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

Merge pull request #460 from maozdemir/feat/documents 

feat: Get answers using preferred number of chunks
This commit is contained in:
Iván Martínez 2023-05-25 08:26:20 +02:00 committed by GitHub
parent 573c4363c4 cf709a6b7a
commit e6d6af4f82
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -22,6 +22,7 @@ PERSIST_DIRECTORY: is the folder you want your vectorstore in
MODEL_PATH: Path to your GPT4All or LlamaCpp supported LLM MODEL_PATH: Path to your GPT4All or LlamaCpp supported LLM
MODEL_N_CTX: Maximum token limit for the LLM model MODEL_N_CTX: Maximum token limit for the LLM model
EMBEDDINGS_MODEL_NAME: SentenceTransformers embeddings model name (see https://www.sbert.net/docs/pretrained_models.html) EMBEDDINGS_MODEL_NAME: SentenceTransformers embeddings model name (see https://www.sbert.net/docs/pretrained_models.html)
TARGET_SOURCE_CHUNKS: The amount of chunks (sources) that will be used to answer a question
``` ```
Note: because of the way `langchain` loads the `SentenceTransformers` embeddings, the first time you run the script it will require internet connection to download the embeddings model itself. Note: because of the way `langchain` loads the `SentenceTransformers` embeddings, the first time you run the script it will require internet connection to download the embeddings model itself.

1
example.env
View File

@ -3,3 +3,4 @@ MODEL_TYPE=GPT4All
MODEL_PATH=models/ggml-gpt4all-j-v1.3-groovy.bin MODEL_PATH=models/ggml-gpt4all-j-v1.3-groovy.bin
EMBEDDINGS_MODEL_NAME=all-MiniLM-L6-v2 EMBEDDINGS_MODEL_NAME=all-MiniLM-L6-v2
MODEL_N_CTX=1000 MODEL_N_CTX=1000
TARGET_SOURCE_DOCUMENTS=4

3
privateGPT.py
View File

@ -16,6 +16,7 @@ persist_directory = os.environ.get('PERSIST_DIRECTORY')
model_type = os.environ.get('MODEL_TYPE') model_type = os.environ.get('MODEL_TYPE')
model_path = os.environ.get('MODEL_PATH') model_path = os.environ.get('MODEL_PATH')
model_n_ctx = os.environ.get('MODEL_N_CTX') model_n_ctx = os.environ.get('MODEL_N_CTX')
target_source_chunks = int(os.environ.get('TARGET_SOURCE_CHUNKS',4))
from constants import CHROMA_SETTINGS from constants import CHROMA_SETTINGS
@ -24,7 +25,7 @@ def main():
args = parse_arguments() args = parse_arguments()
embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name) embeddings = HuggingFaceEmbeddings(model_name=embeddings_model_name)
db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS) db = Chroma(persist_directory=persist_directory, embedding_function=embeddings, client_settings=CHROMA_SETTINGS)
retriever = db.as_retriever() retriever = db.as_retriever(search_kwargs={"k": target_source_chunks})
# activate/deactivate the streaming StdOut callback for LLMs # activate/deactivate the streaming StdOut callback for LLMs
callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()] callbacks = [] if args.mute_stream else [StreamingStdOutCallbackHandler()]
# Prepare the LLM # Prepare the LLM