# Getting PineconeApiException: (400) Reason: Bad Request HTTP response headers: HTTPHeaderDict? **URL:** \ **Category:** Support\ **Tags:** semantic-search, vector-database, embeddings\ **Created:** [August 22, 2024, 8:38am UTC](https://community.pinecone.io/t/getting-pineconeapiexception-400-reason-bad-request-http-response-headers-httpheaderdict/6420 "2024-08-22T08:38:57Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![mishraatharva](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/mishraatharva/32/3001_2.png) [@mishraatharva](https://community.pinecone.io/u/mishraatharva)\ **Post date:** [August 22, 2024, 8:38am UTC](https://community.pinecone.io/t/getting-pineconeapiexception-400-reason-bad-request-http-response-headers-httpheaderdict/6420/1 "2024-08-22T08:38:57Z")
I am using [this link](https://python.langchain.com/v0.2/docs/integrations/vectorstores/pinecone/) to learn langhain and pinecone. Just copy pasted the code as bellow: **MY CODE:** ```auto 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) ``` ```auto 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 ``` ```auto embeddings=( OllamaEmbeddings(model="gemma:2b") ##by default it ues llama2 ) ``` ```auto from langchain_pinecone import PineconeVectorStore vector_store = PineconeVectorStore(index=index, embedding=embeddings) vector_store ``` ```auto 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: ```auto --------------------------------------------------------------------------- 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: ```auto --------------------------------------------------------------------------- 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. ---
**Author:** ![ZacharyProser](https://sea2.discourse-cdn.com/flex020/user_avatar/community.pinecone.io/zacharyproser/32/1146_2.png) [@ZacharyProser](https://community.pinecone.io/u/ZacharyProser)\ **Post date:** [August 26, 2024, 2:46pm UTC](https://community.pinecone.io/t/getting-pineconeapiexception-400-reason-bad-request-http-response-headers-httpheaderdict/6420/2 "2024-08-26T14:46:08Z")
Hi @mishraatharva, Thanks for your question. I’d strongly recommend starting with [our official LangChain guide](https://docs.pinecone.io/integrations/langchain), especially if you want to learn. It looks like your first error is occurring because your index name is not defined. Your second error is a dimensionality mismatch. You need to set your Pinecone index to have the same number of dimensions that your embedding model outputs. For example, if you were using OpenAI’s text-embedding-3-small, which outputs 1536 dimensions, you would need to set your Pinecone index to 1536 dimensions when creating it. It appears there’s a mismatch between the embedding model you’re using and the dimensionality set on your index. Hope that helps! Best, Zack