How can implement function calling from OpenAI with Langchain Retrieval

Question

I'm implementing /api/chat, which uses OpenAI, LangChain and Pinecone store vector. It looks to work fine when OpenAI response text message, but when OpenAI response function call and then text is empty. And the API not show anything in response. Please read the code to get more details.

export const POST = async (req: Request) => {
  try {
    const body = await req.json()
    const messages = body.messages ?? []
    const previousMessages = messages.slice(0, -1)
    const currentMessageContent = messages[messages.length - 1].content

    await pineconeClient.init({
      apiKey: process.env.PINECONE_API_KEY as string,
      environment: process.env.PINECONE_ENVIRONMENT as string,
    })

    const pineconeIndex = pineconeClient.Index('documents')

    const llm = new ChatOpenAI({
      modelName: 'gpt-4-0613',
      streaming: true,
      openAIApiKey: process.env.OPENAI_API_KEY as string,
      maxTokens: 2048,
      temperature: 0.2,
      presencePenalty: 0,
      verbose: true,
    }).bind({
      functions: [getWeather],
    })

    const vectorStore = await PineconeStore.fromExistingIndex(new OpenAIEmbeddings(), {
      pineconeIndex: pineconeIndex,
      filter: {
        personaId: { $eq: body.personaId },
      },
    })

    const retriever = vectorStore.asRetriever()

    const standaloneQuestionChain = RunnableSequence.from([
      {
        question: (input: ConversationalRetrievalQAChainInput) => input.question,
        chat_history: (input: ConversationalRetrievalQAChainInput) => formatVercelMessages(input.chat_history),
      },
      condenseQuestionPrompt,
      llm,
      new StringOutputParser(),
    ])

    const answerChain = RunnableSequence.from([
      {
        context: retriever.pipe(combineDocumentsFn),
        question: new RunnablePassthrough(),
      },
      answerPrompt,
      llm,
      new BytesOutputParser(),
    ])

    const conversationalRetrievalQAChain = standaloneQuestionChain.pipe(answerChain)

    const stream = await conversationalRetrievalQAChain.stream({
      question: currentMessageContent,
      chat_history: previousMessages,
    })

    // Instantiate the StreamData. It works with all API providers.

    return new StreamingTextResponse(stream)
  } catch (error: any) {
    console.error(error)
    return NextResponse.json(null, { status: 500 })
  }
}

Test success with text response

curl --location 'http://localhost:3000/api/v2/chat' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "role": "user",
            "content": "hi"
        }
    ]
}'

Text fail with function call response

curl --location 'http://localhost:3000/api/v2/chat' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "role": "user",
            "content": "current weather at Ho Chi Minh city"
        }
    ]
}'

Here is the logs from LLM

web:dev: [llm/start] [1:llm:ChatOpenAI] Entering LLM run with input: {
web:dev:   "messages": [
web:dev:     [
web:dev:       {
web:dev:         "lc": 1,
web:dev:         "type": "constructor",
web:dev:         "id": [
web:dev:           "langchain",
web:dev:           "schema",
web:dev:           "HumanMessage"
web:dev:         ],
web:dev:         "kwargs": {
web:dev:           "content": "\nUse the following pieces of context to answer the question at the end.\nKeep your answer in first person not third person. Don't say \"I don't know\", just say content of the Predict Message.\n\n.\nModern \nscience \nsays: \nThe sun is the past, the earth \nis the present, \nthe\nmoon \nis the future. \nFrom \nan incandescent \nmass we have originated, \nand into\na frozen\n mass \nwe shall turn. Merciless \nis the law of nature, \nand rapidly \nand\nirresistibly \nwe  are  drawn \nto  our  doom. \nLord \nKelvin, \nin  his  profound\nmeditations, \nallows \nus only a short \nspan of life, something \nlike six million\nyears, \nafter which \ntime the sun’s bright \nlight will have ceased \nto shine, \nand\nits life-giving \nheat will have ebbed \naway, and our own earth \nwill be a lump\nof  ice,  hurrying \non  through \nthe  eternal \nnight. \nBut  do  not  let  us  despair\n.\nThere \nwill still be left upon \nit a glimmering \nspark \nof life, and there \nwill be a\nchance \nto kindle\n a new fire on some distant \nstar. This wonderful \npossibility\nseems, \nindeed, \nto  exist, \njudging \nfrom \nProfessor \nDewar\n’s  beautiful\nexperiments \nwith liquid \nair, which show \nthat germs \nof organic life are not\ndestroyed \nby  cold,\n\nSouth \nAfrica\n)  no  lightning \nstrokes \noccurred \nafter \nthe\npointed \nrods were \ninstalled, \naltho \nthe storms \nwere \nas frequent \nas before.\nExperience \nhas shown \nthat just the opposite \nis true. A modern \ncity like New\nYork, presenting \ninnumerable \nsharp points \nand projections \nin good contact\n\nChapter Eight\n\nChapter Eight // i.e the chunks of text retrieved deemed to be moset semantically\n          // relevant to our question\nQuestion: What is the current weather in Ho Chi Minh city? // i.e our actualy question\nHelpful Answer:\n",
web:dev:           "additional_kwargs": {}
web:dev:         }
web:dev:       }
web:dev:     ]
web:dev:   ]
web:dev: }
web:dev: [llm/end] [1:llm:ChatOpenAI] [2.93s] Exiting LLM run with output: {
web:dev:   "generations": [
web:dev:     [
web:dev:       {
web:dev:         "text": "",
web:dev:         "generationInfo": {
web:dev:           "prompt": 0,
web:dev:           "completion": 0
web:dev:         },
web:dev:         "message": {
web:dev:           "lc": 1,
web:dev:           "type": "constructor",
web:dev:           "id": [
web:dev:             "langchain",
web:dev:             "schema",
web:dev:             "AIMessageChunk"
web:dev:           ],
web:dev:           "kwargs": {
web:dev:             "content": "",
web:dev:             "additional_kwargs": {
web:dev:               "function_call": {
web:dev:                 "name": "getWeather",
web:dev:                 "arguments": "{\n  \"location\": \"Ho Chi Minh city\"\n}"
web:dev:               }
web:dev:             }
web:dev:           }
web:dev:         }
web:dev:       }
web:dev:     ]
web:dev:   ]
web:dev: }

• can response function call from OpenAI via Langchain provider same with text response