LocalAI: Difference between revisions

From DWIKI
(Created page with "=Scripts= ==Talk to the chat interface== #!/bin/bash echo -n "Ask me anything: " read A curl -s http://localhost:8080/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "'"$A"'", "temperature": 0.1}] }' |\ jq '.choices[].message.content' | sed 's/\\n/\n/g' | sed 's/\\"/"/g'")
 
mNo edit summary
(3 intermediate revisions by the same user not shown)
Line 1: Line 1:
=Links=
*[https://localai.io LocalAI homepage]
=HOWTO=
==List models=
curl http://localhost:8080/v1/models
==Audio to text==
*https://localai.io/features/audio-to-text/
*https://docs.llamaindex.ai/en/stable/examples/llm/localai/
==Apply model==
curl http://localhost:8080/models/apply -H "Content-Type: application/json" -d '{
  "id": "huggingface@TheBloke/Yarn-Mistral-7B-128k-GGUF/yarn-mistral-7b-128k.Q5_K_M.gguf"
}'
=Scripts=
=Scripts=
==Talk to the chat interface==
==Talk to the chat interface==
Line 4: Line 21:
  echo -n "Ask me anything: "
  echo -n "Ask me anything: "
  read A
  read A
  curl -s http://localhost:8080/v1/chat/completions \
  curl -s http://localhost:8080/v1/chat/completions \
     -H "Content-Type: application/json" \
     -H "Content-Type: application/json" \
     -d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "'"$A"'", "temperature": 0.1}] }' |\
     -d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "'"$A"'", "temperature": 0.1}] }' |\
     jq    '.choices[].message.content' | sed 's/\\n/\n/g' | sed 's/\\"/"/g'
     jq    '.choices[].message.content' | sed 's/\\n/\n/g' | sed 's/\\"/"/g'

Revision as of 19:36, 31 March 2024

Links

HOWTO

=List models

curl http://localhost:8080/v1/models

Audio to text


Apply model

curl http://localhost:8080/models/apply -H "Content-Type: application/json" -d '{
  "id": "huggingface@TheBloke/Yarn-Mistral-7B-128k-GGUF/yarn-mistral-7b-128k.Q5_K_M.gguf"
}'

Scripts

Talk to the chat interface

#!/bin/bash
echo -n "Ask me anything: "
read A
curl -s http://localhost:8080/v1/chat/completions \
   -H "Content-Type: application/json" \
   -d '{ "model": "gpt-4", "messages": [{"role": "user", "content": "'"$A"'", "temperature": 0.1}] }' |\
    jq     '.choices[].message.content' | sed 's/\\n/\n/g' | sed 's/\\"/"/g'