def get_data(API_key, Movie_ID, max_retries=5):
    """
函數以JSON格式提取感興趣的電影的詳細信息。

    parameters:
    API_key (str): Your API key for TMBD
    Movie_ID (str): TMDB id for film of interest

    returns:
    dict: JSON格式的字典，包含您的電影的所有細節
興趣
    """

    query = 'https://api.themoviedb.org/3/movie/' + Movie_ID + \
        '?api_key='+API_key + '&append_to_response=keywords,' + \
            'watch/providers,credits'
    for i in range(max_retries):
        response = requests.get(query)
        if response.status_code == 429:
            # If the response was a 429, wait and then try again
            print(
                f"Request limit reached. Waiting and retrying ({i+1}/{
                    max_retries})")
            time.sleep(2 ** i)  # Exponential backoff
        else:
            dict = response.json()
            return dict

credits = dict['credits']
    actor_list, director_list = [], []

# 分析演員表
cast = credits['cast']
NUM_ACTORS = 5
for member in cast[:NUM_ACTORS]:
    actor_list.append(member["name"])

# 分析劇組
crew = credits['crew']
for member in crew:
    if member['job'] == 'Director':
        director_list.append(member["name"])

actor_str = ', '.join(list(set(actor_list)))
director_str = ', '.join(list(set(director_list)))

# 從所有csv文件加載數據
loader = DirectoryLoader(
    path="./data",
    glob="*.csv",
    loader_cls=CSVLoader,
    show_progress=True)

docs = loader.load()

metadata_field_info = [
    AttributeInfo(
        name="Title", description="The title of the movie", type="string"),
    AttributeInfo(name="Runtime (minutes)",
                  description="The runtime of the movie in minutes", type="integer"),
    AttributeInfo(name="Language",
                  description="The language of the movie", type="string"),
    ...
]

for doc in docs:
    #將page_content字符串解析到字典中
    page_content_dict = dict(line.split(": ", 1)
                             for line in doc.page_content.split("\n") if ": " in line)
    
    doc.page_content = 'Overview: ' + page_content_dict.get(
        'Overview') + '. Keywords: ' + page_content_dict.get('Keywords')
    doc.metadata = {field.name: page_content_dict.get(
        field.name) for field in metadata_field_info}

    #將字段從字符串轉換為字符串列表
    for field in fields_to_convert_list:
        convert_to_list(doc, field)      

    # 將字段從字符串轉換為整數
    for field in fields_to_convert_int:
        convert_to_int(doc, field)

# 如果尚未創建索引，則取消注釋
pc.create_index(
    name=PINECONE_INDEX_NAME,
    dimension=1536,
    metric="cosine",
    spec=PodSpec(
        environment="gcp-starter"
    )
)

# 目標索引和檢查狀態
pc_index = pc.Index(PINECONE_INDEX_NAME)
print(pc_index.describe_index_stats())

embeddings = OpenAIEmbeddings(model='text-embedding-ada-002')

vectorstore = PineconeVectorStore(
    pc_index, embeddings
)

# 創建記錄管理器
namespace = f"pinecone/{PINECONE_INDEX_NAME}"
record_manager = SQLRecordManager(
    namespace, db_url="sqlite:///record_manager_cache.sql"
)

record_manager.create_schema()

# 將文檔上載到松果網站
index(docs, record_manager, vectorstore,
      cleanup="full", source_id_key="Website")

document_content_description = "Brief overview of a movie, along with keywords"

        # 定義允許的比較器列表
        allowed_comparators = [
            "$eq",  # Equal to (number, string, boolean)
            "$ne",  # Not equal to (number, string, boolean)
            "$gt",  # Greater than (number)
            "$gte",  # Greater than or equal to (number)
            "$lt",  # Less than (number)
            "$lte",  # Less than or equal to (number)
            "$in",  # In array (string or number)
            "$nin",  # Not in array (string or number)
            "$exists", # Has the specified metadata field (boolean)
        ]

        examples = [
            (
                "Recommend some films by Yorgos Lanthimos.",
                {
                    "query": "Yorgos Lanthimos",
                    "filter": 'in("Directors", ["Yorgos Lanthimos]")',
                },
            ),
            (
                "Films similar to Yorgos Lanthmios movies.",
                {
                    "query": "Dark comedy, absurd, Greek Weird Wave",
                    "filter": 'NO_FILTER',
                },
            ),
            ...
        ]

        metadata_field_info = [
            AttributeInfo(
                name="Title", description="The title of the movie", type="string"),
            AttributeInfo(name="Runtime (minutes)",
                          description="The runtime of the movie in minutes", type="integer"),
            AttributeInfo(name="Language",
                          description="The language of the movie", type="string"),
            ...
        ]

        constructor_prompt = get_query_constructor_prompt(
            document_content_description,
            metadata_field_info,
            allowed_comparators=allowed_comparators,
            examples=examples,
        )

        output_parser = StructuredQueryOutputParser.from_components()
        query_constructor = constructor_prompt | query_model | output_parser

        retriever = SelfQueryRetriever(
            query_constructor=query_constructor,
            vectorstore=vectorstore,
            structured_query_translator=PineconeTranslator(),
            search_kwargs={'k': 10}
        )

chat_model = ChatOpenAI(
    model=SUMMARY_MODEL_NAME,
    temperature=0,
    streaming=True,
)

prompt = ChatPromptTemplate.from_messages(
    [
        (
            'system',
            """
            Your goal is to recommend films to users based on their 
            query and the retrieved context. If a retrieved film doesn't seem 
            relevant, omit it from your response. If your context is empty
            or none of the retrieved films are relevant, do not recommend films
            , but instead tell the user you couldn't find any films 
            that match their query. Aim for three to five film recommendations,
            as long as the films are relevant. You cannot recommend more than 
            five films. Your recommendation should be relevant, original, and 
            at least two to three sentences long.
            
            YOU CANNOT RECOMMEND A FILM IF IT DOES NOT APPEAR IN YOUR 
            CONTEXT.

            # TEMPLATE FOR OUTPUT
            - **Title of Film**:
                - Runtime:
                - Release Year:
                - Streaming:
                - (Your reasoning for recommending this film)
            
            Question: {question} 
            Context: {context} 
            """
        ),
    ]
)

def format_docs(docs):
    return "\n\n".join(f"{doc.page_content}\n\nMetadata: {doc.metadata}" for doc in docs)

# Create a chatbot Question & Answer chain from the retriever
rag_chain_from_docs = (
    RunnablePassthrough.assign(
        context=(lambda x: format_docs(x["context"])))
    | prompt
    | chat_model
    | StrOutputParser()
)

rag_chain_with_source = RunnableParallel(
    {"context": retriever, "question": RunnablePassthrough()}
).assign(answer=rag_chain_from_docs)

for chunk in rag_chain_with_source.stream(query):
    for key in chunk:
        if key == 'answer':
            yield chunk[key]