[Doc update] update mistral example (#1012)

This commit is contained in:
Deven Patel
2023-12-15 06:12:53 +05:30
committed by GitHub
parent 151746beec
commit 0efbc80ac9
3 changed files with 12 additions and 7 deletions

View File

@@ -13,7 +13,6 @@ Use the model provided on huggingface: `mistralai/Mistral-7B-v0.1`
import os import os
from embedchain import Pipeline as App from embedchain import Pipeline as App
os.environ["OPENAI_API_KEY"] = "sk-xxx"
os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "hf_your_token" os.environ["HUGGINGFACE_ACCESS_TOKEN"] = "hf_your_token"
app = App.from_config("huggingface.yaml") app = App.from_config("huggingface.yaml")
@@ -27,6 +26,11 @@ llm:
max_tokens: 1000 max_tokens: 1000
top_p: 0.5 top_p: 0.5
stream: false stream: false
embedder:
provider: huggingface
config:
model: 'sentence-transformers/all-mpnet-base-v2'
``` ```
</CodeGroup> </CodeGroup>
</Accordion> </Accordion>

View File

@@ -1,14 +1,14 @@
from pathlib import Path
import hashlib import hashlib
import logging import logging
from typing import Optional, Dict, Any from pathlib import Path
from typing import Any, Dict, Optional
from embedchain.utils import detect_datatype from embedchain.config import AddConfig
from embedchain.data_formatter.data_formatter import DataFormatter
from embedchain.helpers.json_serializable import register_deserializable from embedchain.helpers.json_serializable import register_deserializable
from embedchain.loaders.base_loader import BaseLoader from embedchain.loaders.base_loader import BaseLoader
from embedchain.loaders.local_text import LocalTextLoader from embedchain.loaders.local_text import LocalTextLoader
from embedchain.data_formatter.data_formatter import DataFormatter from embedchain.utils import detect_datatype
from embedchain.config import AddConfig
@register_deserializable @register_deserializable

View File

@@ -196,7 +196,8 @@ def detect_datatype(source: Any) -> DataType:
formatted_source = format_source(str(source), 30) formatted_source = format_source(str(source), 30)
if url: if url:
from langchain.document_loaders.youtube import ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS from langchain.document_loaders.youtube import \
ALLOWED_NETLOCK as YOUTUBE_ALLOWED_NETLOCS
if url.netloc in YOUTUBE_ALLOWED_NETLOCS: if url.netloc in YOUTUBE_ALLOWED_NETLOCS:
logging.debug(f"Source of `{formatted_source}` detected as `youtube_video`.") logging.debug(f"Source of `{formatted_source}` detected as `youtube_video`.")