Erro using Clickhouse to create a vectorStore "Annoy index second argument must be String."

[viniciuscr]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain_text_splitters import CharacterTextSplitter
from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
from langchain_community.document_loaders import PyMuPDFLoader
from langchain_community.vectorstores import Clickhouse, ClickhouseSettings

file = "some_file.pdf"
loader = PyMuPDFLoader(file)
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = FastEmbedEmbeddings()

settings = ClickhouseSettings(table="some_table")
docsearch = Clickhouse.from_documents(docs, embeddings, config=settings)

I am using clickhouse suggested in the docks

! docker run -d -p 8123:8123 -p 9005:9000 --name langchain-clickhouse-server --ulimit nofile=262144:262144 clickhouse/clickhouse-server:23.4.2.11

Error Message and Stack Trace (if applicable)

---

DatabaseError Traceback (most recent call last)
Cell In[28], line 7
6 settings = ClickhouseSettings(table="some_table")
----> 7 docsearch = Clickhouse.from_documents(docs, embeddings, config=settings)

File ~/.local/lib/python3.12/site-packages/langchain_core/vectorstores.py:550, in VectorStore.from_documents(cls, documents, embedding, **kwargs)
548 texts = [d.page_content for d in documents]
549 metadatas = [d.metadata for d in documents]
--> 550 return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)

File ~/micromamba/envs/langchain/lib/python3.12/site-packages/langchain_community/vectorstores/clickhouse.py:403, in Clickhouse.from_texts(cls, texts, embedding, metadatas, config, text_ids, batch_size, **kwargs)
376 @classmethod
377 def from_texts(
378 cls,
(...)
385 **kwargs: Any,
386 ) -> Clickhouse:
387 """Create ClickHouse wrapper with existing texts
388
389 Args:
(...)
401 ClickHouse Index
402 """
--> 403 ctx = cls(embedding, config, **kwargs)
404 ctx.add_texts(texts, ids=text_ids, batch_size=batch_size, metadatas=metadatas)
405 return ctx

File ~/micromamba/envs/langchain/lib/python3.12/site-packages/langchain_community/vectorstores/clickhouse.py:205, in Clickhouse.init(self, embedding, config, **kwargs)
200 if self.config.index_type:
201 # Enable index
202 self.client.command(
203 f"SET allow_experimental_{self.config.index_type}_index=1"
204 )
--> 205 self.client.command(self.schema)

File ~/micromamba/envs/langchain/lib/python3.12/site-packages/clickhouse_connect/driver/httpclient.py:336, in HttpClient.command(self, cmd, parameters, data, settings, use_database, external_data)
333 params.update(self._validate_settings(settings or {}))
335 method = 'POST' if payload or fields else 'GET'
--> 336 response = self._raw_request(payload, params, headers, method, fields=fields)
337 if response.data:
338 try:

File ~/micromamba/envs/langchain/lib/python3.12/site-packages/clickhouse_connect/driver/httpclient.py:438, in HttpClient._raw_request(self, data, params, headers, method, retries, stream, server_wait, fields, error_handler)
436 error_handler(response)
437 else:
--> 438 self._error_handler(response)

File ~/micromamba/envs/langchain/lib/python3.12/site-packages/clickhouse_connect/driver/httpclient.py:362, in HttpClient._error_handler(self, response, retried)
360 err_msg = common.format_error(err_content.decode(errors='backslashreplace'))
361 err_str = f':{err_str}\n {err_msg}'
--> 362 raise OperationalError(err_str) if retried else DatabaseError(err_str) from None

DatabaseError: :HTTPDriver for http://localhost:8123/ returned response code 500)
Code: 80. DB::Exception: Annoy index second argument must be String. (INCORRECT_QUERY) (version 23.4.2.11 (official build))

Description

I'm trying to load a pdf and search it using Clickhouse

System Info

System Information

OS: Linux
OS Version: #1 SMP PREEMPT_DYNAMIC Thu May 2 18:59:06 UTC 2024
Python Version: 3.12.3 | packaged by conda-forge | (main, Apr 15 2024, 18:38:13) [GCC 12.3.0]

Package Information

langchain_core: 0.1.52
langchain: 0.1.20
langchain_community: 0.0.38
langsmith: 0.1.59
langchain_chroma: 0.1.1
langchain_openai: 0.1.7
langchain_text_splitters: 0.0.2

Packages not installed (Not Necessarily a Problem)

The following packages were not found:

langgraph
langserve

[MRzhanghaoran]

Longchain 962 sex erro to [sudo place->ls]
utf-8 cud:99023;
That was long chains exit the postation will be erro.