Use File Collection with Web Links got error

[halomoan]

I used Google LCGeminiChat and LCGoogleEmbeddings as default and got no errors when do Upload and Index for the web link.

in the chat windows, i got error and in the log it shows the error message on below. How to fix it ? Thanks.

025-03-09 22:41:48 searching in doc_ids ['c5e0f831-5ad6-4753-bf17-623de0aea8ac']
2025-03-09 22:41:48 retrieval_kwargs: dict_keys(['do_extend', 'scope', 'filters'])
2025-03-09 22:41:49 Number of requested results 100 is greater than number of elements in index 4, updating n_results = 4
2025-03-09 22:41:49 Got 4 from vectorstore
2025-03-09 22:41:49 Got 0 from docstore
2025-03-09 22:41:49 Cohere API key not found. Skipping rerankings.
2025-03-09 22:41:49 Got raw 4 retrieved documents
2025-03-09 22:41:49 Traceback (most recent call last):
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/queueing.py", line 575, in process_events
2025-03-09 22:41:49 response = await route_utils.call_process_api(
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/route_utils.py", line 276, in call_process_api
2025-03-09 22:41:49 output = await app.get_blocks().process_api(
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1923, in process_api
2025-03-09 22:41:49 result = await self.call_function(
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 1520, in call_function
2025-03-09 22:41:49 prediction = await utils.async_iteration(iterator)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 663, in async_iteration
2025-03-09 22:41:49 return await iterator.anext()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 656, in anext
2025-03-09 22:41:49 return await anyio.to_thread.run_sync(
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync
2025-03-09 22:41:49 return await get_async_backend().run_sync_in_worker_thread(
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2461, in run_sync_in_worker_thread
2025-03-09 22:41:49 return await future
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 962, in run
2025-03-09 22:41:49 result = context.run(func, *args)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 639, in run_sync_iterator_async
2025-03-09 22:41:49 return next(iterator)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/gradio/utils.py", line 801, in gen_wrapper
2025-03-09 22:41:49 response = next(iterator)
2025-03-09 22:41:49 File "/app/libs/ktem/ktem/pages/chat/init.py", line 1309, in chat_fn
2025-03-09 22:41:49 for response in pipeline.stream(chat_input, conversation_id, chat_history):
2025-03-09 22:41:49 File "/app/libs/ktem/ktem/reasoning/simple.py", line 289, in stream
2025-03-09 22:41:49 docs, infos = self.retrieve(message, history)
2025-03-09 22:41:49 File "/app/libs/ktem/ktem/reasoning/simple.py", line 130, in retrieve
2025-03-09 22:41:49 retriever_docs = retriever_node(text=query)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1097, in call
2025-03-09 22:41:49 raise e from None
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1088, in call
2025-03-09 22:41:49 output = self.fl.exec(func, args, kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/backends/base.py", line 151, in exec
2025-03-09 22:41:49 return run(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 144, in call
2025-03-09 22:41:49 raise e from None
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 141, in call
2025-03-09 22:41:49 _output = self.next_call(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 117, in call
2025-03-09 22:41:49 return self.next_call(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1017, in _runx
2025-03-09 22:41:49 return self.run(*args, **kwargs)
2025-03-09 22:41:49 File "/app/libs/ktem/ktem/index/file/pipelines.py", line 174, in run
2025-03-09 22:41:49 docs = self.vector_retrieval(text=text, top_k=self.top_k, **retrieval_kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1261, in exec
2025-03-09 22:41:49 return child(*args, **kwargs, fl_runstates=fl_runstates)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1097, in call
2025-03-09 22:41:49 raise e from None
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1088, in call
2025-03-09 22:41:49 output = self.fl.exec(func, args, kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/backends/base.py", line 151, in exec
2025-03-09 22:41:49 return run(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 144, in call
2025-03-09 22:41:49 raise e from None
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 141, in call
2025-03-09 22:41:49 _output = self.next_call(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/middleware.py", line 117, in call
2025-03-09 22:41:49 return self.next_call(*args, **kwargs)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/theflow/base.py", line 1017, in _runx
2025-03-09 22:41:49 return self.run(*args, **kwargs)
2025-03-09 22:41:49 File "/app/libs/kotaemon/kotaemon/indices/vectorindex.py", line 274, in run
2025-03-09 22:41:49 linked_thumbnail_docs = self.doc_store.get(list(thumbnail_doc_ids))
2025-03-09 22:41:49 File "/app/libs/kotaemon/kotaemon/storages/docstores/lancedb.py", line 109, in get
2025-03-09 22:41:49 .to_list()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/query.py", line 327, in to_list
2025-03-09 22:41:49 return self.to_arrow().to_pylist()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/query.py", line 1017, in to_arrow
2025-03-09 22:41:49 return self.to_batches().read_all()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/query.py", line 1029, in to_batches
2025-03-09 22:41:49 return self._table._execute_query(query)
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/table.py", line 2138, in _execute_query
2025-03-09 22:41:49 return LOOP.run(self._table._execute_query(query, batch_size))
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/background_loop.py", line 25, in run
2025-03-09 22:41:49 return asyncio.run_coroutine_threadsafe(future, self.loop).result()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 458, in result
2025-03-09 22:41:49 return self.__get_result()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
2025-03-09 22:41:49 raise self._exception
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/table.py", line 2886, in _execute_query
2025-03-09 22:41:49 table = await async_query.to_arrow()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/query.py", line 1567, in to_arrow
2025-03-09 22:41:49 batch_iter = await self.to_batches()
2025-03-09 22:41:49 File "/usr/local/lib/python3.10/site-packages/lancedb/query.py", line 1557, in to_batches
2025-03-09 22:41:49 return AsyncRecordBatchReader(await self._inner.execute(max_batch_length))
2025-03-09 22:41:49 RuntimeError: lance error: LanceError(IO): sql parser error: Expected: an expression, found: ), /root/.cargo/registry/src/index.crates.io-6f17d22bba15001f/lance-datafusion-0.22.0/src/sql.rs:100:8
2025-03-09 22:41:50 User-id: 2c7c1d1926b346e0b00f3ab3d70ca513, can see public conversations: True