"TypeError in embed_documents: Nested Embedding Structure (List[List[float]]) Causes Failure in LlamaCppEmbeddings with langchain-community v0.3.12"

[Forgotten-Forever]

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.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import LlamaCppEmbeddings

Load a text file

loader = TextLoader("./docs/raw.txt")
docs = loader.load()

Split text into smaller chunks

text_splitter = CharacterTextSplitter(chunk_size=10, chunk_overlap=0)
texts = text_splitter.split_documents(docs)

Prepare input for embedding

embeddings = LlamaCppEmbeddings(model_path="./models/llama-1B-q8_0.gguf")
_texts = [doc.page_content for doc in texts]

Attempt to embed documents

embedded_texts = embeddings.embed_documents(_texts)

print(len(embedded_texts), len(embedded_texts[0]))

Error Message and Stack Trace (if applicable)

[list(map(float, e["embedding"])) for e in embeddings["data"]]
PyDev console: starting.
Traceback (most recent call last):
File "D:\Pycharm\PyCharm Community Edition 2023.2.3\plugins\python-ce\helpers\pydev_pydevd_bundle\pydevd_exec2.py", line 3, in Exec
exec(exp, global_vars, local_vars)
File "", line 1, in
File "", line 1, in
TypeError: float() argument must be a string or a real number, not 'list'

Description

When using langchain-community's LlamaCppEmbeddings with llama-cpp-python, the embed_documents method fails with a TypeError when processing certain input texts. The issue arises because the returned embedding structure from llama_cpp is unexpectedly nested (List[List[float]]), but embed_documents assumes a flat structure (List[float]).

Environment
Python version: 3.10
langchain-community: v0.3.12
llama-cpp-python: v0.3.5
Model: llama-1B-q8_0.gguf --> llama-3.2-1B

Expected Behavior
The embed_documents method should process the embeddings correctly, regardless of whether the returned embedding structure is flat (List[float]) or nested (List[List[float]]).

Actual Behavior
The embed_documents method assumes the returned embeddings are flat (List[float]), but when the structure is nested (List[List[float]]), it fails with the following error:
TypeError: float() argument must be a string or a real number, not 'list'

System Info

(gpt310free) PS D:\Temp\Gpt> python -m langchain_core.sys_info

System Information

OS: Windows
OS Version: 10.0.19045
Python Version: 3.10.13 | packaged by Anaconda, Inc. | (main, Sep 11 2023, 13:24:38) [MSC v.1916 64 bit (AMD64)]

Package Information

langchain_core: 0.3.25
langchain: 0.3.12
langchain_community: 0.3.12
langsmith: 0.1.147
langchain_text_splitters: 0.3.3

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.10
async-timeout: 4.0.3
dataclasses-json: 0.6.7
httpx: 0.27.0
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.25.2
orjson: 3.10.12
packaging: 24.0
pydantic: 2.10.3
pydantic-settings: 2.7.0
PyYAML: 6.0.1
requests: 2.30.0
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
tenacity: 8.2.3
typing-extensions: 4.12.2

[keenborder786]

@Forgotten-Forever fixed in the above PR