klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added Support for Ollama for local model inference. (#1045)

Browse Source 
Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>
This commit is contained in:
Sukkrit Sharma
2023-12-22 05:10:00 +05:30
committed by GitHub
parent 210fe9bb80
commit 0f73ba9677
11 changed files with 348 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/components/data-sources/docs-site.mdx
View File

@@ -10,5 +10,5 @@ from embedchain import Pipeline as App
app = App()
app.add("https://docs.embedchain.ai/", data_type="docs_site")
app.query("What is Embedchain?")
# Answer: Embedchain is a platform that utilizes various components, including paid/proprietary ones, to provide what is believed to be the best configuration available. It uses LLM (Language Model) providers such as OpenAI, Anthpropic, Vertex_AI, GPT4ALL, Azure_OpenAI, LLAMA2, JINA, and COHERE. Embedchain allows users to import and utilize these LLM providers for their applications.'
# Answer: Embedchain is a platform that utilizes various components, including paid/proprietary ones, to provide what is believed to be the best configuration available. It uses LLM (Language Model) providers such as OpenAI, Anthpropic, Vertex_AI, GPT4ALL, Azure_OpenAI, LLAMA2, JINA, Ollama and COHERE. Embedchain allows users to import and utilize these LLM providers for their applications.'
```

27
docs/components/llms.mdx
View File

@@ -12,6 +12,7 @@ Embedchain comes with built-in support for various popular large language models
<Card title="Azure OpenAI" href="#azure-openai"></Card>
<Card title="Anthropic" href="#anthropic"></Card>
<Card title="Cohere" href="#cohere"></Card>
<Card title="Ollama" href="#Ollama"></Card>
<Card title="GPT4All" href="#gpt4all"></Card>
<Card title="JinaChat" href="#jinachat"></Card>
<Card title="Hugging Face" href="#hugging-face"></Card>
@@ -329,6 +330,32 @@ llm:
</CodeGroup>
## Ollama
Setup Ollama using https://github.com/jmorganca/ollama
<CodeGroup>
```python main.py
import os
from embedchain import Pipeline as App
# load llm configuration from config.yaml file
app = App.from_config(config_path="config.yaml")
```
```yaml config.yaml
llm:
provider: ollama
config:
model: 'llama2'
temperature: 0.5
top_p: 1
stream: true
```
</CodeGroup>
## GPT4ALL
Install related dependencies using the following command: