Gemini API：调用.generate_content（提示）时出错

Question

我对法学硕士的开发还很陌生。 我正在尝试使用 google 嵌入在 Streamlit 中使用 Gemini 的 API 编写一个基于 RAG 的应用程序。 该应用程序的目标是在回答用户的请求时从 PDF（这是我的 RAG 的知识库）中检索信息。 我使用 Streamlit 进行接口，使用 FAISS 进行矢量 DB。

这是我拨打电话的代码：

# Get the user's question 
question = st.chat_input("Ask here")

# Handle the user's question
if question:
    vectordb = st.session_state.get("vectordb", None)
    if not vectordb:
        with st.message("assistant"):
            st.write("You need to provide a PDF")
            st.stop()

    # Search the vectordb for similar content to the user's question
    search_results = vectordb.similarity_search(question, k=3)
    # sources of result
    pdf_extract = "/n ".join([result.page_content for result in search_results])

    # Update the prompt with the pdf extract
    prompt[0] = {
        "role": "system",
        "content": prompt_template.format(pdf_extract=pdf_extract),
    }

    # Add the user's question to the prompt and display it
    prompt.append({"role": "user", "content": question})

    with st.chat_message("user"):
        st.write(question)

    # Display an empty assistant message while waiting for the response
    with st.chat_message("assistant"):
        botmsg = st.empty()

    response = []
    result = ""
    
    response = model.generate_content(prompt)
    botmsg.write(result)

型号是

model = genai.GenerativeModel('gemini-pro')

设置 API 密钥等后。 我没有包含这部分代码，因为我认为与该问题无关。

当我执行脚本时，我遇到此错误：

KeyError: "Could not recognize the intended type of the `dict`. A `Content` should have a 'parts' key. A `Part` should have a 'inline_data' or a 'text' key. A `Blob` should have 'mime_type' and 'data' keys. Got keys: ['role', 'content']"

我之前的代码使用了 openAI 的 API 和 OpenAI Embedding 模型，并且它有效：

   for chunk in st.session_state.chat.send_message(prompt):
        text = chunk.choices[0].get("delta", {}).get("content")
        if text is not None:
            response.append(text)
            result = "".join(response).strip()
            botmsg.write(result)

Gemini 对应的代码是这样的：（出现在前面的代码片段中）

    response = model.generate_content(prompt)
    botmsg.write(result)

我该如何解决这个问题？我不明白这个错误，我很确定代码中缺少一些东西。 如果有人遇到过这种情况，或者知道为什么会发生这种情况，我将不胜感激。

提前谢谢您。

Answer 1

这是一个帮助您入门的基本测试脚本。希望这有帮助:)

from vertexai.preview.generative_models import GenerativeModel, GenerationConfig, Part, Content, HarmCategory, HarmBlockThreshold, ResponseBlockedError


class Gemini:
    
    def __init__(self, streaming: bool = False):
    
        # Load the model
        self.model = GenerativeModel("gemini-pro")
        self.streaming = streaming

        # Generation config
        self.config = GenerationConfig(
            temperature=0.0,
            top_p=0.8,
            top_k=32,
            candidate_count=1,
            max_output_tokens=2048,
        )

        # Safety config
        self.safety_config = {   
            HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
            HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_ONLY_HIGH,
            HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
            HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_ONLY_HIGH,
            HarmCategory.HARM_CATEGORY_UNSPECIFIED: HarmBlockThreshold.BLOCK_ONLY_HIGH,
        }
        

    def invoke(self, prompt: dict):
        
        # Format the user input as a Content object
        user_input = Content(
            role="user", 
            parts=[
                Part.from_text(prompt["input"]),
            ]
        )
        
        response = self.model.generate_content(
            contents=user_input,
            generation_config=self.config,
            safety_settings=self.safety_config,
            stream=self.streaming, 
            tools=[]
        )
        
        return response
    

# Initialise the model
model = Gemini(streaming=False)

# Test the model
generated_response = model.invoke({"input": "ELI5 in 50 words or less: Why is the sky blue?"})


# Print the response with basic exception handling
try:
    if hasattr(generated_response.candidates[0].content.parts[0], 'text'):
        print(generated_response.candidates[0].content.parts[0].text)
except ValueError as e:
    print("An error occured: ", e)