{"record":{"id":"67aa3953d3f65b2b","repo":"assafelovic/gpt-researcher","slug":"llm-provider-fast-llm-model-and-smart-llm-model-a","errorCode":null,"errorMessage":"LLM_PROVIDER, FAST_LLM_MODEL and SMART_LLM_MODEL are deprecated and will be removed soon. Use FAST_LLM and SMART_LLM instead.","messagePattern":"LLM_PROVIDER, FAST_LLM_MODEL and SMART_LLM_MODEL are deprecated and will be removed soon\\. Use FAST_LLM and SMART_LLM instead\\.","errorType":"console","errorClass":"FutureWarning","httpStatus":null,"severity":"warning","filePath":"gpt_researcher/config/config.py","lineNumber":134,"sourceCode":"            elif embedding_provider == \"openai\":\n                self.embedding_model = \"text-embedding-3-large\"\n            elif embedding_provider == \"azure_openai\":\n                self.embedding_model = \"text-embedding-3-large\"\n            elif embedding_provider == \"huggingface\":\n                self.embedding_model = \"sentence-transformers/all-MiniLM-L6-v2\"\n            elif embedding_provider == \"gigachat\":\n                self.embedding_model = \"Embeddings\"\n            elif embedding_provider == \"google_genai\":\n                self.embedding_model = \"text-embedding-004\"\n            else:\n                raise Exception(\"Embedding provider not found.\")\n\n        _deprecation_warning = (\n            \"LLM_PROVIDER, FAST_LLM_MODEL and SMART_LLM_MODEL are deprecated and \"\n            \"will be removed soon. Use FAST_LLM and SMART_LLM instead.\"\n        )\n        if os.getenv(\"LLM_PROVIDER\") is not None:\n            warnings.warn(_deprecation_warning, FutureWarning, stacklevel=2)\n            self.fast_llm_provider = (\n                os.environ[\"LLM_PROVIDER\"] or self.fast_llm_provider\n            )\n            self.smart_llm_provider = (\n                os.environ[\"LLM_PROVIDER\"] or self.smart_llm_provider\n            )\n        if os.getenv(\"FAST_LLM_MODEL\") is not None:\n            warnings.warn(_deprecation_warning, FutureWarning, stacklevel=2)\n            self.fast_llm_model = os.environ[\"FAST_LLM_MODEL\"] or self.fast_llm_model\n        if os.getenv(\"SMART_LLM_MODEL\") is not None:\n            warnings.warn(_deprecation_warning, FutureWarning, stacklevel=2)\n            self.smart_llm_model = os.environ[\"SMART_LLM_MODEL\"] or self.smart_llm_model\n\n    def _set_doc_path(self, config: Dict[str, Any]) -> None:\n        self.doc_path = config['DOC_PATH']\n        if self.doc_path:\n            try:\n                self.validate_doc_path()","sourceCodeStart":116,"sourceCodeEnd":152,"githubUrl":"https://github.com/assafelovic/gpt-researcher/blob/6f998577d547b1e54ec662dac63583aa11e3b84b/gpt_researcher/config/config.py#L116-L152","documentation":"FutureWarning from Config when LLM_PROVIDER is set: LLM_PROVIDER (plus FAST_LLM_MODEL/SMART_LLM_MODEL) is deprecated in favor of the combined FAST_LLM and SMART_LLM settings. The old value is still applied to both fast and smart providers, but will be removed.","triggerScenarios":"Instantiating Config/GPTResearcher with LLM_PROVIDER defined in the environment (even if the new FAST_LLM/SMART_LLM vars are also set).","commonSituations":"Migrating from older gpt-researcher versions; leftover .env, docker-compose environment blocks, or hosting platforms (Railway/Heroku config vars) carrying LLM_PROVIDER.","solutions":["Remove LLM_PROVIDER and set FAST_LLM and SMART_LLM to provider/model strings (e.g. FAST_LLM='openai:gpt-4o-mini', SMART_LLM='openai:gpt-4o').","Audit all config stores (.env, docker-compose.yml, CI/CD variables) for LLM_PROVIDER and delete them.","Note the same deprecation message also fires for FAST_LLM_MODEL/SMART_LLM_MODEL — migrate those in the same pass."],"exampleFix":"# before\nLLM_PROVIDER=openai\nFAST_LLM_MODEL=gpt-4o-mini\nSMART_LLM_MODEL=gpt-4o\n# after\nFAST_LLM=openai:gpt-4o-mini\nSMART_LLM=openai:gpt-4o","handlingStrategy":"validation","validationCode":"import os\nassert \"LLM_PROVIDER\" not in os.environ, \"use FAST_LLM / SMART_LLM instead of LLM_PROVIDER\"","typeGuard":null,"tryCatchPattern":null,"preventionTips":["Migrate provider/model env vars in one pass (LLM_PROVIDER, FAST_LLM_MODEL, SMART_LLM_MODEL).","Centralize LLM config in FAST_LLM/SMART_LLM '<provider>:<model>' strings.","Assert absence of deprecated vars in CI startup checks."],"tags":["deprecation","configuration","llm","python"],"backgroundTag":"deprecated-env-var","analyzedSha":"6f998577d547b1e54ec662dac63583aa11e3b84b","analyzedAt":"2026-08-28T17:50:07.383Z","schemaVersion":2},"datasetVersion":"2026-08-28T21:17:43.275Z"}