/llama_cpp/llama_chat_format.py", line 2747, in load_image
    return self._load_image(image_url)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.12/site-packages/llama_cpp/llama_chat_format.py", line 3039, in _load_image
    with urllib.request.urlopen(image_url) as f:
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 215, in urlopen
    return opener.open(url, data, timeout)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 515, in open
    response = self._open(req, data)
               ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 532, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 492, in _call_chain
    result = func(*args)
             ^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 1373, in http_open
    return self.do_open(http.client.HTTPConnection, req)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/urllib/request.py", line 1313, in do_open
    h = http_class(host, timeout=req.timeout, **http_conn_args)
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/http/client.py", line 880, in __init__
    (self.host, self.port) = self._get_hostport(host, port)
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/lib/python3.12/http/client.py", line 935, in _get_hostport
    raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
http.client.InvalidURL: nonnumeric port: 'test@example.com'