KeyArgo
/
private-gpt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: unify embedding models (#2027) 

* feat: unify embedding model to nomic

* docs: add embedding dimensions mismatch

* docs: fix fern
This commit is contained in:
Javier Martinez 2024-07-31 14:35:46 +02:00 committed by GitHub
parent 9027d695c1
commit 40638a18a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 24 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
fern/docs/pages/installation/troubleshooting.mdx
View File

@ -29,3 +29,21 @@ PrivateGPT uses the `AutoTokenizer` library to tokenize input text accurately. I
2. **Set Access Token for Gated Models:**
If you are using a gated model, ensure the `access_token` is set as mentioned in the previous section.
This configuration ensures that PrivateGPT can download and use the correct tokenizer for the model you are working with.
# Embedding dimensions mismatch
If you encounter an error message like `Embedding dimensions mismatch`, it is likely due to the embedding model and
current vector dimension mismatch. To resolve this issue, ensure that the model and the input data have the same vector dimensions.
By default, PrivateGPT uses `nomic-embed-text` embeddings, which have a vector dimension of 768.
If you are using a different embedding model, ensure that the vector dimensions match the model's output.
<Callout intent = "warning">
In versions below to 0.6.0, the default embedding model was `BAAI/bge-small-en-v1.5` in `huggingface` setup.
If you plan to reuse the old generated embeddings, you need to update the `settings.yaml` file to use the correct embedding model:
```yaml
huggingface:
embedding_hf_model_name: BAAI/bge-small-en-v1.5
embedding:
embed_dim: 384
```
</Callout>

2
settings-docker.yaml
View File

@ -13,7 +13,7 @@ llamacpp:
llm_hf_model_file: ${PGPT_HF_MODEL_FILE:Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf}
huggingface:
embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:BAAI/bge-small-en-v1.5}
embedding_hf_model_name: ${PGPT_EMBEDDING_HF_MODEL_NAME:nomic-ai/nomic-embed-text-v1.5}
sagemaker:
llm_endpoint_name: ${PGPT_SAGEMAKER_LLM_ENDPOINT_NAME:}

2
settings-local.yaml
View File

@ -18,7 +18,7 @@ embedding:
mode: huggingface
huggingface:
embedding_hf_model_name: BAAI/bge-small-en-v1.5
embedding_hf_model_name: nomic-ai/nomic-embed-text-v1.5
vectorstore:
database: qdrant

2
settings-vllm.yaml
View File

@ -12,7 +12,7 @@ embedding:
ingest_mode: simple
huggingface:
embedding_hf_model_name: BAAI/bge-small-en-v1.5
embedding_hf_model_name: nomic-ai/nomic-embed-text-v1.5
openai:
api_base: http://localhost:8000/v1

4
settings.yaml
View File

@ -76,10 +76,10 @@ embedding:
# Should be matching the value above in most cases
mode: huggingface
ingest_mode: simple
embed_dim: 384 # 384 is for BAAI/bge-small-en-v1.5
embed_dim: 768 # 768 is for nomic-ai/nomic-embed-text-v1.5
huggingface:
embedding_hf_model_name: BAAI/bge-small-en-v1.5
embedding_hf_model_name: nomic-ai/nomic-embed-text-v1.5
access_token: ${HF_TOKEN:}
vectorstore: