I am using this link to learn langhain and pinecone. Just copy pasted the code as bellow:
MY CODE:
import getpass
import os
import time
from pinecone import Pinecone
os.environ['HF_TOKEN'] = os.getenv('HF_TOKEN')
pinecone_api_key = os.environ.get("PINECONE_API_KEY")
pc = Pinecone(api_key=pinecone_api_key)
index_name = "langchain-pinecone-learning" # change if desired
existing_indexes = [index_info["name"] for index_info in pc.list_indexes()]
if index_name not in existing_indexes:
pc.create_index(
name=index_name,
dimension=3072,
metric="cosine",
spec=ServerlessSpec(cloud="aws", region="us-east-1"),
)
while not pc.describe_index(index_name).status["ready"]:
time.sleep(1)
index = pc.Index(index_name)
index
embeddings=(
OllamaEmbeddings(model="gemma:2b") ##by default it ues llama2
)
from langchain_pinecone import PineconeVectorStore
vector_store = PineconeVectorStore(index=index, embedding=embeddings)
vector_store
from uuid import uuid4
from langchain_core.documents import Document
document_1 = Document(
page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
metadata={"source": "tweet"},
)
document_2 = Document(
page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
metadata={"source": "news"},
)
document_3 = Document(
page_content="Building an exciting new project with LangChain - come check it out!",
metadata={"source": "tweet"},
)
document_4 = Document(
page_content="Robbers broke into the city bank and stole $1 million in cash.",
metadata={"source": "news"},
)
document_5 = Document(
page_content="Wow! That was an amazing movie. I can't wait to see it again.",
metadata={"source": "tweet"},
)
document_6 = Document(
page_content="Is the new iPhone worth the price? Read this review to find out.",
metadata={"source": "website"},
)
document_7 = Document(
page_content="The top 10 soccer players in the world right now.",
metadata={"source": "website"},
)
document_8 = Document(
page_content="LangGraph is the best framework for building stateful, agentic applications!",
metadata={"source": "tweet"},
)
document_9 = Document(
page_content="The stock market is down 500 points today due to fears of a recession.",
metadata={"source": "news"},
)
document_10 = Document(
page_content="I have a bad feeling I am going to get deleted :(",
metadata={"source": "tweet"},
)
documents = [
document_1,
document_2,
document_3,
document_4,
document_5,
document_6,
document_7,
document_8,
document_9,
document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]
vector_store.add_documents(documents=documents, ids=uuids)
# vector_store.from_documents(documents,embeddings)
Now I am here I am 2 errors:
First:
if using vector_store.from_documents(documents,embeddings)
I am getting following error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Cell In[23], line 73
68 uuids = [str(uuid4()) for _ in range(len(documents))]
70 # vector_store.add_documents(documents=documents, ids=uuids)
---> 73 vector_store.from_documents(documents,embeddings)
File u:\GENERATIVE_AI\genv\lib\site-packages\langchain_core\vectorstores\base.py:833, in VectorStore.from_documents(cls, documents, embedding, **kwargs)
831 texts = [d.page_content for d in documents]
832 metadatas = [d.metadata for d in documents]
--> 833 return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
File u:\GENERATIVE_AI\genv\lib\site-packages\langchain_pinecone\vectorstores.py:453, in PineconeVectorStore.from_texts(cls, texts, embedding, metadatas, ids, batch_size, text_key, namespace, index_name, upsert_kwargs, pool_threads, embeddings_chunk_size, async_req, id_prefix, **kwargs)
407 @classmethod
408 def from_texts(
409 cls,
(...)
424 **kwargs: Any,
425 ) -> PineconeVectorStore:
426 """Construct Pinecone wrapper from raw documents.
427
428 This is a user friendly interface that:
(...)
451 )
452 """
...
403 f"Did you mean one of the following indexes: {', '.join(index_names)}"
404 )
405 return index
ValueError: Index 'None' not found in your Pinecone project. Did you mean one of the following indexes: langchain-pinecone-learning
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...
Second:
if using vector_store.add_documents(documents=documents, ids=uuids) i am getting following error:
---------------------------------------------------------------------------
PineconeApiException Traceback (most recent call last)
Cell In[24], line 70
55 documents = [
56 document_1,
57 document_2,
(...)
65 document_10,
66 ]
68 uuids = [str(uuid4()) for _ in range(len(documents))]
---> 70 vector_store.add_documents(documents=documents, ids=uuids)
73 # vector_store.from_documents(documents,embeddings)
File u:\GENERATIVE_AI\genv\lib\site-packages\langchain_core\vectorstores\base.py:282, in VectorStore.add_documents(self, documents, **kwargs)
280 texts = [doc.page_content for doc in documents]
281 metadatas = [doc.metadata for doc in documents]
--> 282 return self.add_texts(texts, metadatas, **kwargs)
283 raise NotImplementedError(
284 f"`add_documents` and `add_texts` has not been implemented "
285 f"for {self.__class__.__name__} "
286 )
File u:\GENERATIVE_AI\genv\lib\site-packages\langchain_pinecone\vectorstores.py:175, in PineconeVectorStore.add_texts(self, texts, metadatas, ids, namespace, batch_size, embedding_chunk_size, async_req, id_prefix, **kwargs)
164 if async_req:
165 # Runs the pinecone upsert asynchronously.
...
PineconeApiException: (400)
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({'Date': 'Thu, 22 Aug 2024 08:37:54 GMT', 'Content-Type': 'application/json', 'Content-Length': '104', 'Connection': 'keep-alive', 'x-pinecone-request-latency-ms': '1094', 'x-pinecone-request-id': '4162547469429931929', 'x-envoy-upstream-service-time': '36', 'server': 'envoy'})
HTTP response body: {"code":3,"message":"Vector dimension 2048 does not match the dimension of the index 4072","details":[]}
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...
Thanks in advance.
I hope to hear from you soon.