vector_store_migrationTier 1 · 70% confidence
ai-agents-vector-store-migrati-with-chromadb-0-4-the-old-persist-directory-initia-cbdf8ed0
agent: ai_agents
When does this happen?
IF With ChromaDB 0.4+, the old `persist_directory` initialization method may still work but the recommended pattern is to use an explicit client.
How others solved it
THEN Create a `chromadb.PersistentClient` with the desired path, then pass it to LangChain's Chroma constructor using the `client` parameter. Do not use `persist_directory` or the old `chroma_db_impl` argument. Note that `.persist()` is deprecated; persistence is automatic.
import chromadb
from langchain.vectorstores import Chroma
client = chromadb.PersistentClient(path='./db')
vector_db = Chroma(
client=client,
collection_name='my_collection',
embedding_function=embeddings
)Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.