{"id":44,"library":"llamaindex","title":"LlamaIndex","description":"LlamaIndex is a data framework for building LLM-powered agents over your data. Specializes in RAG pipelines, document parsing, and agent workflows. Core package is llama-index-core. Integrations are separate packages installed from LlamaHub.","status":"active","version":"0.14.15","language":"python","source_language":"en","source_url":"https://developers.llamaindex.ai/python/framework/changes/deprecated_terms/","tags":["llamaindex","rag","agents","documents","python","llm","retrieval"],"install":[{"cmd":"pip install llama-index","lang":"bash","label":"Python (starter — includes core + default integrations)"},{"cmd":"pip install llama-index-core","lang":"bash","label":"Python (core only — add integrations separately)"},{"cmd":"pip install llama-index-core llama-index-llms-openai llama-index-embeddings-openai","lang":"bash","label":"Python (core + OpenAI)"}],"dependencies":[{"reason":"Required for OpenAI LLM access. Not included in llama-index-core.","package":"llama-index-llms-openai","optional":false},{"reason":"Required for OpenAI embeddings. Not included in llama-index-core.","package":"llama-index-embeddings-openai","optional":false},{"reason":"Required for Anthropic/Claude LLM access.","package":"llama-index-llms-anthropic","optional":true}],"imports":[{"note":"GPTVectorStoreIndex renamed to VectorStoreIndex in 0.10. Old name removed.","wrong":"from llama_index import GPTVectorStoreIndex","symbol":"VectorStoreIndex","correct":"from llama_index.core import VectorStoreIndex"},{"note":"LLMs moved to integration packages in 0.10. Install llama-index-llms-openai.","wrong":"from llama_index import OpenAI","symbol":"OpenAI (LLM)","correct":"from llama_index.llms.openai import OpenAI"},{"note":"AgentRunner, AgentWorker, FunctionCallingAgent, ReActAgent (old) all removed. Use AgentWorkflow.","wrong":"from llama_index.core.agent import AgentRunner","symbol":"AgentWorkflow","correct":"from llama_index.core.agent.workflow import AgentWorkflow"},{"note":"ServiceContext fully removed. Use Settings global object or pass params directly.","wrong":"from llama_index.core import ServiceContext\nservice_context = ServiceContext.from_defaults(llm=...)","symbol":"Settings","correct":"from llama_index.core import Settings\nSettings.llm = OpenAI(model='gpt-4o')"}],"quickstart":{"code":"from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings\nfrom llama_index.llms.openai import OpenAI\nfrom llama_index.embeddings.openai import OpenAIEmbedding\n\nSettings.llm = OpenAI(model='gpt-4o')\nSettings.embed_model = OpenAIEmbedding(model='text-embedding-3-small')\n\ndocuments = SimpleDirectoryReader('data').load_data()\nindex = VectorStoreIndex.from_documents(documents)\nquery_engine = index.as_query_engine()\nresponse = query_engine.query('What did the author do growing up?')\nprint(response)","lang":"python","description":"Minimal RAG pipeline using VectorStoreIndex with OpenAI in LlamaIndex 0.14.x."},"warnings":[{"fix":"Use Settings global object: from llama_index.core import Settings","message":"ServiceContext is fully removed. All code using ServiceContext.from_defaults() will fail.","severity":"breaking","affected_versions":"< 0.10.0"},{"fix":"Migrate to AgentWorkflow, FunctionAgent, CodeActAgent, or ReActAgent (new workflow-based)","message":"AgentRunner, AgentWorker, FunctionCallingAgent, OpenAIAgent, StructuredAgentPlanner all removed.","severity":"breaking","affected_versions":"< 0.14.0"},{"fix":"Use Workflows-based approach instead","message":"QueryPipeline class removed.","severity":"breaking","affected_versions":"< 0.14.0"},{"fix":"Migrate fully to llama-index-core and current integration packages","message":"llama-index-legacy package deprecated and removed from repository.","severity":"breaking","affected_versions":"all"},{"fix":"Use VectorStoreIndex, SimpleKeywordTableIndex etc.","message":"GPTVectorStoreIndex, GPTSimpleKeywordTableIndex and all GPT-prefixed index names removed.","severity":"breaking","affected_versions":"< 0.10.0"},{"fix":"pip install llama-index-core llama-index-llms-anthropic for Claude access","message":"pip install llama-index alone installs OpenAI integrations by default. For other providers install llama-index-core plus the specific integration package.","severity":"gotcha","affected_versions":"all"},{"fix":"Explicitly pass chat_mode if you relied on previous default behaviour","message":"index.as_chat_engine() default changed to CondensePlusContextChatEngine in 0.14.x.","severity":"gotcha","affected_versions":"< 0.14.0"},{"fix":"Ensure the directory specified in SimpleDirectoryReader (e.g., 'data') exists and contains your data files in the environment where the script is executed.","message":"SimpleDirectoryReader requires the specified directory (e.g., 'data') to exist at runtime. If the directory is missing, a ValueError will be raised.","severity":"gotcha","affected_versions":"all"}],"env_vars":null,"search_vec":"'agent':12,23,41 'build':8 'core':25,31 'data':5,15 'document':20,42 'framework':6 'index':30 'instal':36 'integr':32 'llama':29 'llama-index-cor':28 'llamahub':38 'llamaindex':1,2,39 'llm':10,44 'llm-power':9 'packag':26,35 'pars':21 'pipelin':19 'power':11 'python':43 'rag':18,40 'retriev':45 'separ':34 'special':16 'workflow':24","created_at":"2026-03-16T04:39:09.011572+00:00","updated_at":"2026-04-16T16:19:25.926555+00:00","problems":[{"fix":"Update your import statements to use `llama_index.core` for core components. For example, change `from llama_index.query_engine import RetrieverQueryEngine` to `from llama_index.core.query_engine import RetrieverQueryEngine`.","cause":"This error occurs because of a significant refactoring in LlamaIndex v0.10 and later, where core modules were moved under the `llama_index.core` namespace.","error":"ModuleNotFoundError: No module named 'llama_index.query_engine'"},{"fix":"Remove `ServiceContext` and instead configure LLMs, embedding models, etc., using the global `Settings` object or by passing them directly to the relevant LlamaIndex components. For example, use `from llama_index.core import Settings` and then `Settings.llm = OpenAI()` instead of `ServiceContext.from_defaults(llm=OpenAI())`.","cause":"The `ServiceContext` abstraction was deprecated in LlamaIndex v0.10.0 and replaced by a more modular `Settings` object for global configurations, or by directly passing parameters.","error":"ImportError: cannot import name 'ServiceContext' from 'llama_index.core'"},{"fix":"Install the specific integration package using pip. For HuggingFace LLMs, run `pip install llama-index-llms-huggingface`. The general pattern is `pip install llama-index-llms-<provider>`, `llama-index-embeddings-<provider>`, or `llama-index-vector-stores-<provider>`.","cause":"With LlamaIndex v0.10.0 and above, integrations like LLMs, embedding models, and vector stores were split into separate PyPI packages. This error indicates that the specific integration package is not installed.","error":"ModuleNotFoundError: No module named 'llama_index.llms.huggingface'"},{"fix":"Ensure all `llamaindex` packages are updated to compatible versions. If you are integrating with other libraries, they may need to be updated to support the newer LlamaIndex package structure. Manually checking `llama_index.core.__version__` might reveal the version, but the underlying issue is often a version mismatch or an outdated dependency expecting the old structure.","cause":"This error typically arises when an older part of your code or an integrated library attempts to access `__version__` directly from the top-level `llama_index` module, but in newer versions (v0.10.x and later), this attribute might have moved, for instance, to `llama_index.core.__version__` or is not exposed in the same way.","error":"AttributeError: module 'llama_index' has no attribute '__version__'"},{"fix":"Use an LLM that explicitly supports function calling, such as OpenAI's models, or ensure your custom LLM implementation correctly sets `llm.metadata.is_function_calling_model = True` and provides the required function calling methods. Alternatively, if your LLM doesn't support function calling, consider using an agent that doesn't require this capability (e.g., a ReAct agent instead of a FunctionAgent in some contexts).","cause":"This error occurs when an LlamaIndex agent workflow (like `AgentWorkflow`) requires an LLM with function calling capabilities, but the configured LLM does not expose the necessary `is_function_calling_model` metadata or does not implement the `FunctionCallingLLM` interface.","error":"ValueError: LLM must be a FunctionCallingLLM"}],"ecosystem":"pypi","meta_description":null,"install_score":75,"quickstart_score":0,"quickstart_tag":"stale","pypi_latest":null,"cli_name":"llamaindex","cli_version":"sh: 1: llamaindex: not found","type":"library","homepage":"https://www.llamaindex.ai","github":null,"docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["llm-agents","ai-ml"],"base_url":null,"auth_type":null,"provenance":{"verified_status":"passing","verified_at":"2026-06-27","last_verified":"2026-06-27","next_check":"2026-07-27","install_tag":"reviewed"}}