2026-01-21 - 2026-07-21
Overview
1 Release published by 1 user
Published
v0.6.2
358 Issues closed from 1 user
Closed
#455 [PR #290] [CLOSED] Bump ruff from 0.6.5 to 0.6.7
Closed
#456 [PR #296] [CLOSED] Bump ruff from 0.6.5 to 0.6.9
Closed
#457 [PR #297] [CLOSED] add chat-history example.
Closed
#458 [PR #291] [CLOSED] Bump ruff from 0.6.5 to 0.6.8
Closed
#459 [PR #299] [CLOSED] Enable subpath-mounted ollama and basic auth
Closed
#453 [PR #285] [CLOSED] Bump ruff from 0.6.5 to 0.6.6
Closed
#454 [PR #286] [CLOSED] add ollama.list() example.
Closed
#448 [PR #277] [MERGED] no head request for create blob
Closed
#449 [PR #278] [MERGED] Bump pytest from 8.3.2 to 8.3.3
Closed
#450 [PR #282] [CLOSED] add OpenAI example in README.md.
Closed
#451 [PR #281] [MERGED] Bump ruff from 0.6.3 to 0.6.5
Closed
#452 [PR #284] [MERGED] update pyproject.toml
Closed
#444 [PR #270] [CLOSED] Bump ruff from 0.6.3 to 0.6.4
Closed
#445 [PR #275] [MERGED] add basic delete/copy tests
Closed
#446 [PR #276] [MERGED] add pydantic for validation and serialization
Closed
#447 [PR #272] [CLOSED] Make _encode_image error message more helpful and shorten docstring
Closed
#440 [PR #264] [CLOSED] chore(deps): Update dependencies
Closed
#441 [PR #266] [MERGED] _stream in async client raises RuntimeError when processing HTTP errors
Closed
#442 [PR #265] [CLOSED] Bump httpx from 0.27.0 to 0.27.2
Closed
#443 [PR #267] [MERGED] Bump ruff from 0.6.2 to 0.6.3
Closed
#435 [PR #260] [MERGED] Bump pytest-asyncio from 0.23.8 to 0.24.0
Closed
#436 [PR #255] [CLOSED] Bump ruff from 0.5.5 to 0.6.1
Closed
#437 [PR #261] [MERGED] Bump ruff from 0.5.5 to 0.6.2
Closed
#438 [PR #262] [MERGED] IPv6 support
Closed
#439 [PR #256] [CLOSED] support base path. this is useful for multiple applications under one…
Closed
#430 [PR #243] [CLOSED] Bump ruff from 0.5.5 to 0.5.6
Closed
#431 [PR #254] [CLOSED] Bump ruff from 0.5.5 to 0.6.0
Closed
#432 [PR #238] [CLOSED] Autogen Tool, ToolFunction, Parameters, Property schema when opt-in to using type-hinted function params
Closed
#433 [PR #252] [MERGED] Bump pytest-httpserver from 1.0.12 to 1.1.0
Closed
#434 [PR #247] [CLOSED] Bump ruff from 0.5.5 to 0.5.7
Closed
#425 [PR #231] [MERGED] Bump pytest from 8.2.2 to 8.3.2
Closed
#426 [PR #234] [CLOSED] Add Tool Registry Feature
Closed
#427 [PR #230] [MERGED] Bump ruff from 0.5.2 to 0.5.5
Closed
#428 [PR #236] [MERGED] fix: tool_calls response parsing
Closed
#429 [PR #237] [MERGED] update to llama3.1
Closed
#422 [PR #224] [MERGED] Bump pytest-httpserver from 1.0.10 to 1.0.12
Closed
#423 [PR #226] [CLOSED] Bump pytest from 8.2.2 to 8.3.1
Closed
#424 [PR #227] [MERGED] Update Message annotations to support tool calls
Closed
#418 [PR #219] [CLOSED] Bump ruff from 0.5.2 to 0.5.3
Closed
#420 [PR #220] [CLOSED] Bump pytest-httpserver from 1.0.10 to 1.0.11
Closed
#421 [PR #225] [CLOSED] Bump ruff from 0.5.2 to 0.5.4
Closed
#415 [PR #213] [MERGED] integrate tool calls
Closed
#416 [PR #216] [MERGED] Deprecate embeddings from docs in favor of embed
Closed
#417 [PR #215] [MERGED] add insert support to generate endpoint
Closed
#419 [PR #217] [MERGED] Bump pytest-asyncio from 0.23.7 to 0.23.8
Closed
#410 [PR #206] [CLOSED] Bump ruff from 0.4.7 to 0.5.1
Closed
#411 [PR #207] [CLOSED] Adding an example how you can ask several models something.
Closed
#412 [PR #212] [CLOSED] support tool calls
Closed
#413 [PR #208] [MERGED] Support api/embed
Closed
#414 [PR #211] [MERGED] Bump ruff from 0.4.7 to 0.5.2
Closed
#405 [PR #195] [CLOSED] Update _client.py - always include path in create
Closed
#406 [PR #201] [CLOSED] fix: PydanticUserError: Please use typing_extensions.TypedDict inst…
Closed
#407 [PR #199] [CLOSED] fix: Ensure JSON response is properly parsed in generate function when format is set to 'json'
Closed
#408 [PR #198] [CLOSED] Bump ruff from 0.4.7 to 0.5.0
Closed
#409 [PR #203] [MERGED] Bump pillow from 10.3.0 to 10.4.0
Closed
#400 [PR #185] [CLOSED] CLI proof of concept
Closed
#401 [PR #181] [MERGED] Add type overloads to methods
Closed
#402 [PR #189] [CLOSED] Bump ruff from 0.4.7 to 0.4.9
Closed
#403 [PR #182] [CLOSED] Bump ruff from 0.4.7 to 0.4.8
Closed
#404 [PR #194] [CLOSED] Bump ruff from 0.4.7 to 0.4.10
Closed
#395 [PR #177] [MERGED] Python API PS
Closed
#396 [PR #178] [MERGED] Bump pytest from 8.2.0 to 8.2.2
Closed
#397 [PR #175] [CLOSED] Create ollamapythonjava
Closed
#398 [PR #179] [MERGED] Simple Example
Closed
#399 [PR #180] [CLOSED] Overloads for Methods
Closed
#390 [PR #163] [CLOSED] Bump pytest from 8.2.0 to 8.2.1
Closed
#391 [PR #168] [CLOSED] Bump ruff from 0.4.3 to 0.4.5
Closed
#392 [PR #169] [CLOSED] Bump ruff from 0.4.3 to 0.4.6
Closed
#393 [PR #170] [MERGED] Add URL path to client URL in in Client._parse_host()
Closed
#394 [PR #172] [MERGED] Bump ruff from 0.4.3 to 0.4.7
Closed
#389 [PR #162] [MERGED] Bump pytest-asyncio from 0.23.6 to 0.23.7
Closed
#385 [PR #153] [CLOSED] Bump ruff from 0.4.3 to 0.4.4
Closed
#386 [PR #154] [MERGED] add done reason to generate type responses
Closed
#387 [PR #155] [CLOSED] Add clarity to getting started docs.
Closed
#388 [PR #158] [MERGED] Avoid side effects if chat message contains images
Closed
#380 [PR #150] [MERGED] add quantization to create requests
Closed
#381 [PR #151] [CLOSED] accept license, template, system as files
Closed
#382 [PR #148] [MERGED] Bump ruff from 0.4.1 to 0.4.3
Closed
#383 [PR #152] [MERGED] remove old options
Closed
#384 [PR #145] [MERGED] fix: annotation in AsyncClient.embedding
Closed
#375 [PR #135] [MERGED] Update README.md link still point legacy url
Closed
#376 [PR #140] [MERGED] Bump pytest from 8.1.1 to 8.2.0
Closed
#377 [PR #137] [CLOSED] Add Status Badges
Closed
#378 [PR #138] [MERGED] Update README.md
Closed
#379 [PR #141] [CLOSED] Added temperature parameter
Closed
#370 [PR #131] [CLOSED] Bump ruff from 0.4.1 to 0.4.2
Closed
#371 [PR #130] [CLOSED] Updated readme to mention that this library needs ollama service to be running and also snippet to run it if someone is using a jupyter notebook
Closed
#372 [PR #129] [MERGED] Add py.typed to mark the library as typed
Closed
#373 [PR #134] [CLOSED] Bump pytest from 8.1.1 to 8.1.2
Closed
#374 [PR #132] [CLOSED] Add type overloads for chat() method in _client.py
Closed
#365 [PR #122] [CLOSED] Bump ruff from 0.3.4 to 0.4.0
Closed
#366 [PR #118] [MERGED] fix 'content' check on messages in chat()
Closed
#367 [PR #116] [CLOSED] Bump ruff from 0.3.4 to 0.3.7
Closed
#368 [PR #125] [CLOSED] Update README.md - Changed llama2 -> llama3
Closed
#369 [PR #124] [MERGED] Bump ruff from 0.3.4 to 0.4.1
Closed
#361 [PR #114] [MERGED] modified embeddings return annotation
Closed
#362 [PR #111] [CLOSED] Bump ruff from 0.3.4 to 0.3.5
Closed
#363 [PR #115] [CLOSED] Bump ruff from 0.3.4 to 0.3.6
Closed
#364 [PR #107] [MERGED] Bump pytest from 7.4.4 to 8.1.1
Closed
#357 [PR #104] [MERGED] Bump actions/upload-artifact from 3 to 4
Closed
#358 [PR #105] [MERGED] Bump pytest-cov from 4.1.0 to 5.0.0
Closed
#359 [PR #106] [MERGED] Bump ruff from 0.1.15 to 0.3.4
Closed
#360 [PR #110] [MERGED] Bump pillow from 10.2.0 to 10.3.0
Closed
#351 [PR #93] [CLOSED] Add Phorm AI Badge
Closed
#352 [PR #90] [CLOSED] Add an example using continuous dialogue
Closed
#353 [PR #75] [CLOSED] Stability testing for client
Closed
#354 [PR #97] [CLOSED] Loosen httpx constraint
Closed
#355 [PR #102] [MERGED] update dependencies
Closed
#356 [PR #103] [MERGED] add dependabot
Closed
#346 [PR #55] [CLOSED] Testing repeated calls
Closed
#347 [PR #61] [CLOSED] Fixes URL parsing when basic auth is included in the URL.
Closed
#348 [PR #58] [MERGED] python user agent
Closed
#349 [PR #64] [CLOSED] Add iterative_chat and examples for simlified chat history keeping
Closed
#350 [PR #68] [CLOSED] Added example showing how to use generate with images
Closed
#340 [PR #42] [CLOSED] bump httpx to 0.26.0
Closed
#341 [PR #41] [MERGED] Update README.md
Closed
#342 [PR #45] [MERGED] doc(README) : add prerequisites
Closed
#343 [PR #50] [MERGED] fix: encode base64 inputs
Closed
#344 [PR #52] [MERGED] create example
Closed
#345 [PR #54] [CLOSED] Feat/pydantic models & refactor
Closed
#336 [PR #32] [MERGED] update github actions
Closed
#337 [PR #36] [CLOSED] async call in Jupyter notebook
Closed
#338 [PR #34] [MERGED] error handling code
Closed
#339 [PR #40] [MERGED] fix parse modelfile
Closed
#331 [PR #18] [MERGED] fix unit tests
Closed
#333 [PR #28] [CLOSED] Made the API more readable.
Closed
#334 [PR #26] [CLOSED] Add example using seed param to get consistent outputs
Closed
#335 [PR #31] [MERGED] add keep_alive
Closed
#328 [PR #11] [MERGED] ci: give publish job content perms
Closed
#329 [PR #16] [MERGED] fix: update OLLAMA_HOST parsing to match ollama CLI
Closed
#330 [PR #19] [MERGED] upgrade pillow
Closed
#332 [PR #20] [MERGED] fix pull example typo
Closed
#325 [PR #13] [MERGED] add example for pulling with progress bar
Closed
#326 [PR #15] [MERGED] examples
Closed
#327 [PR #17] [MERGED] update response error field to match json response
Closed
#323 [PR #9] [MERGED] s/target/destination/
Closed
#324 [PR #8] [MERGED] fix: remote create new file
Closed
#320 [PR #10] [MERGED] Changed 'show' to use POST instead of GET
Closed
#321 [PR #7] [MERGED] fix gh release upload
Closed
#322 [PR #6] [MERGED] fix publish
Closed
#316 [PR #3] [MERGED] add default async client aliases
Closed
#317 [PR #4] [MERGED] Mxyng/rm default async
Closed
#318 [PR #5] [MERGED] Mxyng
Closed
#319 [PR #2] [MERGED] fix endpoints
Closed
#315 [PR #1] [MERGED] add ci tests/lint
Closed
#311 Test
Closed
#313 qwen3-coder:latest responds with "The models does not support function calls" and other random messages
Closed
#314 x
Closed
#305 Possible bug with kimi-k2-thinking☁️ ollama._types.ResponseError: unmarshal: invalid character 'I' looking for beginning of value (status code: 500))`
Closed
#306 OpenAI compatibility for /v1/embeddings
Closed
#302 A way to set OLLAMA_API_KEY for web_search
Closed
#303 VLM cannot read png
Closed
#299 examples/tools.py ignores defined tools and spits out usual LLM results.
Closed
#300 Missing WebCrawlResponse / WebSearchResponse
Closed
#295 Prompts Being ignored
Closed
#297 examples/structured-outputs-image.py
Closed
#292 Ollama.chat(...) does not support images
Closed
#293 Feature Request: Ollama Tools
Closed
#291 ollama-python does not expose the name field returned by /api/tags
Closed
#289 error in think key and error in message role in ollama gpt-oss
Closed
#286 How to get the Ollama version?
Closed
#288 Unable to connect to proxied model from python api with self-signed SSL certificate
Closed
#283 Wrong example documentation URL
Closed
#285 Think only supports bool
Closed
#280 [BUG] Regular expressions containing escapes cause ResponseErrors
Closed
#281 Log level of "HTTP Request: POST" result should be changed to DEBUG
Closed
#282 Tools not working when providing a schema via format=...
Closed
#279 Thinking with tool calling is problematic
Closed
#275 Think parameter does not seem to work with Qwen3
Closed
#271 Missing license in pyproject
Closed
#272 Critical Packaging Error: Wheels for ollama 0.1.8 and 0.2.1 on PyPI contain pre-0.1.8 code
Closed
#273 release the last version
Closed
#268 ollama.chat() should accept images for vision model support
Closed
#270 Request timeout feature
Closed
#266 ollama-python does not install on Python 3.14 beta 1
Closed
#267 Structured output (json format)
Closed
#262 Role of control returns an error.
Closed
#263 [BUG] Ollama create method is only creating a single model based on the _from parameter, but not the derivate model like the cli
Closed
#259 Sigsegv during garbage collection under certian circumstances
Closed
#260 Is ollama-python avaliable on conda?
Closed
#261 image-based PDFs
Closed
#258 ps method not working through OpenWebUI - ValidationError
Closed
#253 Support for --verbose flag
Closed
#252 status code 503
Closed
#250 Expose "Processor" on PS() Call
Closed
#249 multimodal_chat.py and multimodal_generate.py doesn't exist
Closed
#245 Provide request timeout option
Closed
#246 Ollama and ollama-python have different httpx requirements
Closed
#241 Fine-Tuning
Closed
#243 chat completion does not agree with documentation
Closed
#240 interrupt the inference
Closed
#238 بايثون عايز الاتصال والتأثير
Closed
#239 Documentation?
Closed
#235 Www.theBioutful.home.co seventhunderm
Closed
#236 After changing OLLAMA_HOST=0.0.0.0, ollama.chat() and ollama.generate() not work
Closed
#232 LlamaIndex Fails to Connect to Ollama in Conda Environment, Works in Command Prompt
Closed
#233 Streaming Doesn't Work When Using Tools
Closed
#234 No proper support for Tool Messages?
Closed
#231 Can we access the model using Ollama via WebSockets?
Closed
#228 Structured Output - Literal Validation Error
Closed
#225 Why can't I call the local Ollama model through this python library under Windows system?
Closed
#227 Ollama Python client mostly broken on Windows 11
Closed
#220 Limit the number of generated tokens?
Closed
#221 TypeError: AsyncClient.chat() got an unexpected keyword argument 'tools'
Closed
#224 test asyncio_tool.py with qwen32B(distrilled by deepseek-r1)
Closed
#214 httpcore.RemoteProtocolError: Server disconnected without sending a response. The above exception was the direct cause of the following exception:
Closed
#216 ollama.generate(model='deepseek-r1:1.5b',prompt='hello') error
Closed
#217 Is there an example in the project where a DOC file is used as input for inference?
Closed
#218 Unable to close connections
Closed
#219 API Method to get model loading progress?
Closed
#212 Moondream:v2 issue 500 error
Closed
#213 Tonkenization of the context
Closed
#208 ollama.create How to create models from local files without modelfile?
Closed
#209 ollama.create : "Client.create() got an unexpected keyword argument 'modelfile'"
Closed
#210 FIXED
Closed
#205 Question - Batch Processing
Closed
#206 json: cannot unmarshal object into Go struct field ChatRequest.format of type string (status code: 400)
Closed
#207 Tools with nested properties getting cut short
Closed
#204 Semantic recognition or semantic classification
Closed
#202 import ollama error when os.environ["HTTP_PROXY"] = "socks5h://xxx"
Closed
#203 Missing dependancy
Closed
#199 set flash attention via options?
Closed
#196 chat method is not able to identify add_two_numbers as tool
Closed
#197 Check if ollama server is running or not
Closed
#198 Unable to Connect to Localhost by Default When OLLAMA_HOST is Set to 0.0.0.0
Closed
#194 Tool call doesn't honor the function definition when responding
Closed
#190 ollama._types.ResponseError ResponseError(e.response.text, e.response.status_code) from None
Closed
#187 Adding Dropout Layer to models and accessing nn layers information
Closed
#184 There is a problem using ollama in vscode+jupyter
Closed
#185 Validation error when providing a base64 string to Image(value=...) in Message(images=...)
Closed
#186 where/how can I find the path of ollama model?
Closed
#182 Structured output, json schema error
Closed
#183 ollama.create not working properly
Closed
#178 Model doesn't seem to include tool output in its response
Closed
#179 multi-image support for llama3.2-vision?
Closed
#180 Response + Function Calling on the same model call
Closed
#181 Breaking Change for langchain-ollama==0.2.1 on ollama==0.4.3
Closed
#177 Request: allowing httpx version 0.28
Closed
#172 Error while working with multimodal chat LLaMa 3.2-vision 90B
Closed
#173 Calling chat with function as tool gives an empty response
Closed
#169 New Tool Calling issues.
Closed
#170 craete function ollama._types.ResponseError
Closed
#171 about maintaining session continuity: how to get context by python clinet
Closed
#166 Model doesn't ger offloaded from VRAM after deletion
Closed
#167 Chat with Phyton
Closed
#168 ollama 0.4.0 changes tool_calls API
Closed
#163 [Errno 111] Connection refused while embedding in docker
Closed
#164 ollama.generate() with multimodal llama3.2-vision does not pass images array when raw=True
Closed
#165 AttributeError: 'NoneType' object has no attribute 'get'
Closed
#161 Please add examples for image/vision models
Closed
#162 Update all examples to use the new Pydantic integration
Closed
#157 Exception: Attempted to call a sync iterator on an async stream.
Closed
#158 Raspberry Pi 5 8gb: Running any query with (llava or moondream2) + image causes the device to shut down
Closed
#159 Check tool called when stream is set to true
Closed
#152 Leftovers of a chat template. (Ollama, Llama 3.2)
Closed
#153 InvalidURL: Invalid port: ':1]'
Closed
#154 Ollama
Closed
#156 No model memory
Closed
#148 Command raised an exception: AttributeError: 'Command' object has no attribute 'chat'???
Closed
#149 Unable to set Client host, httpx.ConnectError
Closed
#150 Abort Requests
Closed
#145 Ollama multimodal - Gemma not seeing image
Closed
#147 Not loading Llama 3.2:3b
Closed
#142 How to generate text to image with ollama?
Closed
#144 How to send image to vision model
Closed
#139 Please expose the contents of the _type file to allow for better static type analysis
Closed
#141 Tool calls are not properly returned when chat() is called with stream=True
Closed
#137 ollama._types.ResponseError: llama runner process no longer running: -1
Closed
#133 🐛 Custom modelfile Regression causing ResponseError: command must be one of "from", "license",
Closed
#135 tools not available in ollama
Closed
#131 Return python object instead of JSON
Closed
#132 Inconsistent API Behavior
Closed
#129 create modelfile, this is why
Closed
#130 how to make batch request with python client?
Closed
#127 Reproducible output cannot be achieved in model Mixtral
Closed
#128 Version is set to 0.0.0 in pyproject.toml
Closed
#124 Client's host doesn't work when the host is behind a proxy server
Closed
#126 Avoid the need to download ollama manually
Closed
#121 Persistent chat memory
Closed
#123 Provide a way to override system prompt at runtime
Closed
#118 Pass a list of functions/tools to client like in the API
Closed
#119 Bug in tool_calls response parsing
Closed
#120 Decorator to generate schemas for tools
Closed
#116 Update pypi
Closed
#113 async stream chat *just don't work* (tm)
Closed
#114 Need Temperature/Max_token Options
Closed
#117 tool calls integration broken when empty
Closed
#110 Add way to abort a streaming response from chat / generate
Closed
#111 Wrong host handling
Closed
#104 Model 'llama3' Not Found but from another Docker container
Closed
#108 Getting ConnectError: [Errno 111] Connection refused
Closed
#100 ollama-python equivalent of /clear and context summarization in a chat
Closed
#102 ollama.create fails with ollama._types.ResponseError: name and path are required
Closed
#94 Interactive Mode
Closed
#95 Command Line Interface
Closed
#96 Support for for /api/ps
Closed
#93 ollama.create fails with ollama._types.ResponseError: unexpected EOF
Closed
#90 Met the 503 code status error when run ollama to connect localhost for chat on M3 apple silicon
Closed
#82 ollama._types.ResponseError: model 'llama2' not found
Closed
#84 ollama._types.ResponseError: Unsupported type: 'bool'
Closed
#86 getting NotImplementedError
Closed
#81 Ukrainian language?
Closed
#76 ollama-python outputs sometimes half tokens. original ollama works fine in my system
Closed
#73 Feature request for less configuration by merging external library
Closed
#74 TypeError: Client.__init__() got an unexpected keyword argument 'follow_redirects'
Closed
#75 Client.create inserts escape quotes \" for the last PARAMETER stop.
Closed
#67 gpu not worked, only cpu. How to solve it?
Closed
#70 Support Metrics
Closed
#71 Embeddings don't seem to work.
Closed
#64 Client fails to query resources behind reverse proxy path
Closed
#65 Question: the response I got by using terminal is way better than using ollama.generate
Closed
#66 Error: Server disconnected without sending a response. Error: [WinError 10061] No connection could be made because the target machine actively refused it
Closed
#58 ollama.chat is missing template kwarg.
Closed
#60 Continued Conversations
Closed
#52 Unable to get ollama serve working
Closed
#53 Why Ollama is so terribly slow when I set format="json"
Closed
#54 Python 3.12.2 Cannot import ollama
Closed
#51 Setting up top k , Max tokens , context length ?
Closed
#47 Can I set num_ctx=-1 to use max possible context window?
Closed
#43 pip install ollama error
Closed
#40 terribly slow: format="json", stream=False, please advise
Closed
#41 How do I define the 'base_url' using embeddings()
Closed
#42 Understanding Variable Response Times from a Local Mistral Model
Closed
#38 Possible workaround for the issues with multimodal...
Closed
#39 How to set temprature and output token size in the chat mode?
Closed
#35 From ollama to transformer.AutoModelForCausalLM
Closed
#31 [query] Is it not possible to run ollama python library on a colab notebook ?
Closed
#32 readme needs to show example of image generations
Closed
#33 ollama server hangs constantly
Closed
#28 chat and cli chat get different outputs when using llava
Closed
#30 Add in simple to use iterative chat (chat with history)
Closed
#25 llama2-uncensored:70b might be pointing to regular llama2:70b?
Closed
#26 Where does ollama.pull() store the models?
Closed
#27 Can't get Async to stop
Closed
#22 keep_alive control how long models stay loaded
Closed
#23 🙏 Feature request > Create model from file path with SDK
Closed
#24 ollama.generate & ollama.chat hangs after about 30*mins
Closed
#19 Does chat take options?
Closed
#20 Is there a way for using chat() function by passing more context ?
Closed
#21 Custom models
Closed
#16 📝 Documentation request - for fewshot templates model
Closed
#17 Usage body for LLaVA model
Closed
#18 Batching support in Ollama
Closed
#13 404 on /api/chat
Closed
#14 How can I use context parameter?
Closed
#15 function calling
Closed
#10 asyncio.run() cannot be called from a running event loop
Closed
#11 Error: Head "http://127.0.0.1:11434/": read tcp 127.0.0.1:36136->127.0.0.1:11434: read: connection reset by peer
Closed
#12 Suggestion: Use models to encapsulate request/responses
Closed
#7 ConnectError
Closed
#9 Batching
Closed
#8 README doesn't mention that a running ollama server is required
Closed
#4 Clarification: Does this install ollama or just act as an API to an existing install?
Closed
#5 GUI using Gradio or Pygame or Streamlit
Closed
#6 Is there a command that just serves the REST api , similar to ollama run on the cli
Closed
#1 httpx.ConnectError: [Errno 111] Connection refused
Closed
#2 ollama.generate和ollama.chat的区别是什么？
Closed
#3 Server error '502 Bad Gateway' for url 'http://127.0.0.1:11434/api/chat'
459 Issues created by 1 user
Opened
#1 httpx.ConnectError: [Errno 111] Connection refused
Opened
#2 ollama.generate和ollama.chat的区别是什么？
Opened
#3 Server error '502 Bad Gateway' for url 'http://127.0.0.1:11434/api/chat'
Opened
#4 Clarification: Does this install ollama or just act as an API to an existing install?
Opened
#5 GUI using Gradio or Pygame or Streamlit
Opened
#6 Is there a command that just serves the REST api , similar to ollama run on the cli
Opened
#7 ConnectError
Opened
#8 README doesn't mention that a running ollama server is required
Opened
#9 Batching
Opened
#10 asyncio.run() cannot be called from a running event loop
Opened
#11 Error: Head "http://127.0.0.1:11434/": read tcp 127.0.0.1:36136->127.0.0.1:11434: read: connection reset by peer
Opened
#12 Suggestion: Use models to encapsulate request/responses
Opened
#13 404 on /api/chat
Opened
#14 How can I use context parameter?
Opened
#15 function calling
Opened
#16 📝 Documentation request - for fewshot templates model
Opened
#17 Usage body for LLaVA model
Opened
#18 Batching support in Ollama
Opened
#19 Does chat take options?
Opened
#20 Is there a way for using chat() function by passing more context ?
Opened
#21 Custom models
Opened
#22 keep_alive control how long models stay loaded
Opened
#23 🙏 Feature request > Create model from file path with SDK
Opened
#24 ollama.generate & ollama.chat hangs after about 30*mins
Opened
#25 llama2-uncensored:70b might be pointing to regular llama2:70b?
Opened
#26 Where does ollama.pull() store the models?
Opened
#27 Can't get Async to stop
Opened
#28 chat and cli chat get different outputs when using llava
Opened
#29 Setting which GPU to use with PyTorch
Opened
#30 Add in simple to use iterative chat (chat with history)
Opened
#31 [query] Is it not possible to run ollama python library on a colab notebook ?
Opened
#32 readme needs to show example of image generations
Opened
#33 ollama server hangs constantly
Opened
#34 System Message causing no answer from Assistant
Opened
#35 From ollama to transformer.AutoModelForCausalLM
Opened
#36 Add example for chat with history
Opened
#37 fail to run this example file [examples/multimodal/main.py]
Opened
#38 Possible workaround for the issues with multimodal...
Opened
#39 How to set temprature and output token size in the chat mode?
Opened
#40 terribly slow: format="json", stream=False, please advise
Opened
#41 How do I define the 'base_url' using embeddings()
Opened
#42 Understanding Variable Response Times from a Local Mistral Model
Opened
#43 pip install ollama error
Opened
#44 pull method to get total progress info ?
Opened
#45 client run timeout,no response
Opened
#46 Running without network error: ollama._types.ResponseError
Opened
#47 Can I set num_ctx=-1 to use max possible context window?
Opened
#48 ResponseError(without error information) when running with python
Opened
#49 num_ctx=100000 does not work
Opened
#50 response error when calling any ollama functions
Opened
#51 Setting up top k , Max tokens , context length ?
Opened
#52 Unable to get ollama serve working
Opened
#53 Why Ollama is so terribly slow when I set format="json"
Opened
#54 Python 3.12.2 Cannot import ollama
Opened
#55 Clone the HuggingFace repository (optional) llm/llama.cpp/convert.py can't find this file.
Opened
#56 Use with personal context
Opened
#57 json format do not return all the results
Opened
#58 ollama.chat is missing template kwarg.
Opened
#59 ai接受不到图片，也不按system设定执行
Opened
#60 Continued Conversations
Opened
#61 Max token question
Opened
#62 Second request never completes
Opened
#63 ❔ Dealing with Structured Outputs (pydantic) 📝
Opened
#64 Client fails to query resources behind reverse proxy path
Opened
#65 Question: the response I got by using terminal is way better than using ollama.generate
Opened
#66 Error: Server disconnected without sending a response. Error: [WinError 10061] No connection could be made because the target machine actively refused it
Opened
#67 gpu not worked, only cpu. How to solve it?
Opened
#68 Support "ping" on client for the health endpoint
Opened
#69 Add an error message when Ollama server isn't running
Opened
#70 Support Metrics
Opened
#71 Embeddings don't seem to work.
Opened
#72 Add a link to the documentation from the README
Opened
#73 Feature request for less configuration by merging external library
Opened
#74 TypeError: Client.__init__() got an unexpected keyword argument 'follow_redirects'
Opened
#75 Client.create inserts escape quotes \" for the last PARAMETER stop.
Opened
#76 ollama-python outputs sometimes half tokens. original ollama works fine in my system
Opened
#77 Function Calling
Opened
#78 GPU- Utilization freezing
Opened
#79 AttributeError: partially initialized module 'ollama' has no attribute 'chat' (most likely due to a circular import)
Opened
#80 ollama._types.ResponseError: no FROM line for the model was specified
Opened
#81 Ukrainian language?
Opened
#82 ollama._types.ResponseError: model 'llama2' not found
Opened
#83 Logits/Probabilities along with the generated token
Opened
#84 ollama._types.ResponseError: Unsupported type: 'bool'
Opened
#85 custom client seems working not as expected with apple silicon mac
Opened
#86 getting NotImplementedError
Opened
#87 GPU Selection & Device Specification
Opened
#88 model not found on macOS after upgraded to 0.1.38
Opened
#89 OLLAMA Python, Why can't I use all the threads on the CPU?
Opened
#90 Met the 503 code status error when run ollama to connect localhost for chat on M3 apple silicon
Opened
#91 http 104 error
Opened
#92 Local running lamma3. httpx.connecterror [wrong ssl]
Opened
#93 ollama.create fails with ollama._types.ResponseError: unexpected EOF
Opened
#94 Interactive Mode
Opened
#95 Command Line Interface
Opened
#96 Support for for /api/ps
Opened
#97 Python cannot use custom ollama model
Opened
#98 Documentation Request
Opened
#99 How to implment access token or other form of authorization
Opened
#100 ollama-python equivalent of /clear and context summarization in a chat
Opened
#101 Full features of rest api
Opened
#102 ollama.create fails with ollama._types.ResponseError: name and path are required
Opened
#103 Chat example
Opened
#104 Model 'llama3' Not Found but from another Docker container
Opened
#105 Async client can only process 2 instances at at time
Opened
#106 no option to click on chooseing a model!
Opened
#107 Where does ollama-python saves the pulled model?
Opened
#108 Getting ConnectError: [Errno 111] Connection refused
Opened
#109 Issue with Ollama and Pydantic
Opened
#110 Add way to abort a streaming response from chat / generate
Opened
#111 Wrong host handling
Opened
#112 Timeout error after approximately 10 seconds when running on macOS
Opened
#113 async stream chat *just don't work* (tm)
Opened
#114 Need Temperature/Max_token Options
Opened
#115 Please do not append port 80 or 443 when I set a custom host, as this can lead to errors on certain gateways.
Opened
#116 Update pypi
Opened
#117 tool calls integration broken when empty
Opened
#118 Pass a list of functions/tools to client like in the API
Opened
#119 Bug in tool_calls response parsing
Opened
#120 Decorator to generate schemas for tools
Opened
#121 Persistent chat memory
Opened
#122 Ollama in combination with Mistral NeMo is making up weird questions on its own
Opened
#123 Provide a way to override system prompt at runtime
Opened
#124 Client's host doesn't work when the host is behind a proxy server
Opened
#125 'timed out waiting for llama runner to start' in ~6 minutes when trying to load large model
Opened
#126 Avoid the need to download ollama manually
Opened
#127 Reproducible output cannot be achieved in model Mixtral
Opened
#128 Version is set to 0.0.0 in pyproject.toml
Opened
#129 create modelfile, this is why
Opened
#130 how to make batch request with python client?
Opened
#131 Return python object instead of JSON
Opened
#132 Inconsistent API Behavior
Opened
#133 🐛 Custom modelfile Regression causing ResponseError: command must be one of "from", "license",
Opened
#134 Add a 'stop' method to abort model loading
Opened
#135 tools not available in ollama
Opened
#136 Inconsistent prompt_eval_count for Large Prompts in Ollama Python Library
Opened
#137 ollama._types.ResponseError: llama runner process no longer running: -1
Opened
#138 Inquiry About Token Probability Feature
Opened
#139 Please expose the contents of the _type file to allow for better static type analysis
Opened
#140 Ollama chat stream Newline
Opened
#141 Tool calls are not properly returned when chat() is called with stream=True
Opened
#142 How to generate text to image with ollama?
Opened
#143 Can we get an ollama.stop?
Opened
#144 How to send image to vision model
Opened
#145 Ollama multimodal - Gemma not seeing image
Opened
#146 Unable to generate responses normally when invoking the fine-tuned model using Python.
Opened
#147 Not loading Llama 3.2:3b
Opened
#148 Command raised an exception: AttributeError: 'Command' object has no attribute 'chat'???
Opened
#149 Unable to set Client host, httpx.ConnectError
Opened
#150 Abort Requests
Opened
#151 Slow Inference on LLAMA 3.1 405B using ollama.generate with Large Code Snippets on multi-H100 GPUs
Opened
#152 Leftovers of a chat template. (Ollama, Llama 3.2)
Opened
#153 InvalidURL: Invalid port: ':1]'
Opened
#154 Ollama
Opened
#155 Ollama gives error Connection refused.
Opened
#156 No model memory
Opened
#157 Exception: Attempted to call a sync iterator on an async stream.
Opened
#158 Raspberry Pi 5 8gb: Running any query with (llava or moondream2) + image causes the device to shut down
Opened
#159 Check tool called when stream is set to true
Opened
#160 504 Gateway Timeout - The server didn't respond in time
Opened
#161 Please add examples for image/vision models
Opened
#162 Update all examples to use the new Pydantic integration
Opened
#163 [Errno 111] Connection refused while embedding in docker
Opened
#164 ollama.generate() with multimodal llama3.2-vision does not pass images array when raw=True
Opened
#165 AttributeError: 'NoneType' object has no attribute 'get'
Opened
#166 Model doesn't ger offloaded from VRAM after deletion
Opened
#167 Chat with Phyton
Opened
#168 ollama 0.4.0 changes tool_calls API
Opened
#169 New Tool Calling issues.
Opened
#170 craete function ollama._types.ResponseError
Opened
#171 about maintaining session continuity: how to get context by python clinet
Opened
#172 Error while working with multimodal chat LLaMa 3.2-vision 90B
Opened
#173 Calling chat with function as tool gives an empty response
Opened
#174 Missing "projector_info" key and others in ollama.show() dictionary output for version 0.4.1
Opened
#175 Embeddings underperform compared to Llama cpp
Opened
#176 Error message is not helpful when the input to a model exceeds the limit.
Opened
#177 Request: allowing httpx version 0.28
Opened
#178 Model doesn't seem to include tool output in its response
Opened
#179 multi-image support for llama3.2-vision?
Opened
#180 Response + Function Calling on the same model call
Opened
#181 Breaking Change for langchain-ollama==0.2.1 on ollama==0.4.3
Opened
#182 Structured output, json schema error
Opened
#183 ollama.create not working properly
Opened
#184 There is a problem using ollama in vscode+jupyter
Opened
#185 Validation error when providing a base64 string to Image(value=...) in Message(images=...)
Opened
#186 where/how can I find the path of ollama model?
Opened
#187 Adding Dropout Layer to models and accessing nn layers information
Opened
#188 Get custom headers in ChatResponse
Opened
#189 httpx broke ollama being used within multiple event loops
Opened
#190 ollama._types.ResponseError ResponseError(e.response.text, e.response.status_code) from None
Opened
#191 Simple Chat gives httpx.ConnectError
Opened
#192 A few questions about vision models (multimodal)
Opened
#193 Unable to set keep_alive parameter
Opened
#194 Tool call doesn't honor the function definition when responding
Opened
#195 Unable to set environment variables - OLLAMA_NUM_PARALLEL, OLLAMA_NUM_GPU, and OLLAMA_NUM_THREAD
Opened
#196 chat method is not able to identify add_two_numbers as tool
Opened
#197 Check if ollama server is running or not
Opened
#198 Unable to Connect to Localhost by Default When OLLAMA_HOST is Set to 0.0.0.0
Opened
#199 set flash attention via options?
Opened
#200 Multimodal Embeddings?
Opened
#201 Upgrade Poetry to 2.x.x or use uv
Opened
#202 import ollama error when os.environ["HTTP_PROXY"] = "socks5h://xxx"
Opened
#203 Missing dependancy
Opened
#204 Semantic recognition or semantic classification
Opened
#205 Question - Batch Processing
Opened
#206 json: cannot unmarshal object into Go struct field ChatRequest.format of type string (status code: 400)
Opened
#207 Tools with nested properties getting cut short
Opened
#208 ollama.create How to create models from local files without modelfile?
Opened
#209 ollama.create : "Client.create() got an unexpected keyword argument 'modelfile'"
Opened
#210 FIXED
Opened
#211 Possible bugs in both tools examples (or at least something to document)
Opened
#212 Moondream:v2 issue 500 error
Opened
#213 Tonkenization of the context
Opened
#214 httpcore.RemoteProtocolError: Server disconnected without sending a response. The above exception was the direct cause of the following exception:
Opened
#215 ollama.pull() fails with ResponseError but ollama pull on the command line works fine
Opened
#216 ollama.generate(model='deepseek-r1:1.5b',prompt='hello') error
Opened
#217 Is there an example in the project where a DOC file is used as input for inference?
Opened
#218 Unable to close connections
Opened
#219 API Method to get model loading progress?
Opened
#220 Limit the number of generated tokens?
Opened
#221 TypeError: AsyncClient.chat() got an unexpected keyword argument 'tools'
Opened
#222 embed function with LLMs in Ollama
Opened
#223 How to use images
Opened
#224 test asyncio_tool.py with qwen32B(distrilled by deepseek-r1)
Opened
#225 Why can't I call the local Ollama model through this python library under Windows system?
Opened
#226 BUG: ollama.create() fails with ollama server message indicating missing path or modelfile, but CLI cclient works with same information
Opened
#227 Ollama Python client mostly broken on Windows 11
Opened
#228 Structured Output - Literal Validation Error
Opened
#229 Tool property missing enum
Opened
#230 Phi-4-mini function calling support
Opened
#231 Can we access the model using Ollama via WebSockets?
Opened
#232 LlamaIndex Fails to Connect to Ollama in Conda Environment, Works in Command Prompt
Opened
#233 Streaming Doesn't Work When Using Tools
Opened
#234 No proper support for Tool Messages?
Opened
#235 Www.theBioutful.home.co seventhunderm
Opened
#236 After changing OLLAMA_HOST=0.0.0.0, ollama.chat() and ollama.generate() not work
Opened
#237 Model List not available via Ollama library.
Opened
#238 بايثون عايز الاتصال والتأثير
Opened
#239 Documentation?
Opened
#240 interrupt the inference
Opened
#241 Fine-Tuning
Opened
#242 Tool calling example may have a glitch - seems to only record the result of the last tool call
Opened
#243 chat completion does not agree with documentation
Opened
#244 Feature Request: Wheel for Ollama Server and Corresponding Startup
Opened
#245 Provide request timeout option
Opened
#246 Ollama and ollama-python have different httpx requirements
Opened
#247 [BUG] Inconsistent response for api/tag
Opened
#248 Pydantic ValidationError: tool_calls.function.arguments expects dict, receives str from server
Opened
#249 multimodal_chat.py and multimodal_generate.py doesn't exist
Opened
#250 Expose "Processor" on PS() Call
Opened
#251 No model information retrieval
Opened
#252 status code 503
Opened
#253 Support for --verbose flag
Opened
#254 Stop a Currently Running Model
Opened
#255 [Bug] Does not provide capabilities for /show api call
Opened
#256 options (temp, etc) print values list in python
Opened
#257 Simple Enums missing from structured outputs
Opened
#258 ps method not working through OpenWebUI - ValidationError
Opened
#259 Sigsegv during garbage collection under certian circumstances
Opened
#260 Is ollama-python avaliable on conda?
Opened
#261 image-based PDFs
Opened
#262 Role of control returns an error.
Opened
#263 [BUG] Ollama create method is only creating a single model based on the _from parameter, but not the derivate model like the cli
Opened
#264 types: loosen constraint on tool JSON
Opened
#265 PydanticDeprecatedSince211: Accessing the 'model_fields' attribute on the instance is deprecated.
Opened
#266 ollama-python does not install on Python 3.14 beta 1
Opened
#267 Structured output (json format)
Opened
#268 ollama.chat() should accept images for vision model support
Opened
#269 Is logprobs supported in chat()? If not, can it be added?
Opened
#270 Request timeout feature
Opened
#271 Missing license in pyproject
Opened
#272 Critical Packaging Error: Wheels for ollama 0.1.8 and 0.2.1 on PyPI contain pre-0.1.8 code
Opened
#273 release the last version
Opened
#274 Error on importing: "re.PatternError: global flags not at the start of the expression at position 24"
Opened
#275 Think parameter does not seem to work with Qwen3
Opened
#276 Thinking with Structured Output does not work
Opened
#277 Add Client.close() and context manager
Opened
#278 Logging level of "HTTP Request: POST" should be DEBUG, not INFO
Opened
#279 Thinking with tool calling is problematic
Opened
#280 [BUG] Regular expressions containing escapes cause ResponseErrors
Opened
#281 Log level of "HTTP Request: POST" result should be changed to DEBUG
Opened
#282 Tools not working when providing a schema via format=...
Opened
#283 Wrong example documentation URL
Opened
#284 Server disconnected without sending a response
Opened
#285 Think only supports bool
Opened
#286 How to get the Ollama version?
Opened
#287 unexpected error format in response (status code: 500) with gpt-oss:20b
Opened
#288 Unable to connect to proxied model from python api with self-signed SSL certificate
Opened
#289 error in think key and error in message role in ollama gpt-oss
Opened
#290 Is interaction with MCP tool possible?
Opened
#291 ollama-python does not expose the name field returned by /api/tags
Opened
#292 Ollama.chat(...) does not support images
Opened
#293 Feature Request: Ollama Tools
Opened
#294 ollama client uses the keyword 'input' for embeddings, but Ollama 0.11.4 requires 'prompt' ?
Opened
#295 Prompts Being ignored
Opened
#296 Images and context windows
Opened
#297 examples/structured-outputs-image.py
Opened
#298 think flag has no effect when using qwen3:8b
Opened
#299 examples/tools.py ignores defined tools and spits out usual LLM results.
Opened
#300 Missing WebCrawlResponse / WebSearchResponse
Opened
#301 answer seems to relate only to the system prompt, not to the actual prompt (user)
Opened
#302 A way to set OLLAMA_API_KEY for web_search
Opened
#303 VLM cannot read png
Opened
#304 Issues with qwen3:32b, llama4:16x17b, gpt-oss:20b
Opened
#305 Possible bug with kimi-k2-thinking☁️ ollama._types.ResponseError: unmarshal: invalid character 'I' looking for beginning of value (status code: 500))`
Opened
#306 OpenAI compatibility for /v1/embeddings
Opened
#307 cant support deepseek-ocr model
Opened
#308 num_gpu option confusion
Opened
#309 AI模型minimax-m2:cloud无法通过py调用
Opened
#310 ShowResponse ValidationError when /api/show omits model_info (cloud models)
Opened
#311 Test
Opened
#312 Could you add the with-as syntax
Opened
#313 qwen3-coder:latest responds with "The models does not support function calls" and other random messages
Opened
#314 x
Opened
#315 [PR #1] [MERGED] add ci tests/lint
Opened
#316 [PR #3] [MERGED] add default async client aliases
Opened
#317 [PR #4] [MERGED] Mxyng/rm default async
Opened
#318 [PR #5] [MERGED] Mxyng
Opened
#319 [PR #2] [MERGED] fix endpoints
Opened
#320 [PR #10] [MERGED] Changed 'show' to use POST instead of GET
Opened
#321 [PR #7] [MERGED] fix gh release upload
Opened
#322 [PR #6] [MERGED] fix publish
Opened
#323 [PR #9] [MERGED] s/target/destination/
Opened
#324 [PR #8] [MERGED] fix: remote create new file
Opened
#325 [PR #13] [MERGED] add example for pulling with progress bar
Opened
#326 [PR #15] [MERGED] examples
Opened
#327 [PR #17] [MERGED] update response error field to match json response
Opened
#328 [PR #11] [MERGED] ci: give publish job content perms
Opened
#329 [PR #16] [MERGED] fix: update OLLAMA_HOST parsing to match ollama CLI
Opened
#330 [PR #19] [MERGED] upgrade pillow
Opened
#331 [PR #18] [MERGED] fix unit tests
Opened
#332 [PR #20] [MERGED] fix pull example typo
Opened
#333 [PR #28] [CLOSED] Made the API more readable.
Opened
#334 [PR #26] [CLOSED] Add example using seed param to get consistent outputs
Opened
#335 [PR #31] [MERGED] add keep_alive
Opened
#336 [PR #32] [MERGED] update github actions
Opened
#337 [PR #36] [CLOSED] async call in Jupyter notebook
Opened
#338 [PR #34] [MERGED] error handling code
Opened
#339 [PR #40] [MERGED] fix parse modelfile
Opened
#340 [PR #42] [CLOSED] bump httpx to 0.26.0
Opened
#341 [PR #41] [MERGED] Update README.md
Opened
#342 [PR #45] [MERGED] doc(README) : add prerequisites
Opened
#343 [PR #50] [MERGED] fix: encode base64 inputs
Opened
#344 [PR #52] [MERGED] create example
Opened
#345 [PR #54] [CLOSED] Feat/pydantic models & refactor
Opened
#346 [PR #55] [CLOSED] Testing repeated calls
Opened
#347 [PR #61] [CLOSED] Fixes URL parsing when basic auth is included in the URL.
Opened
#348 [PR #58] [MERGED] python user agent
Opened
#349 [PR #64] [CLOSED] Add iterative_chat and examples for simlified chat history keeping
Opened
#350 [PR #68] [CLOSED] Added example showing how to use generate with images
Opened
#351 [PR #93] [CLOSED] Add Phorm AI Badge
Opened
#352 [PR #90] [CLOSED] Add an example using continuous dialogue
Opened
#353 [PR #75] [CLOSED] Stability testing for client
Opened
#354 [PR #97] [CLOSED] Loosen httpx constraint
Opened
#355 [PR #102] [MERGED] update dependencies
Opened
#356 [PR #103] [MERGED] add dependabot
Opened
#357 [PR #104] [MERGED] Bump actions/upload-artifact from 3 to 4
Opened
#358 [PR #105] [MERGED] Bump pytest-cov from 4.1.0 to 5.0.0
Opened
#359 [PR #106] [MERGED] Bump ruff from 0.1.15 to 0.3.4
Opened
#360 [PR #110] [MERGED] Bump pillow from 10.2.0 to 10.3.0
Opened
#361 [PR #114] [MERGED] modified embeddings return annotation
Opened
#362 [PR #111] [CLOSED] Bump ruff from 0.3.4 to 0.3.5
Opened
#363 [PR #115] [CLOSED] Bump ruff from 0.3.4 to 0.3.6
Opened
#364 [PR #107] [MERGED] Bump pytest from 7.4.4 to 8.1.1
Opened
#365 [PR #122] [CLOSED] Bump ruff from 0.3.4 to 0.4.0
Opened
#366 [PR #118] [MERGED] fix 'content' check on messages in chat()
Opened
#367 [PR #116] [CLOSED] Bump ruff from 0.3.4 to 0.3.7
Opened
#368 [PR #125] [CLOSED] Update README.md - Changed llama2 -> llama3
Opened
#369 [PR #124] [MERGED] Bump ruff from 0.3.4 to 0.4.1
Opened
#370 [PR #131] [CLOSED] Bump ruff from 0.4.1 to 0.4.2
Opened
#371 [PR #130] [CLOSED] Updated readme to mention that this library needs ollama service to be running and also snippet to run it if someone is using a jupyter notebook
Opened
#372 [PR #129] [MERGED] Add py.typed to mark the library as typed
Opened
#373 [PR #134] [CLOSED] Bump pytest from 8.1.1 to 8.1.2
Opened
#374 [PR #132] [CLOSED] Add type overloads for chat() method in _client.py
Opened
#375 [PR #135] [MERGED] Update README.md link still point legacy url
Opened
#376 [PR #140] [MERGED] Bump pytest from 8.1.1 to 8.2.0
Opened
#377 [PR #137] [CLOSED] Add Status Badges
Opened
#378 [PR #138] [MERGED] Update README.md
Opened
#379 [PR #141] [CLOSED] Added temperature parameter
Opened
#380 [PR #150] [MERGED] add quantization to create requests
Opened
#381 [PR #151] [CLOSED] accept license, template, system as files
Opened
#382 [PR #148] [MERGED] Bump ruff from 0.4.1 to 0.4.3
Opened
#383 [PR #152] [MERGED] remove old options
Opened
#384 [PR #145] [MERGED] fix: annotation in AsyncClient.embedding
Opened
#385 [PR #153] [CLOSED] Bump ruff from 0.4.3 to 0.4.4
Opened
#386 [PR #154] [MERGED] add done reason to generate type responses
Opened
#387 [PR #155] [CLOSED] Add clarity to getting started docs.
Opened
#388 [PR #158] [MERGED] Avoid side effects if chat message contains images
Opened
#389 [PR #162] [MERGED] Bump pytest-asyncio from 0.23.6 to 0.23.7
Opened
#390 [PR #163] [CLOSED] Bump pytest from 8.2.0 to 8.2.1
Opened
#391 [PR #168] [CLOSED] Bump ruff from 0.4.3 to 0.4.5
Opened
#392 [PR #169] [CLOSED] Bump ruff from 0.4.3 to 0.4.6
Opened
#393 [PR #170] [MERGED] Add URL path to client URL in in Client._parse_host()
Opened
#394 [PR #172] [MERGED] Bump ruff from 0.4.3 to 0.4.7
Opened
#395 [PR #177] [MERGED] Python API PS
Opened
#396 [PR #178] [MERGED] Bump pytest from 8.2.0 to 8.2.2
Opened
#397 [PR #175] [CLOSED] Create ollamapythonjava
Opened
#398 [PR #179] [MERGED] Simple Example
Opened
#399 [PR #180] [CLOSED] Overloads for Methods
Opened
#400 [PR #185] [CLOSED] CLI proof of concept
Opened
#401 [PR #181] [MERGED] Add type overloads to methods
Opened
#402 [PR #189] [CLOSED] Bump ruff from 0.4.7 to 0.4.9
Opened
#403 [PR #182] [CLOSED] Bump ruff from 0.4.7 to 0.4.8
Opened
#404 [PR #194] [CLOSED] Bump ruff from 0.4.7 to 0.4.10
Opened
#405 [PR #195] [CLOSED] Update _client.py - always include path in create
Opened
#406 [PR #201] [CLOSED] fix: PydanticUserError: Please use typing_extensions.TypedDict inst…
Opened
#407 [PR #199] [CLOSED] fix: Ensure JSON response is properly parsed in generate function when format is set to 'json'
Opened
#408 [PR #198] [CLOSED] Bump ruff from 0.4.7 to 0.5.0
Opened
#409 [PR #203] [MERGED] Bump pillow from 10.3.0 to 10.4.0
Opened
#410 [PR #206] [CLOSED] Bump ruff from 0.4.7 to 0.5.1
Opened
#411 [PR #207] [CLOSED] Adding an example how you can ask several models something.
Opened
#412 [PR #212] [CLOSED] support tool calls
Opened
#413 [PR #208] [MERGED] Support api/embed
Opened
#414 [PR #211] [MERGED] Bump ruff from 0.4.7 to 0.5.2
Opened
#415 [PR #213] [MERGED] integrate tool calls
Opened
#416 [PR #216] [MERGED] Deprecate embeddings from docs in favor of embed
Opened
#417 [PR #215] [MERGED] add insert support to generate endpoint
Opened
#418 [PR #219] [CLOSED] Bump ruff from 0.5.2 to 0.5.3
Opened
#419 [PR #217] [MERGED] Bump pytest-asyncio from 0.23.7 to 0.23.8
Opened
#420 [PR #220] [CLOSED] Bump pytest-httpserver from 1.0.10 to 1.0.11
Opened
#421 [PR #225] [CLOSED] Bump ruff from 0.5.2 to 0.5.4
Opened
#422 [PR #224] [MERGED] Bump pytest-httpserver from 1.0.10 to 1.0.12
Opened
#423 [PR #226] [CLOSED] Bump pytest from 8.2.2 to 8.3.1
Opened
#424 [PR #227] [MERGED] Update Message annotations to support tool calls
Opened
#425 [PR #231] [MERGED] Bump pytest from 8.2.2 to 8.3.2
Opened
#426 [PR #234] [CLOSED] Add Tool Registry Feature
Opened
#427 [PR #230] [MERGED] Bump ruff from 0.5.2 to 0.5.5
Opened
#428 [PR #236] [MERGED] fix: tool_calls response parsing
Opened
#429 [PR #237] [MERGED] update to llama3.1
Opened
#430 [PR #243] [CLOSED] Bump ruff from 0.5.5 to 0.5.6
Opened
#431 [PR #254] [CLOSED] Bump ruff from 0.5.5 to 0.6.0
Opened
#432 [PR #238] [CLOSED] Autogen Tool, ToolFunction, Parameters, Property schema when opt-in to using type-hinted function params
Opened
#433 [PR #252] [MERGED] Bump pytest-httpserver from 1.0.12 to 1.1.0
Opened
#434 [PR #247] [CLOSED] Bump ruff from 0.5.5 to 0.5.7
Opened
#435 [PR #260] [MERGED] Bump pytest-asyncio from 0.23.8 to 0.24.0
Opened
#436 [PR #255] [CLOSED] Bump ruff from 0.5.5 to 0.6.1
Opened
#437 [PR #261] [MERGED] Bump ruff from 0.5.5 to 0.6.2
Opened
#438 [PR #262] [MERGED] IPv6 support
Opened
#439 [PR #256] [CLOSED] support base path. this is useful for multiple applications under one…
Opened
#440 [PR #264] [CLOSED] chore(deps): Update dependencies
Opened
#441 [PR #266] [MERGED] _stream in async client raises RuntimeError when processing HTTP errors
Opened
#442 [PR #265] [CLOSED] Bump httpx from 0.27.0 to 0.27.2
Opened
#443 [PR #267] [MERGED] Bump ruff from 0.6.2 to 0.6.3
Opened
#444 [PR #270] [CLOSED] Bump ruff from 0.6.3 to 0.6.4
Opened
#445 [PR #275] [MERGED] add basic delete/copy tests
Opened
#446 [PR #276] [MERGED] add pydantic for validation and serialization
Opened
#447 [PR #272] [CLOSED] Make _encode_image error message more helpful and shorten docstring
Opened
#448 [PR #277] [MERGED] no head request for create blob
Opened
#449 [PR #278] [MERGED] Bump pytest from 8.3.2 to 8.3.3
Opened
#450 [PR #282] [CLOSED] add OpenAI example in README.md.
Opened
#451 [PR #281] [MERGED] Bump ruff from 0.6.3 to 0.6.5
Opened
#452 [PR #284] [MERGED] update pyproject.toml
Opened
#453 [PR #285] [CLOSED] Bump ruff from 0.6.5 to 0.6.6
Opened
#454 [PR #286] [CLOSED] add ollama.list() example.
Opened
#455 [PR #290] [CLOSED] Bump ruff from 0.6.5 to 0.6.7
Opened
#456 [PR #296] [CLOSED] Bump ruff from 0.6.5 to 0.6.9
Opened
#457 [PR #297] [CLOSED] add chat-history example.
Opened
#458 [PR #291] [CLOSED] Bump ruff from 0.6.5 to 0.6.8
Opened
#459 [PR #299] [CLOSED] Enable subpath-mounted ollama and basic auth