mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2026-07-19 14:13:35 -04:00
[GH-ISSUE #3419] [backend] error: Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }). #2205
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @NCNeo on GitHub (Mar 7, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3419
Issue: recently install Anything LLM on my Mac Pro 2012 - chip inter E5 + 2 graphical cards.
Deploy Docker and Docker Compose thru Brew
Pull Docker Imagen from official site
Mount Storage as documentation says
export STORAGE_LOCATION=$HOME/anythingllm &&
mkdir -p $STORAGE_LOCATION &&
touch "$STORAGE_LOCATION/.env" &&
docker run -d -p 3001:3001
--cap-add SYS_ADMIN
-v ${STORAGE_LOCATION}:/app/server/storage
-v ${STORAGE_LOCATION}/.env:/app/server/.env
-e STORAGE_DIR="/app/server/storage"
mintplexlabs/anythingllm
Start service running good in https://localhost:3001
When I select the model (OpenAI with API Key), Ollama installed locally, Get in UI "Failed To Fecht" when I review the Log, get this.
025-03-07 17:49:56 [backend] error: Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }).
2025-03-07 17:49:56 at new OpenAI (/app/server/node_modules/openai/index.js:53:19)
2025-03-07 17:49:56 at openAiModels (/app/server/utils/helpers/customModels.js:91:18)
2025-03-07 17:49:56 at getCustomModels (/app/server/utils/helpers/customModels.js:43:20)
2025-03-07 17:49:56 at /app/server/endpoints/system.js:960:41
2025-03-07 17:49:56 at Layer.handle [as handle_request] (/app/server/node_modules/express/lib/router/layer.js:95:5)
2025-03-07 17:49:56 at next (/app/server/node_modules/express/lib/router/route.js:149:13)
2025-03-07 17:49:56 at /app/server/utils/middleware/multiUserProtected.js:60:7
2025-03-07 17:49:56 at Layer.handle [as handle_request] (/app/server/node_modules/express/lib/router/layer.js:95:5)
2025-03-07 17:49:56 at next (/app/server/node_modules/express/lib/router/route.js:149:13)
2025-03-07 17:49:56 at validatedRequest (/app/server/utils/middleware/validatedRequest.js:20:5)
2025-03-07 17:49:57 [backend] error: Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }).
2025-03-07 17:49:57 at new OpenAI (/app/server/node_modules/openai/index.js:53:19)
2025-03-07 17:49:57 at openAiModels (/app/server/utils/helpers/customModels.js:91:18)
2025-03-07 17:49:57 at getCustomModels (/app/server/utils/helpers/customModels.js:43:20)
2025-03-07 17:49:57 at /app/server/endpoints/system.js:960:41
2025-03-07 17:49:57 at Layer.handle [as handle_request] (/app/server/node_modules/express/lib/router/layer.js:95:5)
2025-03-07 17:49:57 at next (/app/server/node_modules/express/lib/router/route.js:149:13)
2025-03-07 17:49:57 at /app/server/utils/middleware/multiUserProtected.js:60:7
2025-03-07 17:49:57 at Layer.handle [as handle_request] (/app/server/node_modules/express/lib/router/layer.js:95:5)
2025-03-07 17:49:57 at next (/app/server/node_modules/express/lib/router/route.js:149:13)
2025-03-07 17:49:57 at validatedRequest (/app/server/utils/middleware/validatedRequest.js:20:5)
2025-03-07 17:50:04 [backend] error: TypeError: fetch failed
2025-03-07 17:50:04 at node:internal/deps/undici/undici:12618:11
2025-03-07 17:50:04 at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
2025-03-07 17:50:04 at async ollamaAIModels (/app/server/utils/helpers/customModels.js:346:18)
2025-03-07 17:50:04 at async getCustomModels (/app/server/utils/helpers/customModels.js:49:14)
2025-03-07 17:50:04 at async /app/server/endpoints/system.js:960:35
2025-03-07 17:50:04 [backend] error: TypeError: fetch failed
2025-03-07 17:50:04 at node:internal/deps/undici/undici:12618:11
2025-03-07 17:50:04 at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
2025-03-07 17:50:04 at async ollamaAIModels (/app/server/utils/helpers/customModels.js:346:18)
2025-03-07 17:50:04 at async getCustomModels (/app/server/utils/helpers/customModels.js:49:14)
2025-03-07 17:50:04 at async /app/server/endpoints/system.js:960:35
I try to find the solution thru Github or Discord, but non of this issue. Please see attached file to support the case. If there already solution of this please helpmeet to refer the documentation.
@timothycarambat commented on GitHub (Mar 9, 2025):
because
localhostdoes not work in docker for Ollama. You need to usehost.docker.internalto reach the host OS localhost. So in your casehttp://host.docker.internal:11434to reach ollama. This should be auto-detected for you if you select Ollama@NCNeo commented on GitHub (Mar 14, 2025):
Timothy in my case I used openAI and Ollama with your configuration suggested, but still have same problem. Another option?
@nepomuc commented on GitHub (Sep 7, 2025):
@timothycarambat Same problem. :/ Can you help? I simply used the run-command from you doc and want to only set up AnythingLLM with my ollama instance on my LAN.
Setting it up with openai at the onboarding also results in an error:
[backend] error: Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }).to [GH-ISSUE #3419] [backend] error: Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }).