From 172499404a07656a22cd2a0587c4d0599928a0ac Mon Sep 17 00:00:00 2001 From: William De Vena <60664495+williamdevena@users.noreply.github.com> Date: Mon, 4 Mar 2024 15:11:48 +0100 Subject: [PATCH] Docs: Updated callbacks/index.mdx adding example on invoke method (#18403) ## PR title Docs: Updated callbacks/index.mdx adding example on runnable methods ## PR message - **Description:** Updated callbacks/index.mdx adding an example on how to pass callbacks to the runnable methods (invoke, batch, ...) - **Issue:** #16379 - **Dependencies:** None --- docs/docs/modules/callbacks/index.mdx | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/docs/docs/modules/callbacks/index.mdx b/docs/docs/modules/callbacks/index.mdx index 3a3ba08cfb8..817e3c07945 100644 --- a/docs/docs/modules/callbacks/index.mdx +++ b/docs/docs/modules/callbacks/index.mdx @@ -135,10 +135,25 @@ Prompt after formatting: ## Where to pass in callbacks -The `callbacks` argument is available on most objects throughout the API (Chains, Models, Tools, Agents, etc.) in two different places: +The `callbacks` are available on most objects throughout the API (Chains, Models, Tools, Agents, etc.) in two different places: -- **Constructor callbacks**: defined in the constructor, e.g. `LLMChain(callbacks=[handler], tags=['a-tag'])`, which will be used for all calls made on that object, and will be scoped to that object only, e.g. if you pass a handler to the `LLMChain` constructor, it will not be used by the Model attached to that chain. -- **Request callbacks**: defined in the `run()`/`apply()` methods used for issuing a request, e.g. `chain.run(input, callbacks=[handler])`, which will be used for that specific request only, and all sub-requests that it contains (e.g. a call to an LLMChain triggers a call to a Model, which uses the same handler passed in the `call()` method). +- **Constructor callbacks**: defined in the constructor, e.g. `LLMChain(callbacks=[handler], tags=['a-tag'])`. In this case, the callbacks will be used for all calls made on that object, and will be scoped to that object only, e.g. if you pass a handler to the `LLMChain` constructor, it will not be used by the Model attached to that chain. +- **Request callbacks**: defined in the 'invoke' method used for issuing a request. In this case, the callbacks will be used for that specific request only, and all sub-requests that it contains (e.g. a call to an LLMChain triggers a call to a Model, which uses the same handler passed in the `invoke()` method). In the `invoke()` method callbacks are passed through the config parameter. +Example with the 'invoke' method (**Note**: the same approach can be used for the `batch`, `ainvoke`, and `abatch` methods.): +```python +handler = StdOutCallbackHandler() +llm = OpenAI() +prompt = PromptTemplate.from_template("1 + {number} = ") + +config = { + 'callbacks' : [handler] +} + +chain = prompt | chain +chain.invoke({"number":2}, config=config) +``` + +**Note:** `chain = prompt | chain` is equivalent to `chain = LLMChain(llm=llm, prompt=prompt)` (check [LangChain Expression Language (LCEL) documentation](https://python.langchain.com/docs/expression_language/) for more details) The `verbose` argument is available on most objects throughout the API (Chains, Models, Tools, Agents, etc.) as a constructor argument, e.g. `LLMChain(verbose=True)`, and it is equivalent to passing a `ConsoleCallbackHandler` to the `callbacks` argument of that object and all child objects. This is useful for debugging, as it will log all events to the console.