langchainjs
langchainjs copied to clipboard
hwchase17
@nfcampos This is a half ass paste, but `extractSections` was proven out in some code I have elsewhere so I know that function is good
I'm trying to use the ConversationalRetrievalQAChain with GPT3.5 because it's cheaper than GPT3. But when I try to use `new ChatOpenAI()` as the model for `ConversationalRetrievalQAChain` it gives an error...
Context: I'm trying to stream a response from my Next.js API route to the frontend. I'm trying to use Server-Sent Events to accomplish that, but im getting the following error...
I'm getting the following `axios` error when calling my `ConversationChain` ### Error ``` "Error: Network Error\n at createError (webpack-internal:///(api)/./node_modules/langchain/dist/util/axios-fetch-adapter.js:316:19)\n at getResponse (webpack-internal:///(api)/./node_modules/langchain/dist/util/axios-fetch-adapter.js:197:16)\n at async fetchAdapter (webpack-internal:///(api)/./node_modules/langchain/dist/util/axios-fetch-adapter.js:174:18)" ``` ### Implementation ```...
Builds on config changes in #534 Adds an `llmType` arg to `CreatePromptArgs` for the ZeroShotAgent's `createPrompt` method. This allows us to conveniently set a default prompt for `ZeroShotAgent` based on...
I have been playing around with langchain and langchainjs and noticed that the textsplitters were producing different results. My goal is to align the textsplitters in langchainjs to be more...
```js const callbackManager = CallbackManager.fromHandlers({ handleLLMEnd: async (output: LLMResult) => { console.log(JSON.stringify(output, null, 2)); }, handleLLMError: async (err: Error) => { console.error(err); }, }) ``` ```js new OpenAIChat({ // ...other...
I tried to emulate the langchain python implementation of Pinecone Hybrid Search. I also used the Supabase Hybrid Search implementation as a reference. Thanks @hwchase17 @ericciarla I went with `BertWordPieceTokenizer`...
