lollms-client 1.1.2__tar.gz → 1.3.0__tar.gz

{lollms_client-1.1.2/src/lollms_client.egg-info → lollms_client-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lollms_client
-Version: 1.1.2
+Version: 1.3.0
 Summary: A client library for LoLLMs generate endpoint
 Author-email: ParisNeo <parisneoai@gmail.com>
 License: Apache Software License

{lollms_client-1.1.2 → lollms_client-1.3.0}/pyproject.toml

@@ -46,3 +46,5 @@ where = ["src"]
 
 [tool.setuptools.dynamic]
 version = {attr = "lollms_client.__version__"}
+[tool.setuptools.package-data]
+lollms_client = ["assets/*.json"]

{lollms_client-1.1.2 → lollms_client-1.3.0}/src/lollms_client/__init__.py

@@ -8,7 +8,7 @@ from lollms_client.lollms_utilities import PromptReshaper # Keep general utiliti
 from lollms_client.lollms_mcp_binding import LollmsMCPBinding, LollmsMCPBindingManager
 from lollms_client.lollms_llm_binding import LollmsLLMBindingManager
 
-__version__ = "1.1.2" # Updated version
+__version__ = "1.3.0" # Updated version
 
 # Optionally, you could define __all__ if you want to be explicit about exports
 __all__ = [

lollms_client-1.3.0/src/lollms_client/assets/models_ctx_sizes.json

@@ -0,0 +1,382 @@
+{
+    "agentica-org/deepcoder-14b-preview": 8192,
+    "agentica-org/deepcoder-14b-preview:free": 8192,
+    "ai21/jamba-large-1.7": 256000,
+    "ai21/jamba-mini-1.7": 256000,
+    "aion-labs/aion-1.0": 8192,
+    "aion-labs/aion-1.0-mini": 8192,
+    "aion-labs/aion-rp-llama-3.1-8b": 131072,
+    "alfredpros/codellama-7b-instruct-solidity": 16384,
+    "alpindale/goliath-120b": 4096,
+    "amazon/nova-lite-v1": 32768,
+    "amazon/nova-micro-v1": 32768,
+    "amazon/nova-pro-v1": 32768,
+    "anthracite-org/magnum-v2-72b": 131072,
+    "anthracite-org/magnum-v4-72b": 131072,
+    "claude-3-haiku": 200000,
+    "claude-3-haiku:beta": 200000,
+    "claude-3-opus": 200000,
+    "claude-3-opus:beta": 200000,
+    "claude-3.5-haiku": 200000,
+    "claude-3.5-haiku-20241022": 200000,
+    "claude-3.5-haiku:beta": 200000,
+    "claude-3.5-sonnet": 200000,
+    "claude-3.5-sonnet-20240620": 200000,
+    "claude-3.5-sonnet-20240620:beta": 200000,
+    "claude-3.5-sonnet:beta": 200000,
+    "claude-3.7-sonnet": 200000,
+    "claude-3.7-sonnet:beta": 200000,
+    "claude-3.7-sonnet:thinking": 200000,
+    "claude-3-5-haiku": 200000,
+    "claude-3-5-haiku-20241022": 200000,
+    "claude-3-5-haiku:beta": 200000,
+    "claude-3-5-sonnet": 200000,
+    "claude-3-5-sonnet-20240620": 200000,
+    "claude-3-5-sonnet-20240620:beta": 200000,
+    "claude-3-5-sonnet:beta": 200000,
+    "claude-3-7-sonnet": 200000,
+    "claude-3-7-sonnet:beta": 200000,
+    "claude-3-7-sonnet:thinking": 200000,
+    "claude-opus-4": 200000,
+    "claude-opus-4.1": 200000,
+    "claude-sonnet-4": 200000,
+    "arcee-ai/coder-large": 32768,
+    "arcee-ai/maestro-reasoning": 32768,
+    "arcee-ai/spotlight": 32768,
+    "arcee-ai/virtuoso-large": 32768,
+    "arliai/qwq-32b-arliai-rpr-v1": 8192,
+    "arliai/qwq-32b-arliai-rpr-v1:free": 8192,
+    "baidu/ernie-4.5-300b-a47b": 128000,
+    "bytedance/ui-tars-1.5-7b": 8192,
+    "cognitivecomputations/dolphin-mistral-24b-venice-edition:free": 32768,
+    "cognitivecomputations/dolphin-mixtral-8x22b": 65536,
+    "cognitivecomputations/dolphin3.0-mistral-24b": 32768,
+    "cognitivecomputations/dolphin3.0-mistral-24b:free": 32768,
+    "cognitivecomputations/dolphin3.0-r1-mistral-24b": 32768,
+    "cognitivecomputations/dolphin3.0-r1-mistral-24b:free": 32768,
+    "cohere/command": 8192,
+    "cohere/command-a": 8192,
+    "cohere/command-r": 128000,
+    "cohere/command-r-03-2024": 128000,
+    "cohere/command-r-08-2024": 128000,
+    "cohere/command-r-plus": 128000,
+    "cohere/command-r-plus-04-2024": 128000,
+    "cohere/command-r-plus-08-2024": 128000,
+    "cohere/command-r7b-12-2024": 128000,
+    "deepseek/deepseek-chat": 32768,
+    "deepseek/deepseek-chat-v3-0324": 32768,
+    "deepseek/deepseek-chat-v3-0324:free": 32768,
+    "deepseek/deepseek-prover-v2": 131072,
+    "deepseek/deepseek-r1": 32768,
+    "deepseek/deepseek-r1-0528": 32768,
+    "deepseek/deepseek-r1-0528-qwen3-8b": 32768,
+    "deepseek/deepseek-r1-0528-qwen3-8b:free": 32768,
+    "deepseek/deepseek-r1-0528:free": 32768,
+    "deepseek/deepseek-r1-distill-llama-70b": 131072,
+    "deepseek/deepseek-r1-distill-llama-70b:free": 131072,
+    "deepseek/deepseek-r1-distill-llama-8b": 131072,
+    "deepseek/deepseek-r1-distill-qwen-1.5b": 32768,
+    "deepseek/deepseek-r1-distill-qwen-14b": 32768,
+    "deepseek/deepseek-r1-distill-qwen-14b:free": 32768,
+    "deepseek/deepseek-r1-distill-qwen-32b": 32768,
+    "deepseek/deepseek-r1-distill-qwen-7b": 32768,
+    "deepseek/deepseek-r1:free": 32768,
+    "deepseek/deepseek-v3-base": 32768,
+    "eleutherai/llemma_7b": 8192,
+    "featherless/qwerky-72b:free": 8192,
+    "google/gemini-2.0-flash-001": 1000000,
+    "google/gemini-2.0-flash-exp:free": 1000000,
+    "google/gemini-2.0-flash-lite-001": 1000000,
+    "google/gemini-2.5-flash": 1000000,
+    "google/gemini-2.5-flash-lite": 1000000,
+    "google/gemini-2.5-flash-lite-preview-06-17": 1000000,
+    "google/gemini-2.5-pro": 2000000,
+    "google/gemini-2.5-pro-exp-03-25": 2000000,
+    "google/gemini-2.5-pro-preview": 2000000,
+    "google/gemini-2.5-pro-preview-05-06": 2000000,
+    "google/gemini-flash-1.5": 1000000,
+    "google/gemini-flash-1.5-8b": 1000000,
+    "google/gemini-pro-1.5": 2000000,
+    "google/gemma-2-27b-it": 8192,
+    "google/gemma-2-9b-it": 8192,
+    "google/gemma-2-9b-it:free": 8192,
+    "google/gemma-3-12b-it": 131072,
+    "google/gemma-3-12b-it:free": 131072,
+    "google/gemma-3-27b-it": 131072,
+    "google/gemma-3-27b-it:free": 131072,
+    "google/gemma-3-4b-it": 131072,
+    "google/gemma-3-4b-it:free": 131072,
+    "google/gemma-3n-e2b-it:free": 131072,
+    "google/gemma-3n-e4b-it": 131072,
+    "google/gemma-3n-e4b-it:free": 131072,
+    "gryphe/mythomax-l2-13b": 4096,
+    "inception/mercury": 32768,
+    "inception/mercury-coder": 32768,
+    "infermatic/mn-inferor-12b": 8192,
+    "inflection/inflection-3-pi": 128000,
+    "inflection/inflection-3-productivity": 128000,
+    "liquid/lfm-3b": 8192,
+    "liquid/lfm-40b": 8192,
+    "liquid/lfm-7b": 8192,
+    "mancer/weaver": 8192,
+    "meta-llama/llama-3-70b-instruct": 8192,
+    "meta-llama/llama-3-8b-instruct": 8192,
+    "meta-llama/llama-3.1-405b": 131072,
+    "meta-llama/llama-3.1-405b-instruct": 131072,
+    "meta-llama/llama-3.1-405b-instruct:free": 131072,
+    "meta-llama/llama-3.1-70b-instruct": 131072,
+    "meta-llama/llama-3.1-8b-instruct": 131072,
+    "meta-llama/llama-3.2-11b-vision-instruct": 131072,
+    "meta-llama/llama-3.2-11b-vision-instruct:free": 131072,
+    "meta-llama/llama-3.2-1b-instruct": 131072,
+    "meta-llama/llama-3.2-3b-instruct": 131072,
+    "meta-llama/llama-3.2-3b-instruct:free": 131072,
+    "meta-llama/llama-3.2-90b-vision-instruct": 131072,
+    "meta-llama/llama-3.3-70b-instruct": 131072,
+    "meta-llama/llama-3.3-70b-instruct:free": 131072,
+    "meta-llama/llama-4-maverick": 131072,
+    "meta-llama/llama-4-scout": 131072,
+    "meta-llama/llama-guard-2-8b": 8192,
+    "meta-llama/llama-guard-3-8b": 131072,
+    "meta-llama/llama-guard-4-12b": 131072,
+    "microsoft/mai-ds-r1": 32768,
+    "microsoft/mai-ds-r1:free": 32768,
+    "microsoft/phi-3-medium-128k-instruct": 131072,
+    "microsoft/phi-3-mini-128k-instruct": 131072,
+    "microsoft/phi-3.5-mini-128k-instruct": 131072,
+    "microsoft/phi-4": 131072,
+    "microsoft/phi-4-multimodal-instruct": 131072,
+    "microsoft/phi-4-reasoning-plus": 131072,
+    "microsoft/wizardlm-2-8x22b": 65536,
+    "minimax/minimax-01": 200000,
+    "minimax/minimax-m1": 200000,
+    "mistralai/codestral-2501": 32768,
+    "mistralai/codestral-2508": 32768,
+    "mistralai/devstral-medium": 32768,
+    "mistralai/devstral-small": 32768,
+    "mistralai/devstral-small-2505": 32768,
+    "mistralai/devstral-small-2505:free": 32768,
+    "mistralai/magistral-medium-2506": 32768,
+    "mistralai/magistral-medium-2506:thinking": 32768,
+    "mistralai/magistral-small-2506": 32768,
+    "mistralai/ministral-3b": 32768,
+    "mistralai/ministral-8b": 32768,
+    "mistralai/mistral-7b-instruct": 32768,
+    "mistralai/mistral-7b-instruct-v0.1": 8192,
+    "mistralai/mistral-7b-instruct-v0.2": 32768,
+    "mistralai/mistral-7b-instruct-v0.3": 32768,
+    "mistralai/mistral-7b-instruct:free": 32768,
+    "mistralai/mistral-large": 32768,
+    "mistralai/mistral-large-2407": 128000,
+    "mistralai/mistral-large-2411": 128000,
+    "mistralai/mistral-medium-3": 32768,
+    "mistralai/mistral-nemo": 128000,
+    "mistralai/mistral-nemo:free": 128000,
+    "mistralai/mistral-saba": 32768,
+    "mistralai/mistral-small": 32768,
+    "mistralai/mistral-small-24b-instruct-2501": 32768,
+    "mistralai/mistral-small-24b-instruct-2501:free": 32768,
+    "mistralai/mistral-small-3.1-24b-instruct": 32768,
+    "mistralai/mistral-small-3.1-24b-instruct:free": 32768,
+    "mistralai/mistral-small-3.2-24b-instruct": 32768,
+    "mistralai/mistral-small-3.2-24b-instruct:free": 32768,
+    "mistralai/mistral-tiny": 32768,
+    "mistralai/mixtral-8x22b-instruct": 65536,
+    "mistralai/mixtral-8x7b-instruct": 32768,
+    "mistralai/pixtral-12b": 128000,
+    "mistralai/pixtral-large-2411": 128000,
+    "moonshotai/kimi-dev-72b:free": 200000,
+    "moonshotai/kimi-k2": 200000,
+    "moonshotai/kimi-k2:free": 200000,
+    "moonshotai/kimi-vl-a3b-thinking": 200000,
+    "moonshotai/kimi-vl-a3b-thinking:free": 200000,
+    "morph/morph-v3-fast": 8192,
+    "morph/morph-v3-large": 8192,
+    "neversleep/llama-3-lumimaid-70b": 8192,
+    "neversleep/llama-3.1-lumimaid-8b": 131072,
+    "neversleep/noromaid-20b": 32768,
+    "nousresearch/deephermes-3-llama-3-8b-preview:free": 8192,
+    "nousresearch/deephermes-3-mistral-24b-preview": 32768,
+    "nousresearch/hermes-2-pro-llama-3-8b": 8192,
+    "nousresearch/hermes-3-llama-3.1-405b": 131072,
+    "nousresearch/hermes-3-llama-3.1-70b": 131072,
+    "nousresearch/nous-hermes-2-mixtral-8x7b-dpo": 32768,
+    "nvidia/llama-3.1-nemotron-70b-instruct": 131072,
+    "nvidia/llama-3.1-nemotron-ultra-253b-v1": 131072,
+    "nvidia/llama-3.1-nemotron-ultra-253b-v1:free": 131072,
+    "nvidia/llama-3.3-nemotron-super-49b-v1": 131072,
+    "openai/chatgpt-4o-latest": 128000,
+    "openai/codex-mini": 2048,
+    "openai/gpt-3.5-turbo": 4096,
+    "openai/gpt-3.5-turbo-0613": 4096,
+    "openai/gpt-3.5-turbo-16k": 16384,
+    "openai/gpt-3.5-turbo-instruct": 4096,
+    "openai/gpt-4": 8192,
+    "openai/gpt-4-0314": 8192,
+    "openai/gpt-4-1106-preview": 128000,
+    "openai/gpt-4-turbo": 128000,
+    "openai/gpt-4-turbo-preview": 128000,
+    "openai/gpt-4.1": 128000,
+    "openai/gpt-4.1-mini": 128000,
+    "openai/gpt-4.1-nano": 128000,
+    "openai/gpt-4o": 128000,
+    "openai/gpt-4o-2024-05-13": 128000,
+    "openai/gpt-4o-2024-08-06": 128000,
+    "openai/gpt-4o-2024-11-20": 128000,
+    "openai/gpt-4o-mini": 128000,
+    "openai/gpt-4o-mini-2024-07-18": 128000,
+    "openai/gpt-4o-mini-search-preview": 128000,
+    "openai/gpt-4o-search-preview": 128000,
+    "openai/gpt-4o:extended": 128000,
+    "openai/gpt-5": 200000,
+    "openai/gpt-5-chat": 200000,
+    "openai/gpt-5-mini": 200000,
+    "openai/gpt-5-nano": 200000,
+    "openai/gpt-oss-120b": 128000,
+    "openai/gpt-oss-20b": 128000,
+    "openai/gpt-oss-20b:free": 128000,
+    "openai/o1": 128000,
+    "openai/o1-mini": 128000,
+    "openai/o1-mini-2024-09-12": 128000,
+    "openai/o1-pro": 128000,
+    "openai/o3": 200000,
+    "openai/o3-mini": 200000,
+    "openai/o3-mini-high": 200000,
+    "openai/o3-pro": 200000,
+    "openai/o4-mini": 128000,
+    "openai/o4-mini-high": 128000,
+    "opengvlab/internvl3-14b": 8192,
+    "openrouter/auto": 8192,
+    "perplexity/r1-1776": 32768,
+    "perplexity/sonar": 32768,
+    "perplexity/sonar-deep-research": 32768,
+    "perplexity/sonar-pro": 32768,
+    "perplexity/sonar-reasoning": 32768,
+    "perplexity/sonar-reasoning-pro": 32768,
+    "pygmalionai/mythalion-13b": 4096,
+    "qwen/qwen-2-72b-instruct": 32768,
+    "qwen/qwen-2.5-72b-instruct": 131072,
+    "qwen/qwen-2.5-72b-instruct:free": 131072,
+    "qwen/qwen-2.5-7b-instruct": 131072,
+    "qwen/qwen-2.5-coder-32b-instruct": 131072,
+    "qwen/qwen-2.5-coder-32b-instruct:free": 131072,
+    "qwen/qwen-2.5-vl-7b-instruct": 131072,
+    "qwen/qwen-max": 32768,
+    "qwen/qwen-plus": 32768,
+    "qwen/qwen-turbo": 8192,
+    "qwen/qwen-vl-max": 32768,
+    "qwen/qwen-vl-plus": 32768,
+    "qwen/qwen2.5-vl-32b-instruct": 131072,
+    "qwen/qwen2.5-vl-32b-instruct:free": 131072,
+    "qwen/qwen2.5-vl-72b-instruct": 131072,
+    "qwen/qwen2.5-vl-72b-instruct:free": 131072,
+    "qwen/qwen3-14b": 32768,
+    "qwen/qwen3-14b:free": 32768,
+    "qwen/qwen3-235b-a22b": 32768,
+    "qwen/qwen3-235b-a22b-2507": 32768,
+    "qwen/qwen3-235b-a22b-thinking-2507": 32768,
+    "qwen/qwen3-235b-a22b:free": 32768,
+    "qwen/qwen3-30b-a3b": 32768,
+    "qwen/qwen3-30b-a3b-instruct-2507": 32768,
+    "qwen/qwen3-30b-a3b:free": 32768,
+    "qwen/qwen3-32b": 32768,
+    "qwen/qwen3-4b:free": 32768,
+    "qwen/qwen3-8b": 32768,
+    "qwen/qwen3-8b:free": 32768,
+    "qwen/qwen3-coder": 32768,
+    "qwen/qwen3-coder:free": 32768,
+    "qwen/qwq-32b": 32768,
+    "qwen/qwq-32b-preview": 32768,
+    "qwen/qwq-32b:free": 32768,
+    "raifle/sorcererlm-8x22b": 65536,
+    "rekaai/reka-flash-3:free": 128000,
+    "sao10k/l3-euryale-70b": 8192,
+    "sao10k/l3-lunaris-8b": 8192,
+    "sao10k/l3.1-euryale-70b": 131072,
+    "sao10k/l3.3-euryale-70b": 131072,
+    "sarvamai/sarvam-m:free": 8192,
+    "scb10x/llama3.1-typhoon2-70b-instruct": 131072,
+    "shisa-ai/shisa-v2-llama3.3-70b": 131072,
+    "shisa-ai/shisa-v2-llama3.3-70b:free": 131072,
+    "sophosympatheia/midnight-rose-70b": 4096,
+    "switchpoint/router": 8192,
+    "tencent/hunyuan-a13b-instruct": 8192,
+    "tencent/hunyuan-a13b-instruct:free": 8192,
+    "thedrummer/anubis-70b-v1.1": 8192,
+    "thedrummer/anubis-pro-105b-v1": 8192,
+    "thedrummer/rocinante-12b": 8192,
+    "thedrummer/skyfall-36b-v2": 8192,
+    "thedrummer/unslopnemo-12b": 128000,
+    "thedrummer/valkyrie-49b-v1": 8192,
+    "thudm/glm-4-32b": 2000000,
+    "thudm/glm-4.1v-9b-thinking": 2000000,
+    "thudm/glm-z1-32b:free": 2000000,
+    "tngtech/deepseek-r1t-chimera": 32768,
+    "tngtech/deepseek-r1t-chimera:free": 32768,
+    "tngtech/deepseek-r1t2-chimera:free": 32768,
+    "undi95/remm-slerp-l2-13b": 4096,
+    "x-ai/grok-2-1212": 128000,
+    "x-ai/grok-2-vision-1212": 128000,
+    "x-ai/grok-3": 128000,
+    "x-ai/grok-3-beta": 128000,
+    "x-ai/grok-3-mini": 128000,
+    "x-ai/grok-3-mini-beta": 128000,
+    "x-ai/grok-4": 128000,
+    "x-ai/grok-vision-beta": 128000,
+    "z-ai/glm-4-32b": 2000000,
+    "z-ai/glm-4.5": 2000000,
+    "z-ai/glm-4.5-air": 2000000,
+    "z-ai/glm-4.5-air:free": 2000000,
+    "llama3.1": 131072,   
+    "llama3.2": 131072,   
+    "llama3.3": 131072,   
+    "llama3": 8192,       
+    "llama2": 4096,       
+    "mixtral8x22b": 65536, 
+    "mixtral": 32768,     
+    "mistral": 32768,     
+    "gemma3": 131072,     
+    "gemma2": 8192,       
+    "gemma": 8192,        
+    "phi3": 131072,       
+    "phi2": 2048,         
+    "phi": 2048,          
+    "qwen2.5": 131072,    
+    "qwen2": 32768,       
+    "qwen": 8192,         
+    "codellama": 16384,   
+    "codegemma": 8192,    
+    "deepseek-coder-v2": 131072,  
+    "deepseek-coder": 16384,  
+    "deepseek-v2": 131072,    
+    "deepseek-llm": 4096,     
+    "yi1.5": 32768,       
+    "yi": 4096,           
+    "command-r": 131072,  
+    "wizardlm2": 32768,   
+    "wizardlm": 16384,    
+    "zephyr": 65536,      
+    "vicuna": 2048,       
+    "falcon": 2048,       
+    "starcoder": 8192,    
+    "stablelm": 4096,     
+    "orca2": 4096,        
+    "orca": 4096,         
+    "dolphin": 32768,     
+    "openhermes": 8192,
+    "gpt-oss": 128000,
+    "gpt-3.5-turbo": 4096,
+    "gpt-4": 8192,
+    "grok-2": 128000,
+    "grok-2-1212": 128000,
+    "grok-2-vision-1212": 128000,
+    "grok-3": 128000,
+    "grok-3-fast": 128000,
+    "grok-3-beta": 128000,
+    "grok-3-mini": 128000,
+    "grok-3-mini-beta": 128000,
+    "grok-3-mini-fast": 128000,
+    "grok-4-0709": 128000,
+    "grok-4": 128000,
+    "grok-vision-beta": 128000
+}

{lollms_client-1.1.2 → lollms_client-1.3.0}/src/lollms_client/llm_bindings/lollms/__init__.py

@@ -9,7 +9,7 @@ from lollms_client.lollms_discussion import LollmsDiscussion
 from typing import Optional, Callable, List, Union
 from ascii_colors import ASCIIColors, trace_exception
 from typing import List, Dict
-
+import httpx
 import pipmaster as pm
 
 pm.ensure_packages(["openai","tiktoken"])
@@ -49,7 +49,7 @@ class LollmsBinding(LollmsLLMBinding):
 
         if not self.service_key:
             self.service_key = os.getenv("LOLLMS_API_KEY", self.service_key)
-        self.client = openai.OpenAI(api_key=self.service_key, base_url=None if self.host_address is None else self.host_address if len(self.host_address)>0 else None)
+        self.client = openai.OpenAI(api_key=self.service_key, base_url=None if self.host_address is None else self.host_address if len(self.host_address)>0 else None, http_client=httpx.Client(verify=self.verify_ssl_certificate))
         self.completion_format = ELF_COMPLETION_FORMAT.Chat
 
     def lollms_listMountedPersonalities(self, host_address:str|None=None):

{lollms_client-1.1.2 → lollms_client-1.3.0}/src/lollms_client/llm_bindings/ollama/__init__.py

@@ -680,7 +680,63 @@ class OllamaBinding(LollmsLLMBinding):
         
         ASCIIColors.warning(f"Context size not found for model '{model_name}'")
         return None
+
+    def ps(self):
+        """
+        Lists running models in a standardized, flat format.
+
+        This method corresponds to the /api/ps endpoint in the Ollama API. It retrieves
+        the models currently loaded into memory and transforms the data into a simplified,
+        flat list of dictionaries.
+
+        Returns:
+            list[dict]: A list of dictionaries, each representing a running model with a standardized set of keys.
+                        Returns an empty list if the client is not initialized or if an error occurs.
         
+        Example of a returned model dictionary:
+        {
+            "model_name": "gemma3:12b",
+            "size": 13861175232,
+            "vram_size": 10961479680,
+            "parameters_size": "12.2B",
+            "quantization_level": "Q4_K_M",
+            "context_size": 32000,
+            "parent_model": "",
+            "expires_at": "2025-08-20T22:28:18.6708784+02:00"
+        }
+        """
+        if not self.ollama_client:
+            ASCIIColors.warning("Ollama client not initialized. Cannot list running models.")
+            return []
+
+        try:
+            running_models_response = self.ollama_client.ps()
+            
+            models_list = running_models_response.get('models', [])
+            standardized_models = []
+
+            for model_data in models_list:
+                details = model_data.get('details', {})
+                
+                flat_model_info = {
+                    "model_name": model_data.get("name"),
+                    "size": model_data.get("size"),
+                    "vram_size": model_data.get("size_vram"),
+                    "expires_at": model_data.get("expires_at"),
+                    "parameters_size": details.get("parameter_size"),
+                    "quantization_level": details.get("quantization_level"),
+                    "parent_model": details.get("parent_model"),
+                    # Add context_size if it exists in the details
+                    "context_size": details.get("context_length") 
+                }
+                standardized_models.append(flat_model_info)
+            
+            return standardized_models
+
+        except Exception as e:
+            ASCIIColors.error(f"Failed to list running models from Ollama at {self.host_address}: {e}")
+            return []
+
 if __name__ == '__main__':
     global full_streamed_text
     # Example Usage (requires an Ollama server running)

{lollms_client-1.1.2 → lollms_client-1.3.0}/src/lollms_client/llm_bindings/openai/__init__.py

@@ -10,7 +10,7 @@ from typing import Optional, Callable, List, Union
 from ascii_colors import ASCIIColors, trace_exception
 from typing import List, Dict
 import math
-
+import httpx
 import pipmaster as pm
 
 pm.ensure_packages(["openai","tiktoken"])
@@ -47,7 +47,7 @@ class OpenAIBinding(LollmsLLMBinding):
 
         if not self.service_key:
             self.service_key = os.getenv("OPENAI_API_KEY", self.service_key)
-        self.client = openai.OpenAI(api_key=self.service_key, base_url=None if self.host_address is None else self.host_address if len(self.host_address)>0 else None)
+        self.client = openai.OpenAI(api_key=self.service_key, base_url=None if self.host_address is None else self.host_address if len(self.host_address)>0 else None, http_client=httpx.Client(verify=self.verify_ssl_certificate))
         self.completion_format = ELF_COMPLETION_FORMAT.Chat
 
     def _build_openai_params(self, messages: list, **kwargs) -> dict:
@@ -668,4 +668,4 @@ class OpenAIBinding(LollmsLLMBinding):
         """
         self.model = model_name
         self.model_name = model_name
-        return True
+        return True