index = GPTSimpleVectorIndex.from_documents(file_doc) line?@app.route("/query", methods=["GET"])
def query_index():
global index
query_text = request.args.get("text", None)
if query_text is None:
return "No text found, please include a ?text=blah parameter in the URL", 400
query_engine = index.as_query_engine(service_context=service_context, streaming=True)
def response_stream(response):
def generate():
for text in response:
yield text
return generate
return stream_with_context(response_stream(query_engine.query(query_text).response_gen))response = graph.query(
query_str=query_str,
query_configs=query_configs,
service_context=service_context_chatgpt
) response = graph.query(
^^^^^^^^^^^^
TypeError: BaseQueryEngine.query() got an unexpected keyword argument 'query_str'save_to_string has been replaced by StorageContext. How would I save it to S3? from llama_index import StorageContext, load_index_from_storage # rebuild storage context storage_context = StorageContext.from_defaults(persist_dir="./storage") # load index index = load_index_from_storage(storage_context)
The new context does not provide any additional information, so the original answer remains the same. so it messes it up when I try loading the response into a JSON file. Do you know how to remove this additional commentary it keeps returning?build_graph_from_documents on them. What's the best way of doing this? I tried using the S3Reader but it, unfortunately, kept throwing an error.Error querying graph: Invalid template: Context information is below.
---------------------
{context_str
}
------------
...insert prompt here...
variables do not match the required input_variables: ['context_str'
]query_str as args when calling the graph object. For example: response = graph.query(query_str=query_str, query_configs=query_configs)max_tokens limit, the output still keeps getting cut off. Does anyone know what might be causing this?`llama-index through pip?requirements.txt:openai==0.26.5 tiktoken==0.2.0 wheel===0.38.4 langchain==0.0.94 llama-index==0.4.13
--platform=linux/x86_64 to my Dockerfile but it didn't change anything.