Spaces:
Sleeping
Sleeping
crStiv
commited on
docs: correct typos and grammar (#1839)
Browse files* Update overview.md
* Update web-search.md
docs/source/configuration/models/overview.md
CHANGED
|
@@ -43,7 +43,7 @@ You can change things like the parameters, or customize the preprompt to better
|
|
| 43 |
|
| 44 |
When querying the model for a chat response, the `chatPromptTemplate` template is used. `messages` is an array of chat messages, it has the format `[{ content: string }, ...]`. To identify if a message is a user message or an assistant message the `ifUser` and `ifAssistant` block helpers can be used.
|
| 45 |
|
| 46 |
-
The following is the default `chatPromptTemplate`, although newlines and
|
| 47 |
|
| 48 |
```handlebars
|
| 49 |
{{preprompt}}
|
|
|
|
| 43 |
|
| 44 |
When querying the model for a chat response, the `chatPromptTemplate` template is used. `messages` is an array of chat messages, it has the format `[{ content: string }, ...]`. To identify if a message is a user message or an assistant message the `ifUser` and `ifAssistant` block helpers can be used.
|
| 45 |
|
| 46 |
+
The following is the default `chatPromptTemplate`, although newlines and indentation have been added for readability. You can find the prompts used in production for HuggingChat [here](https://github.com/huggingface/chat-ui/blob/main/PROMPTS.md). The templating language used is [Handlebars](https://www.npmjs.com/package/handlebars).
|
| 47 |
|
| 48 |
```handlebars
|
| 49 |
{{preprompt}}
|
docs/source/configuration/web-search.md
CHANGED
|
@@ -7,7 +7,7 @@ Chat UI features a powerful Web Search feature. A high level overview of how it
|
|
| 7 |
3. Load each search result into playwright and scrape
|
| 8 |
4. Convert scraped HTML to Markdown tree with headings as parents
|
| 9 |
5. Create embeddings for each Markdown element
|
| 10 |
-
6. Find the
|
| 11 |
7. Get the corresponding Markdown elements and their parent, up to 8000 characters
|
| 12 |
8. Supply the information as context to the model
|
| 13 |
|
|
@@ -28,7 +28,7 @@ For locally scraped Google results, put `USE_LOCAL_WEBSEARCH=true` in your `.env
|
|
| 28 |
|
| 29 |
> SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
|
| 30 |
|
| 31 |
-
You may enable support via the `SEARXNG_QUERY_URL` where `<query>` will be
|
| 32 |
|
| 33 |
Example: `https://searxng.yourdomain.com/search?q=<query>&engines=duckduckgo,google&format=json`
|
| 34 |
|
|
|
|
| 7 |
3. Load each search result into playwright and scrape
|
| 8 |
4. Convert scraped HTML to Markdown tree with headings as parents
|
| 9 |
5. Create embeddings for each Markdown element
|
| 10 |
+
6. Find the embeddings closest to the user query using a vector similarity search (inner product)
|
| 11 |
7. Get the corresponding Markdown elements and their parent, up to 8000 characters
|
| 12 |
8. Supply the information as context to the model
|
| 13 |
|
|
|
|
| 28 |
|
| 29 |
> SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
|
| 30 |
|
| 31 |
+
You may enable support via the `SEARXNG_QUERY_URL` where `<query>` will be replaced with the query keywords. Please see [the official documentation](https://docs.searxng.org/dev/search_api.html) for more information
|
| 32 |
|
| 33 |
Example: `https://searxng.yourdomain.com/search?q=<query>&engines=duckduckgo,google&format=json`
|
| 34 |
|