github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-01 10:54:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Simplify HumanMessages in the quick start guide (#4026)

Browse Source 
In the section `Get Message Completions from a Chat Model` of the quick
start guide, the HumanMessage doesn't need to include `Translate this
sentence from English to French.` when there is a system message.

Simplify HumanMessages in these examples can further demonstrate the
power of LLM.
This commit is contained in:
Gengliang Wang 2023-05-03 22:45:03 -07:00 committed by GitHub
parent 087a4bd2b8
commit 8af25867cb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/getting_started/getting_started.md
View File

@ -316,7 +316,7 @@ You can also pass in multiple messages for OpenAI's gpt-3.5-turbo and gpt-4 mode
```python ```python
messages = [ messages = [
SystemMessage(content="You are a helpful assistant that translates English to French."), SystemMessage(content="You are a helpful assistant that translates English to French."),
HumanMessage(content="Translate this sentence from English to French. I love programming.") HumanMessage(content="I love programming.")
] ]
chat(messages) chat(messages)
# -> AIMessage(content="J'aime programmer.", additional_kwargs={}) # -> AIMessage(content="J'aime programmer.", additional_kwargs={})
@ -327,22 +327,22 @@ You can go one step further and generate completions for multiple sets of messag
batch_messages = [ batch_messages = [
[ [
SystemMessage(content="You are a helpful assistant that translates English to French."), SystemMessage(content="You are a helpful assistant that translates English to French."),
HumanMessage(content="Translate this sentence from English to French. I love programming.") HumanMessage(content="I love programming.")
], ],
[ [
SystemMessage(content="You are a helpful assistant that translates English to French."), SystemMessage(content="You are a helpful assistant that translates English to French."),
HumanMessage(content="Translate this sentence from English to French. I love artificial intelligence.") HumanMessage(content="I love artificial intelligence.")
], ],
] ]
result = chat.generate(batch_messages) result = chat.generate(batch_messages)
result result
# -> LLMResult(generations=[[ChatGeneration(text="J'aime programmer.", generation_info=None, message=AIMessage(content="J'aime programmer.", additional_kwargs={}))], [ChatGeneration(text="J'aime l'intelligence artificielle.", generation_info=None, message=AIMessage(content="J'aime l'intelligence artificielle.", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}}) # -> LLMResult(generations=[[ChatGeneration(text="J'aime programmer.", generation_info=None, message=AIMessage(content="J'aime programmer.", additional_kwargs={}))], [ChatGeneration(text="J'aime l'intelligence artificielle.", generation_info=None, message=AIMessage(content="J'aime l'intelligence artificielle.", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 57, 'completion_tokens': 20, 'total_tokens': 77}})
``` ```
You can recover things like token usage from this LLMResult: You can recover things like token usage from this LLMResult:
``` ```
result.llm_output['token_usage'] result.llm_output['token_usage']
# -> {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89} # -> {'prompt_tokens': 57, 'completion_tokens': 20, 'total_tokens': 77}
``` ```

14
docs/modules/models/chat/getting_started.ipynb
View File

@ -107,7 +107,7 @@
"source": [ "source": [
"messages = [\n", "messages = [\n",
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n", " SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n", " HumanMessage(content=\"I love programming.\")\n",
"]\n", "]\n",
"chat(messages)" "chat(messages)"
] ]
@ -131,7 +131,7 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}})" "LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 57, 'completion_tokens': 20, 'total_tokens': 77}})"
] ]
}, },
"execution_count": 5, "execution_count": 5,
@ -143,11 +143,11 @@
"batch_messages = [\n", "batch_messages = [\n",
" [\n", " [\n",
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n", " SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
" HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n", " HumanMessage(content=\"I love programming.\")\n",
" ],\n", " ],\n",
" [\n", " [\n",
" SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n", " SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
" HumanMessage(content=\"Translate this sentence from English to French. I love artificial intelligence.\")\n", " HumanMessage(content=\"I love artificial intelligence.\")\n",
" ],\n", " ],\n",
"]\n", "]\n",
"result = chat.generate(batch_messages)\n", "result = chat.generate(batch_messages)\n",
@ -171,9 +171,9 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"{'token_usage': {'prompt_tokens': 71,\n", "{'token_usage': {'prompt_tokens': 57,\n",
" 'completion_tokens': 18,\n", " 'completion_tokens': 20,\n",
" 'total_tokens': 89}}" " 'total_tokens': 77}}"
] ]
}, },
"execution_count": 6, "execution_count": 6,