16 Commits (f1313339ac6f45bcf0afcf572d372c7e3660c0af)

Author	SHA1	Message	Date
Yudhajit Sinha	280a914920	community[patch]: Invoke callback prior to yielding token (ollama) (#18629) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ & _astream_ methods in llms/ollama. - Issue: #16913 - Dependencies: None	6 months ago
gonvee	b82644078e	community: Add `keep_alive` parameter to control how long the model w… (#19005) ... Add `keep_alive` parameter to control how long the model will stay loaded into memory with Ollama。 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Nikita Titov	9f2ab37162	community[patch]: don't try to parse json in case of errored response (#18317) ... Related issue: #13896. In case Ollama is behind a proxy, proxy error responses cannot be viewed. You aren't even able to check response code. For example, if your Ollama has basic access authentication and it's not passed, `JSONDecodeError` will overwrite the truth response error. <details> <summary><b>Log now:</b></summary> ``` { "name": "JSONDecodeError", "message": "Expecting value: line 1 column 1 (char 0)", "stack": "--------------------------------------------------------------------------- JSONDecodeError Traceback (most recent call last) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/requests/models.py:971, in Response.json(self, **kwargs) 970 try: --> 971 return complexjson.loads(self.text, **kwargs) 972 except JSONDecodeError as e: 973 # Catch JSON-related errors and raise as requests.JSONDecodeError 974 # This aliases json.JSONDecodeError and simplejson.JSONDecodeError File /opt/miniforge3/envs/.gpt/lib/python3.10/json/__init__.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw) 343 if (cls is None and object_hook is None and 344 parse_int is None and parse_float is None and 345 parse_constant is None and object_pairs_hook is None and not kw): --> 346 return _default_decoder.decode(s) 347 if cls is None: File /opt/miniforge3/envs/.gpt/lib/python3.10/json/decoder.py:337, in JSONDecoder.decode(self, s, _w) 333 \"\"\"Return the Python representation of ``s`` (a ``str`` instance 334 containing a JSON document). 335 336 \"\"\" --> 337 obj, end = self.raw_decode(s, idx=_w(s, 0).end()) 338 end = _w(s, end).end() File /opt/miniforge3/envs/.gpt/lib/python3.10/json/decoder.py:355, in JSONDecoder.raw_decode(self, s, idx) 354 except StopIteration as err: --> 355 raise JSONDecodeError(\"Expecting value\", s, err.value) from None 356 return obj, end JSONDecodeError: Expecting value: line 1 column 1 (char 0) During handling of the above exception, another exception occurred: JSONDecodeError Traceback (most recent call last) Cell In[3], line 1 ----> 1 print(translate_func().invoke('text')) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/runnables/base.py:2053, in RunnableSequence.invoke(self, input, config) 2051 try: 2052 for i, step in enumerate(self.steps): -> 2053 input = step.invoke( 2054 input, 2055 # mark each step as a child run 2056 patch_config( 2057 config, callbacks=run_manager.get_child(f\"seq:step:{i+1}\") 2058 ), 2059 ) 2060 # finish the root run 2061 except BaseException as e: File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:165, in BaseChatModel.invoke(self, input, config, stop, **kwargs) 154 def invoke( 155 self, 156 input: LanguageModelInput, (...) 160 **kwargs: Any, 161 ) -> BaseMessage: 162 config = ensure_config(config) 163 return cast( 164 ChatGeneration, --> 165 self.generate_prompt( 166 [self._convert_input(input)], 167 stop=stop, 168 callbacks=config.get(\"callbacks\"), 169 tags=config.get(\"tags\"), 170 metadata=config.get(\"metadata\"), 171 run_name=config.get(\"run_name\"), 172 **kwargs, 173 ).generations[0][0], 174 ).message File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:543, in BaseChatModel.generate_prompt(self, prompts, stop, callbacks, **kwargs) 535 def generate_prompt( 536 self, 537 prompts: List[PromptValue], (...) 540 **kwargs: Any, 541 ) -> LLMResult: 542 prompt_messages = [p.to_messages() for p in prompts] --> 543 return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:407, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs) 405 if run_managers: 406 run_managers[i].on_llm_error(e, response=LLMResult(generations=[])) --> 407 raise e 408 flattened_outputs = [ 409 LLMResult(generations=[res.generations], llm_output=res.llm_output) 410 for res in results 411 ] 412 llm_output = self._combine_llm_outputs([res.llm_output for res in results]) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:397, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs) 394 for i, m in enumerate(messages): 395 try: 396 results.append( --> 397 self._generate_with_cache( 398 m, 399 stop=stop, 400 run_manager=run_managers[i] if run_managers else None, 401 **kwargs, 402 ) 403 ) 404 except BaseException as e: 405 if run_managers: File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:576, in BaseChatModel._generate_with_cache(self, messages, stop, run_manager, **kwargs) 572 raise ValueError( 573 \"Asked to cache, but no cache found at `langchain.cache`.\" 574 ) 575 if new_arg_supported: --> 576 return self._generate( 577 messages, stop=stop, run_manager=run_manager, **kwargs 578 ) 579 else: 580 return self._generate(messages, stop=stop, **kwargs) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_community/chat_models/ollama.py:250, in ChatOllama._generate(self, messages, stop, run_manager, **kwargs) 226 def _generate( 227 self, 228 messages: List[BaseMessage], (...) 231 **kwargs: Any, 232 ) -> ChatResult: 233 \"\"\"Call out to Ollama's generate endpoint. 234 235 Args: (...) 247 ]) 248 \"\"\" --> 250 final_chunk = self._chat_stream_with_aggregation( 251 messages, 252 stop=stop, 253 run_manager=run_manager, 254 verbose=self.verbose, 255 **kwargs, 256 ) 257 chat_generation = ChatGeneration( 258 message=AIMessage(content=final_chunk.text), 259 generation_info=final_chunk.generation_info, 260 ) 261 return ChatResult(generations=[chat_generation]) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_community/chat_models/ollama.py:183, in ChatOllama._chat_stream_with_aggregation(self, messages, stop, run_manager, verbose, **kwargs) 174 def _chat_stream_with_aggregation( 175 self, 176 messages: List[BaseMessage], (...) 180 **kwargs: Any, 181 ) -> ChatGenerationChunk: 182 final_chunk: Optional[ChatGenerationChunk] = None --> 183 for stream_resp in self._create_chat_stream(messages, stop, **kwargs): 184 if stream_resp: 185 chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_community/chat_models/ollama.py:156, in ChatOllama._create_chat_stream(self, messages, stop, **kwargs) 147 def _create_chat_stream( 148 self, 149 messages: List[BaseMessage], 150 stop: Optional[List[str]] = None, 151 **kwargs: Any, 152 ) -> Iterator[str]: 153 payload = { 154 \"messages\": self._convert_messages_to_ollama_messages(messages), 155 } --> 156 yield from self._create_stream( 157 payload=payload, stop=stop, api_url=f\"{self.base_url}/api/chat/\", **kwargs 158 ) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_community/llms/ollama.py:234, in _OllamaCommon._create_stream(self, api_url, payload, stop, **kwargs) 228 raise OllamaEndpointNotFoundError( 229 \"Ollama call failed with status code 404. \" 230 \"Maybe your model is not found \" 231 f\"and you should pull the model with `ollama pull {self.model}`.\" 232 ) 233 else: --> 234 optional_detail = response.json().get(\"error\") 235 raise ValueError( 236 f\"Ollama call failed with status code {response.status_code}.\" 237 f\" Details: {optional_detail}\" 238 ) 239 return response.iter_lines(decode_unicode=True) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/requests/models.py:975, in Response.json(self, **kwargs) 971 return complexjson.loads(self.text, **kwargs) 972 except JSONDecodeError as e: 973 # Catch JSON-related errors and raise as requests.JSONDecodeError 974 # This aliases json.JSONDecodeError and simplejson.JSONDecodeError --> 975 raise RequestsJSONDecodeError(e.msg, e.doc, e.pos) JSONDecodeError: Expecting value: line 1 column 1 (char 0)" } ``` </details> <details> <summary><b>Log after a fix:</b></summary> ``` { "name": "ValueError", "message": "Ollama call failed with status code 401. Details: <html>\r <head><title>401 Authorization Required</title></head>\r <body>\r <center><h1>401 Authorization Required</h1></center>\r <hr><center>nginx/1.18.0 (Ubuntu)</center>\r </body>\r </html>\r ", "stack": "--------------------------------------------------------------------------- ValueError Traceback (most recent call last) Cell In[2], line 1 ----> 1 print(translate_func().invoke('text')) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/runnables/base.py:2053, in RunnableSequence.invoke(self, input, config) 2051 try: 2052 for i, step in enumerate(self.steps): -> 2053 input = step.invoke( 2054 input, 2055 # mark each step as a child run 2056 patch_config( 2057 config, callbacks=run_manager.get_child(f\"seq:step:{i+1}\") 2058 ), 2059 ) 2060 # finish the root run 2061 except BaseException as e: File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:165, in BaseChatModel.invoke(self, input, config, stop, **kwargs) 154 def invoke( 155 self, 156 input: LanguageModelInput, (...) 160 **kwargs: Any, 161 ) -> BaseMessage: 162 config = ensure_config(config) 163 return cast( 164 ChatGeneration, --> 165 self.generate_prompt( 166 [self._convert_input(input)], 167 stop=stop, 168 callbacks=config.get(\"callbacks\"), 169 tags=config.get(\"tags\"), 170 metadata=config.get(\"metadata\"), 171 run_name=config.get(\"run_name\"), 172 **kwargs, 173 ).generations[0][0], 174 ).message File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:543, in BaseChatModel.generate_prompt(self, prompts, stop, callbacks, **kwargs) 535 def generate_prompt( 536 self, 537 prompts: List[PromptValue], (...) 540 **kwargs: Any, 541 ) -> LLMResult: 542 prompt_messages = [p.to_messages() for p in prompts] --> 543 return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:407, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs) 405 if run_managers: 406 run_managers[i].on_llm_error(e, response=LLMResult(generations=[])) --> 407 raise e 408 flattened_outputs = [ 409 LLMResult(generations=[res.generations], llm_output=res.llm_output) 410 for res in results 411 ] 412 llm_output = self._combine_llm_outputs([res.llm_output for res in results]) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:397, in BaseChatModel.generate(self, messages, stop, callbacks, tags, metadata, run_name, **kwargs) 394 for i, m in enumerate(messages): 395 try: 396 results.append( --> 397 self._generate_with_cache( 398 m, 399 stop=stop, 400 run_manager=run_managers[i] if run_managers else None, 401 **kwargs, 402 ) 403 ) 404 except BaseException as e: 405 if run_managers: File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_core/language_models/chat_models.py:576, in BaseChatModel._generate_with_cache(self, messages, stop, run_manager, **kwargs) 572 raise ValueError( 573 \"Asked to cache, but no cache found at `langchain.cache`.\" 574 ) 575 if new_arg_supported: --> 576 return self._generate( 577 messages, stop=stop, run_manager=run_manager, **kwargs 578 ) 579 else: 580 return self._generate(messages, stop=stop, **kwargs) File /opt/miniforge3/envs/.gpt/lib/python3.10/site-packages/langchain_community/chat_models/ollama.py:250, in ChatOllama._generate(self, messages, stop, run_manager, **kwargs) 226 def _generate( 227 self, 228 messages: List[BaseMessage], (...) 231 **kwargs: Any, 232 ) -> ChatResult: 233 \"\"\"Call out to Ollama's generate endpoint. 234 235 Args: (...) 247 ]) 248 \"\"\" --> 250 final_chunk = self._chat_stream_with_aggregation( 251 messages, 252 stop=stop, 253 run_manager=run_manager, 254 verbose=self.verbose, 255 **kwargs, 256 ) 257 chat_generation = ChatGeneration( 258 message=AIMessage(content=final_chunk.text), 259 generation_info=final_chunk.generation_info, 260 ) 261 return ChatResult(generations=[chat_generation]) File /storage/gpt-project/Repos/repo_nikita/gpt_lib/langchain/ollama.py:328, in ChatOllamaCustom._chat_stream_with_aggregation(self, messages, stop, run_manager, verbose, **kwargs) 319 def _chat_stream_with_aggregation( 320 self, 321 messages: List[BaseMessage], (...) 325 **kwargs: Any, 326 ) -> ChatGenerationChunk: 327 final_chunk: Optional[ChatGenerationChunk] = None --> 328 for stream_resp in self._create_chat_stream(messages, stop, **kwargs): 329 if stream_resp: 330 chunk = _chat_stream_response_to_chat_generation_chunk(stream_resp) File /storage/gpt-project/Repos/repo_nikita/gpt_lib/langchain/ollama.py:301, in ChatOllamaCustom._create_chat_stream(self, messages, stop, **kwargs) 292 def _create_chat_stream( 293 self, 294 messages: List[BaseMessage], 295 stop: Optional[List[str]] = None, 296 **kwargs: Any, 297 ) -> Iterator[str]: 298 payload = { 299 \"messages\": self._convert_messages_to_ollama_messages(messages), 300 } --> 301 yield from self._create_stream( 302 payload=payload, stop=stop, api_url=f\"{self.base_url}/api/chat\", **kwargs 303 ) File /storage/gpt-project/Repos/repo_nikita/gpt_lib/langchain/ollama.py:134, in _OllamaCommonCustom._create_stream(self, api_url, payload, stop, **kwargs) 132 else: 133 optional_detail = response.text --> 134 raise ValueError( 135 f\"Ollama call failed with status code {response.status_code}.\" 136 f\" Details: {optional_detail}\" 137 ) 138 return response.iter_lines(decode_unicode=True) ValueError: Ollama call failed with status code 401. Details: <html>\r <head><title>401 Authorization Required</title></head>\r <body>\r <center><h1>401 Authorization Required</h1></center>\r <hr><center>nginx/1.18.0 (Ubuntu)</center>\r </body>\r </html>\r " } ``` </details> The same is true for timeout errors or when you simply mistyped in `base_url` arg and get response from some other service, for instance. Real Ollama errors are still clearly readable: ``` ValueError: Ollama call failed with status code 400. Details: {"error":"invalid options: unknown_option"} ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	7 months ago
Brad Erickson	ecd72d26cf	community: Bugfix - correct Ollama API path to avoid HTTP 307 (#17895) ... Sets the correct /api/generate path, without ending /, to reduce HTTP requests. Reference: https://github.com/ollama/ollama/blob/efe040f8/docs/api.md#generate-request-streaming Before: DEBUG: Starting new HTTP connection (1): localhost:11434 DEBUG: http://localhost:11434 "POST /api/generate/ HTTP/1.1" 307 0 DEBUG: http://localhost:11434 "POST /api/generate HTTP/1.1" 200 None After: DEBUG: Starting new HTTP connection (1): localhost:11434 DEBUG: http://localhost:11434 "POST /api/generate HTTP/1.1" 200 None	7 months ago
Harrison Chase	4eda647fdd	infra: add -p to mkdir in lint steps (#17013) ... Previously, if this did not find a mypy cache then it wouldnt run this makes it always run adding mypy ignore comments with existing uncaught issues to unblock other prs --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	7 months ago
Zhuoyun(John) Xu	508bde7f40	community[patch]: Ollama - Pass headers to post request in async method (#16660) ... # Description A previous PR (https://github.com/langchain-ai/langchain/pull/15881) added option to pass headers to ollama endpoint, but headers are not pass to the async method.	8 months ago
Micah Parker	6543e585a5	community[patch]: Added support for Ollama's num_predict option in ChatOllama (#16633) ... Just a simple default addition to the options payload for a ollama generate call to support a max_new_tokens parameter. Should fix issue: https://github.com/langchain-ai/langchain/issues/14715	8 months ago
Fei Wang	d0e101e4e0	community[patch]: fix ollama astream (#16070) ... Update ollama.py	8 months ago
chyroc	d334efc848	community[patch]: fix top_p type hint (#15452) ... fix: https://github.com/langchain-ai/langchain/issues/15341 @efriis	8 months ago
shahrin014	86321a949f	community: Ollama - Parameter structure to follow official documentation (#16035) ... ## Feature - Follow parameter structure as per official documentation - top level parameters (e.g. model, system, template) will be passed as top level parameters - other parameters will be sent in options unless options is provided  ## Tests - Test if top level parameters handled properly - Test if parameters that are not top level parameters are handled as options - Test if options is provided, it will be passed as is	8 months ago
shahrin014	bdd90ae2ee	community: Ollama - Pass headers to post request (#15881) ... ## Feature - Set additional headers in constructor - Headers will be sent in post request This feature is useful if deploying Ollama on a cloud service such as hugging face, which requires authentication tokens to be passed in the request header. ## Tests - Test if header is passed - Test if header is not passed	8 months ago
David Křístek	a010f29013	fix: call correct stream method in ollama (#15104) ... Co-authored-by: David Kristek <david@David--MacBook-Pro.local>	8 months ago
shroominic	e6f0cee896	community: Async Ollama + ChatOllama (#15169) ... **Description:** Adding async methods to booth OllamaLLM and ChatOllama to enable async streaming and async .on_llm_new_token callbacks. **Issue:** ChatOllama is not working in combination with an AsyncCallbackManager because the .on_llm_new_token method is not awaited.	9 months ago
chyroc	3a3f880e5a	Patch: improve ollama 404 api error message, fix #15147 (#15156) ... Make this issue more clearly exposed to developers	9 months ago
Lance Martin	42421860bc	Add image support for Ollama (#14713) ... Support [LLaVA](https://ollama.ai/library/llava): * Upgrade Ollama * `ollama pull llava` Ensure compatibility with [image prompt template](https://github.com/langchain-ai/langchain/pull/14263) --------- Co-authored-by: jacoblee93 <jacoblee93@gmail.com>	9 months ago
Bagatur	ed58eeb9c5	community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) ... Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes	9 months ago