ConnectionRefusedError When try to do embedding in RAG

Question

I wanted to write Rag and using llama3 on Google Colab and I used the following code:

#### INDEXING ####

# Load Documents
loader = WebBaseLoader(
    web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("post-content", "post-title", "post-header")
        )
    ),
)
docs = loader.load()

# Split
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)

# Embed
vectorstore = Chroma.from_documents(
    documents=splits, 
    embedding=OllamaEmbeddings(model=local_llm)
)

retriever = vectorstore.as_retriever()

But when it comes to Chroma.from_documents, I get the following error:

ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7c949f725420>: Failed to establish a new connection: [Errno 111] Connection refused'))


During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)

<ipython-input-9-2332286f4c58> in <cell line: 29>()
     27 
     28 # Embed
---> 29 vectorstore = Chroma.from_documents(
     30     documents=splits,
     31     embedding=OllamaEmbeddings(model=local_llm)

/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py in from_documents(cls, documents, embedding, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)
    788         texts = [doc.page_content for doc in documents]
    789         metadatas = [doc.metadata for doc in documents]
--> 790         return cls.from_texts(
    791             texts=texts,
    792             embedding=embedding,

/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py in from_texts(cls, texts, embedding, metadatas, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)
    746                 documents=texts,
    747             ):
--> 748                 chroma_collection.add_texts(
    749                     texts=batch[3] if batch[3] else [],
    750                     metadatas=batch[2] if batch[2] else None,

/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py in add_texts(self, texts, metadatas, ids, **kwargs)
    274         texts = list(texts)
    275         if self._embedding_function is not None:
--> 276             embeddings = self._embedding_function.embed_documents(texts)
    277         if metadatas:
    278             # fill metadatas with empty dicts if somebody

/usr/local/lib/python3.10/dist-packages/langchain_community/embeddings/ollama.py in embed_documents(self, texts)
    209         """
    210         instruction_pairs = [f"{self.embed_instruction}{text}" for text in texts]
--> 211         embeddings = self._embed(instruction_pairs)
    212         return embeddings
    213 

/usr/local/lib/python3.10/dist-packages/langchain_community/embeddings/ollama.py in _embed(self, input)
    197         else:
    198             iter_ = input
--> 199         return [self._process_emb_response(prompt) for prompt in iter_]
    200 
    201     def embed_documents(self, texts: List[str]) -> List[List[float]]:

/usr/local/lib/python3.10/dist-packages/langchain_community/embeddings/ollama.py in <listcomp>(.0)
    197         else:
    198             iter_ = input
--> 199         return [self._process_emb_response(prompt) for prompt in iter_]
    200 
    201     def embed_documents(self, texts: List[str]) -> List[List[float]]:

/usr/local/lib/python3.10/dist-packages/langchain_community/embeddings/ollama.py in _process_emb_response(self, input)
    168             )
    169         except requests.exceptions.RequestException as e:
--> 170             raise ValueError(f"Error raised by inference endpoint: {e}")
    171 
    172         if res.status_code != 200:

ValueError: Error raised by inference endpoint: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7c949f725420>: Failed to establish a new connection: [Errno 111] Connection refused'))

I used: ! pip install langchain and ! pip install chromadb for installing needed libraries.