# ChatOllama > **Class** in `@langchain/ollama` 📖 [View in docs](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama) Ollama chat model integration. Setup: Install `@langchain/ollama` and the Ollama app. ```bash npm install @langchain/ollama export OLLAMA_BASE_URL="http://127.0.0.1:11434" # Optional; defaults to http://127.0.0.1:11434 if not set ``` ## [Constructor args](https://api.js.langchain.com/classes/_langchain_ollama.ChatOllama.html#constructor) ## [Runtime args](https://api.js.langchain.com/interfaces/_langchain_ollama.ChatOllamaCallOptions.html) Runtime args can be passed as the second argument to any of the base runnable methods `.invoke`. `.stream`, `.batch`, etc. They can also be passed via `.withConfig`, or the second arg in `.bindTools`, like shown in the examples below: ```typescript // When calling `.withConfig`, call options should be passed via the first argument const llmWithArgsBound = llm.withConfig({ stop: ["\n"], }); // When calling `.bindTools`, call options should be passed via the second argument const llmWithTools = llm.bindTools( [...], { stop: ["\n"], } ); ``` ## Examples
Instantiate ```typescript import { ChatOllama } from '@langchain/ollama'; const llm = new ChatOllama({ model: "llama-3.1:8b", temperature: 0, // other params... }); ```

Invoking ```typescript const input = `Translate "I love programming" into French.`; // Models also accept a list of chat messages or a formatted prompt const result = await llm.invoke(input); console.log(result); ``` ```txt AIMessage { "content": "The translation of \"I love programming\" into French is:\n\n\"J'adore programmer.\"", "additional_kwargs": {}, "response_metadata": { "model": "llama3.1:8b", "created_at": "2024-08-12T22:12:23.09468Z", "done_reason": "stop", "done": true, "total_duration": 3715571291, "load_duration": 35244375, "prompt_eval_count": 19, "prompt_eval_duration": 3092116000, "eval_count": 20, "eval_duration": 585789000 }, "tool_calls": [], "invalid_tool_calls": [], "usage_metadata": { "input_tokens": 19, "output_tokens": 20, "total_tokens": 39 } } ```

Streaming Chunks ```typescript for await (const chunk of await llm.stream(input)) { console.log(chunk); } ``` ```txt AIMessageChunk { "content": "The", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } AIMessageChunk { "content": " translation", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } AIMessageChunk { "content": " of", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } AIMessageChunk { "content": " \"", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } AIMessageChunk { "content": "I", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } ... AIMessageChunk { "content": "", "additional_kwargs": {}, "response_metadata": {}, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [] } AIMessageChunk { "content": "", "additional_kwargs": {}, "response_metadata": { "model": "llama3.1:8b", "created_at": "2024-08-12T22:13:22.22423Z", "done_reason": "stop", "done": true, "total_duration": 8599883208, "load_duration": 35975875, "prompt_eval_count": 19, "prompt_eval_duration": 7918195000, "eval_count": 20, "eval_duration": 643569000 }, "tool_calls": [], "tool_call_chunks": [], "invalid_tool_calls": [], "usage_metadata": { "input_tokens": 19, "output_tokens": 20, "total_tokens": 39 } } ```

Bind tools ```typescript import { z } from 'zod'; const GetWeather = { name: "GetWeather", description: "Get the current weather in a given location", schema: z.object({ location: z.string().describe("The city and state, e.g. San Francisco, CA") }), } const GetPopulation = { name: "GetPopulation", description: "Get the current population in a given location", schema: z.object({ location: z.string().describe("The city and state, e.g. San Francisco, CA") }), } const llmWithTools = llm.bindTools([GetWeather, GetPopulation]); const aiMsg = await llmWithTools.invoke( "Which city is hotter today and which is bigger: LA or NY?" ); console.log(aiMsg.tool_calls); ``` ```txt [ { name: 'GetWeather', args: { location: 'Los Angeles, CA' }, id: '49410cad-2163-415e-bdcd-d26938a9c8c5', type: 'tool_call' }, { name: 'GetPopulation', args: { location: 'New York, NY' }, id: '39e230e4-63ec-4fae-9df0-21c3abe735ad', type: 'tool_call' } ] ```

Structured Output ```typescript import { z } from 'zod'; const Joke = z.object({ setup: z.string().describe("The setup of the joke"), punchline: z.string().describe("The punchline to the joke"), rating: z.number().optional().describe("How funny the joke is, from 1 to 10") }).describe('Joke to tell user.'); const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" }); const jokeResult = await structuredLlm.invoke("Tell me a joke about cats"); console.log(jokeResult); ``` ```txt { punchline: 'Why did the cat join a band? Because it wanted to be the purr-cussionist!', rating: 8, setup: 'A cat walks into a music store and asks the owner...' } ```

Usage Metadata ```typescript const aiMsgForMetadata = await llm.invoke(input); console.log(aiMsgForMetadata.usage_metadata); ``` ```txt { input_tokens: 19, output_tokens: 20, total_tokens: 39 } ```

Response Metadata ```typescript const aiMsgForResponseMetadata = await llm.invoke(input); console.log(aiMsgForResponseMetadata.response_metadata); ``` ```txt { model: 'llama3.1:8b', created_at: '2024-08-12T22:17:42.274795Z', done_reason: 'stop', done: true, total_duration: 6767071209, load_duration: 31628209, prompt_eval_count: 19, prompt_eval_duration: 6124504000, eval_count: 20, eval_duration: 608785000 } ```

## Signature ```javascript class ChatOllama ``` ## Extends - `BaseChatModel` ## Implements - `ChatOllamaInput` ## Constructors - [`constructor()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/constructor) ## Properties - `baseUrl` - `cache` - `callbacks` - `caller` - `checkOrPullModel` - `client` - `disableStreaming` - `embeddingOnly` - `f16Kv` - `format` - `frequencyPenalty` - `keepAlive` - `lc_kwargs` - `lc_namespace` - `lc_runnable` - `lc_serializable` - `logitsAll` - `lowVram` - `mainGpu` - `metadata` - `mirostat` - `mirostatEta` - `mirostatTau` - `model` - `name` - `numa` - `numBatch` - `numCtx` - `numGpu` - `numKeep` - `numPredict` - `numThread` - `outputVersion` - `ParsedCallOptions` - `penalizeNewline` - `presencePenalty` - `repeatLastN` - `repeatPenalty` - `seed` - `streaming` - `tags` - `temperature` - `tfsZ` - `think` - `topK` - `topP` - `typicalP` - `useMlock` - `useMmap` - `verbose` - `vocabOnly` - `callKeys` - `lc_aliases` - `lc_attributes` - `lc_id` - `lc_secrets` - `lc_serializable_keys` - `profile` ## Methods - [`_addVersion()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_addVersion) - [`_batchWithConfig()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_batchWithConfig) - [`_callWithConfig()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_callWithConfig) - [`_combineLLMOutput()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_combineLLMOutput) - [`_filterInvocationParamsForTracing()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_filterInvocationParamsForTracing) - [`_generate()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_generate) - [`_generateCached()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_generateCached) - [`_getOptionsList()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_getOptionsList) - [`_getSerializedCacheKeyParametersForCall()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_getSerializedCacheKeyParametersForCall) - [`_identifyingParams()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_identifyingParams) - [`_llmType()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_llmType) - [`_modelType()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_modelType) - [`_separateRunnableConfigFromCallOptions()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_separateRunnableConfigFromCallOptions) - [`_separateRunnableConfigFromCallOptionsCompat()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_separateRunnableConfigFromCallOptionsCompat) - [`_streamChatModelEvents()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_streamChatModelEvents) - [`_streamIterator()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_streamIterator) - [`_streamLog()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_streamLog) - [`_streamResponseChunks()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_streamResponseChunks) - [`_transformStreamWithConfig()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_transformStreamWithConfig) - [`assign()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/assign) - [`asTool()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/asTool) - [`batch()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/batch) - [`bindTools()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/bindTools) - [`generate()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/generate) - [`generatePrompt()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/generatePrompt) - [`getGraph()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/getGraph) - [`getLsParams()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/getLsParams) - [`getLsParamsWithDefaults()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/getLsParamsWithDefaults) - [`getName()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/getName) - [`getNumTokens()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/getNumTokens) - [`invocationParams()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/invocationParams) - [`invoke()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/invoke) - [`pick()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/pick) - [`pipe()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/pipe) - [`pull()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/pull) - [`serialize()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/serialize) - [`stream()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/stream) - [`streamEvents()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/streamEvents) - [`streamLog()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/streamLog) - [`streamV2()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/streamV2) - [`toJSON()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/toJSON) - [`toJSONNotImplemented()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/toJSONNotImplemented) - [`transform()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/transform) - [`withConfig()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/withConfig) - [`withFallbacks()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/withFallbacks) - [`withListeners()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/withListeners) - [`withRetry()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/withRetry) - [`withStructuredOutput()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/withStructuredOutput) - [`_convertInputToPromptValue()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/_convertInputToPromptValue) - [`deserialize()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/deserialize) - [`isRunnable()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/isRunnable) - [`lc_name()`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama/lc_name) --- [View source on GitHub](https://github.com/langchain-ai/langchainjs/blob/c5e896270207fcd3bdf1d1877e80b94c72d35f1e/libs/providers/langchain-ollama/src/chat_models.ts#L420)